fix(engram): the semantic leg was deleting 234 memory records per boot

The accumulated retrieval stack (iterations 1-9) put the claim-24 semantic leg and the claim-10 associative leg on engram_search_json — the function ~40 internal .el call sites already used as a KEYED read. Seven of those sites delete every record that comes back ("prune all existing X nodes, keep exactly one"): memory.el:176, sessions.el:250/268/444/523, soul.el:359. mem_boot_count_inc() calls engram_search_json("soul:boot_count", 50) and engram_forget()s all 50 results. With a lexical leg that returned 1 record. With a semantic leg it returns 50 — the 49 nearest neighbours of the STRING "soul:boot_count" — and the soul deletes them. MEASURED on the harness corpus, isolated, read-only, zero writes from any caller: 234 node records destroyed in a single boot. The deletion list is the soul's own lookup result list, in rank order. Casualties include 6 Knowledge nodes, a layer-1 "CORE IDENTITY - GENESIS, LINEAGE" Memory, the value node kn-58874a74, and the gold answers to 8 of the 75 gold-set queries. After the fix: 1 deletion, which is the one the code intends. THE BOUNDARY, from Will. Claim 24 authorises the vector index "to respond to EMBEDDING SEARCH QUERIES by returning the node records whose embedding vectors have the highest cosine similarity to a query vector". A keyed state read is not an embedding search query; it is the identifier-keyed retrieval of claim 23 ("node records are stored under a key encoding the node identifier"). One function served both, so a nearest neighbour of "soul:boot_count" was treated as a boot counter. So: engram_search_json returns to its lexical contract, and the legs move to engram_recall_json, which is what /api/neuron/recall reaches — the route the MCP wrapper, the app, and this harness all call. Retrieval quality on that route is unchanged by construction. MEASURED, 75-query extended gold set, embedded corpus, vs the iteration-9 baseline: +3 / -0 (q15, q28, q60), p=0.2500, hit@5 53.8 -> 58.5%, latency 1.02x, every regression guard held, nonsense 10/10. Net +3 against a floor of 6 is NOT-SHOWN and I am not calling it an improvement. The deliverable is the defect. Diagnostics kept, env-gated (EG_DIAG / EG_DIAG_ID), zero cost when unset: node/embedding census at load, per-query leg dump, and a FORGET log — the last is the regression detector for exactly this class of bug. LIMIT, stated: handle_api_search_knowledge still uses the lexical function. It is a retrieval surface and arguably wants the legs, but nothing in this harness measures it, so I did not change unmeasured behaviour.
measure: claim 24 unflooring is +4 (NOT-SHOWN); asymmetric embedding prefixes are -5 (discarded)
2026-08-07 18:12:43 -05:00 · 2026-08-07 17:45:05 -05:00 · 2026-08-07 17:34:58 -05:00 · 2026-08-07 16:58:34 -05:00 · 2026-08-07 15:55:42 -05:00 · 2026-08-07 15:51:49 -05:00
38 changed files with 25269 additions and 15 deletions
@@ -450,7 +450,12 @@ fn handle_api_recall(method: String, path: String, body: String) -> String {
    if str_eq(eff_q, "") {
        return api_or_empty(engram_scan_nodes_json(limit, 0))
    }
-    let results: String = engram_search_json(eff_q, limit)
+    // engram_recall_json, not engram_search_json: this route IS the retrieval
+    // surface (claim 24's "embedding search queries"), so it gets the semantic
+    // and associative legs. engram_search_json stays lexical because ~40
+    // internal call sites pass a KEY and seven of them delete every record
+    // that comes back — see the boundary note above eg_search_json_impl.
+    let results: String = engram_recall_json(eff_q, limit)
    return api_or_empty(results)
 }

@@ -0,0 +1,21 @@
+import numpy as np, json, urllib.request
+SP="/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad"
+np.seterr(all='ignore')
+M=np.load(SP+'/emb.npy'); eids=open(SP+'/ids.txt',encoding='utf-8',errors='surrogateescape').read().split('\n')
+eidx={k:i for i,k in enumerate(eids)}
+gold=json.load(open("/Users/timlingo/Development/neuron-technologies/_wt-assoc-leg/tools/retrieval-eval/gold_set.json"))['queries']
+VALS=sorted({r for q in gold if q['category']=='paraphrase' for r in q['relevant']})
+VI=[eidx[v] for v in VALS]
+def emb(t):
+    b=json.dumps({"model":"nomic-embed-text","prompt":t}).encode()
+    r=urllib.request.Request("http://127.0.0.1:11434/api/embeddings",data=b,headers={"Content-Type":"application/json"})
+    v=np.array(json.load(urllib.request.urlopen(r,timeout=60))["embedding"],dtype=np.float32)
+    return v/(np.linalg.norm(v)+1e-9)
+print("qid  cat         bestValueNodeGlobalRank   goldGlobalRank  goldSiblingRank")
+for q in gold:
+    if q['category']!='paraphrase': continue
+    v=emb(q['query']); s=M@v; s[~np.isfinite(s)]=-1
+    ranks=sorted(int((s>s[j]).sum())+1 for j in VI)
+    g=eidx[q['relevant'][0]]; gr=int((s>s[g]).sum())+1
+    sv=np.array([s[j] for j in VI]); sib=int((sv>s[g]).sum())+1
+    print("%-4s %-11s best=%-5d (top3 val ranks %s)  gold=%-5d sib=%d" % (q['id'],q['category'],ranks[0],ranks[:3],gr,sib))
@@ -0,0 +1,43 @@
+import json,sys,pickle,numpy as np,itertools
+sys.path.insert(0,'.')
+from policy2 import legs3,outcome,G,NODES,merge
+# cache per-query leg id-lists, floored and unfloored
+cache={}
+for q in G['queries']:
+    Lf,Sf,Af=legs3(q['query'])
+    Lu,Su,Au=legs3(q['query'],unfloor=True)
+    cache[q['id']]=dict(L=Lf,Sf=Sf,A=Af,Su=Su,Au=Au)
+pickle.dump(cache,open('ceil.pkl','wb'))
+def mrg(pattern,L,S,A,lim=10):
+    out=[];p={'L':0,'S':0,'A':0};src={'L':L,'S':S,'A':A}
+    i=0
+    while len(out)<lim:
+        prog=False
+        for ch in pattern:
+            lst=src[ch]
+            if p[ch]<len(lst):
+                x=lst[p[ch]];p[ch]+=1;prog=True
+                if x not in out: out.append(x)
+                if len(out)>=lim: return out
+        if not prog: break
+    return out
+def ev(pattern,unfl):
+    res={}
+    for q in G['queries']:
+        c=cache[q['id']]
+        S=c['Su'] if unfl else c['Sf']
+        ids=[NODES[i]['id'] for i in mrg(pattern,c['L'],S,c['A'],10)]
+        res[q['id']]=outcome(q,ids)
+    return res
+base=ev('LSA',False)
+print("baseline",sum(base.values()))
+best=[]
+pats=['LSA','LAS','SLA','ALS','SAL','ASL','LSSA','LSASA','LSAA','LSSAA','LSAS','SSLA','LLSA','SALSA','LSAAS']
+for unfl in (False,True):
+    for p in pats:
+        r=ev(p,unfl)
+        g=sorted(k for k in base if r[k] and not base[k]);l=sorted(k for k in base if base[k] and not r[k])
+        best.append((len(g)-len(l),p,unfl,g,l))
+best.sort(reverse=True)
+for n,p,u,g,l in best[:10]:
+    print("net=%+d  pat=%-6s unfloor=%s gains=%s losses=%s"%(n,p,u,g,l))
@@ -0,0 +1,146 @@
+{
+ "baseline": "bm25lex",
+ "candidate": "wsclaim24",
+ "n_shared_queries": 38,
+ "fixed_by_candidate": [
+  "q14",
+  "q25"
+ ],
+ "broken_by_candidate": [
+  "q15",
+  "q28",
+  "q33",
+  "q34"
+ ],
+ "discordant": 6,
+ "net_queries": -2,
+ "mcnemar_exact_p": 0.6875,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1184.4,
+  "latency_ms_p95": 1620.0,
+  "latency_ms_max": 1655.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5768475572047,
+  "recall@10": 0.6563414759843332,
+  "precision@5": 0.19428571428571437,
+  "mrr@10": 0.5026530612244898,
+  "nonsense_clean": "0/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 524.8,
+  "latency_ms_p95": 738.7,
+  "latency_ms_max": 755.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.5,
+    "recall@5": 0.07575757575757576,
+    "recall@10": 0.13636363636363635,
+    "mrr@10": 0.23214285714285712
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 0,
+    "avg_false_positives": 10.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6923076923076923,
+    "recall@5": 0.6923076923076923,
+    "recall@10": 0.7692307692307693,
+    "mrr@10": 0.29423076923076924
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5335884353741497,
+    "recall@10": 0.5933956916099773,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {
+  "baseline": {
+   "runs": 2,
+   "hit@5_min": 0.7428571428571429,
+   "hit@5_max": 0.7428571428571429,
+   "spread_queries": 0
+  }
+ }
+}
@@ -0,0 +1,149 @@
+{
+ "baseline": "unfloor-clean",
+ "candidate": "splitfix",
+ "n_shared_queries": 75,
+ "fixed_by_candidate": [
+  "q15",
+  "q28",
+  "q60"
+ ],
+ "broken_by_candidate": [],
+ "discordant": 3,
+ "net_queries": 3,
+ "mcnemar_exact_p": 0.25,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.5384615384615384,
+  "recall@5": 0.44907176157176154,
+  "recall@10": 0.5380300255300255,
+  "precision@5": 0.13230769230769232,
+  "mrr@10": 0.32437728937728944,
+  "nonsense_clean": "10/10",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 632.5,
+  "latency_ms_p95": 992.5,
+  "latency_ms_max": 1177.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.5,
+    "recall@5": 0.07575757575757576,
+    "recall@10": 0.13636363636363635,
+    "mrr@10": 0.23214285714285712
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.3,
+    "recall@5": 0.3,
+    "recall@10": 0.4,
+    "mrr@10": 0.11638888888888889
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 10,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6923076923076923,
+    "recall@5": 0.6923076923076923,
+    "recall@10": 0.7692307692307693,
+    "mrr@10": 0.29423076923076924
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5335884353741497,
+    "recall@10": 0.5933956916099773,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.5846153846153846,
+  "recall@5": 0.48102442429365505,
+  "recall@10": 0.5692415490492414,
+  "precision@5": 0.14153846153846153,
+  "mrr@10": 0.3351709401709402,
+  "nonsense_clean": "10/10",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 646.9,
+  "latency_ms_p95": 1028.5,
+  "latency_ms_max": 1197.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.15967365967365968,
+    "mrr@10": 0.24166666666666667
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.43333333333333335,
+    "mrr@10": 0.12120370370370372
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 10,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.7692307692307693,
+    "recall@5": 0.7692307692307693,
+    "recall@10": 0.8461538461538461,
+    "mrr@10": 0.33269230769230773
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5335884353741497,
+    "recall@10": 0.5775226757369615,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {}
+}
@@ -0,0 +1,150 @@
+{
+ "baseline": "assoc-leg",
+ "candidate": "semseed",
+ "n_shared_queries": 38,
+ "fixed_by_candidate": [
+  "q18",
+  "q19",
+  "q22"
+ ],
+ "broken_by_candidate": [
+  "q11"
+ ],
+ "discordant": 4,
+ "net_queries": 2,
+ "mcnemar_exact_p": 0.625,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.6285714285714286,
+  "recall@5": 0.45309194773480493,
+  "recall@10": 0.5405733155733157,
+  "precision@5": 0.17714285714285719,
+  "mrr@10": 0.42650793650793645,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1228.5,
+  "latency_ms_p95": 1681.8,
+  "latency_ms_max": 1718.6,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.07342657342657342,
+    "recall@10": 0.24825174825174826,
+    "mrr@10": 0.22777777777777777
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.38461538461538464,
+    "recall@5": 0.38461538461538464,
+    "recall@10": 0.38461538461538464,
+    "mrr@10": 0.17307692307692307
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.8571428571428571,
+    "recall@5": 0.4882369614512472,
+    "recall@10": 0.6329365079365079,
+    "mrr@10": 0.6634920634920636
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.2222222222222222,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.6857142857142857,
+  "recall@5": 0.5213459159887731,
+  "recall@10": 0.6027048348476919,
+  "precision@5": 0.18285714285714294,
+  "mrr@10": 0.4608730158730158,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1227.1,
+  "latency_ms_p95": 1692.6,
+  "latency_ms_max": 1710.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.07342657342657344,
+    "recall@10": 0.24825174825174823,
+    "mrr@10": 0.20833333333333334
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.7142857142857143,
+    "recall@5": 0.40093537414965985,
+    "recall@10": 0.5150226757369615,
+    "mrr@10": 0.6507936507936508
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {
+  "baseline": {
+   "runs": 2,
+   "hit@5_min": 0.6285714285714286,
+   "hit@5_max": 0.6285714285714286,
+   "spread_queries": 0
+  },
+  "candidate": {
+   "runs": 2,
+   "hit@5_min": 0.6857142857142857,
+   "hit@5_max": 0.6857142857142857,
+   "spread_queries": 0
+  }
+ }
+}
@@ -0,0 +1,146 @@
+{
+ "baseline": "bm25lex",
+ "candidate": "wordstart",
+ "n_shared_queries": 38,
+ "fixed_by_candidate": [
+  "q35"
+ ],
+ "broken_by_candidate": [],
+ "discordant": 1,
+ "net_queries": 1,
+ "mcnemar_exact_p": 1.0,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1184.4,
+  "latency_ms_p95": 1620.0,
+  "latency_ms_max": 1655.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "3/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 542.6,
+  "latency_ms_p95": 741.3,
+  "latency_ms_max": 758.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 3,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {
+  "baseline": {
+   "runs": 2,
+   "hit@5_min": 0.7428571428571429,
+   "hit@5_max": 0.7428571428571429,
+   "spread_queries": 0
+  },
+  "candidate": {
+   "runs": 2,
+   "hit@5_min": 0.7428571428571429,
+   "hit@5_max": 0.7428571428571429,
+   "spread_queries": 0
+  }
+ }
+}
@@ -0,0 +1,154 @@
+{
+ "baseline": "hybrid-semantic",
+ "candidate": "semseed",
+ "n_shared_queries": 38,
+ "fixed_by_candidate": [
+  "q18",
+  "q19",
+  "q22",
+  "q27",
+  "q28",
+  "q29",
+  "q31"
+ ],
+ "broken_by_candidate": [
+  "q11"
+ ],
+ "discordant": 8,
+ "net_queries": 6,
+ "mcnemar_exact_p": 0.0703125,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "candidate better",
+ "baseline_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.5142857142857142,
+  "recall@5": 0.4409013605442177,
+  "recall@10": 0.5047619047619047,
+  "precision@5": 0.15428571428571433,
+  "mrr@10": 0.38746031746031745,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1219.7,
+  "latency_ms_p95": 1667.1,
+  "latency_ms_max": 1720.2,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.0,
+    "recall@5": 0.0,
+    "recall@10": 0.0,
+    "mrr@10": 0.0
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.38461538461538464,
+    "recall@5": 0.38461538461538464,
+    "recall@10": 0.38461538461538464,
+    "mrr@10": 0.17307692307692307
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.8571428571428571,
+    "recall@5": 0.4902210884353741,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.6634920634920636
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.2222222222222222,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.6857142857142857,
+  "recall@5": 0.5213459159887731,
+  "recall@10": 0.6027048348476919,
+  "precision@5": 0.18285714285714294,
+  "mrr@10": 0.4608730158730158,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1227.1,
+  "latency_ms_p95": 1692.6,
+  "latency_ms_max": 1710.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.07342657342657344,
+    "recall@10": 0.24825174825174823,
+    "mrr@10": 0.20833333333333334
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.7142857142857143,
+    "recall@5": 0.40093537414965985,
+    "recall@10": 0.5150226757369615,
+    "mrr@10": 0.6507936507936508
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {
+  "baseline": {
+   "runs": 2,
+   "hit@5_min": 0.5142857142857142,
+   "hit@5_max": 0.5142857142857142,
+   "spread_queries": 0
+  },
+  "candidate": {
+   "runs": 2,
+   "hit@5_min": 0.6857142857142857,
+   "hit@5_max": 0.6857142857142857,
+   "spread_queries": 0
+  }
+ }
+}
@@ -0,0 +1,166 @@
+{
+ "baseline": "main-ext",
+ "candidate": "stack-ext",
+ "n_shared_queries": 75,
+ "fixed_by_candidate": [
+  "q10",
+  "q15",
+  "q16",
+  "q18",
+  "q19",
+  "q20",
+  "q21",
+  "q22",
+  "q26",
+  "q27",
+  "q28",
+  "q29",
+  "q31",
+  "q35",
+  "q37",
+  "q40",
+  "q44",
+  "q48",
+  "q49",
+  "q50"
+ ],
+ "broken_by_candidate": [],
+ "discordant": 20,
+ "net_queries": 20,
+ "mcnemar_exact_p": 1.9073486328125e-06,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "candidate better",
+ "baseline_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.18461538461538463,
+  "recall@5": 0.14510073260073258,
+  "recall@10": 0.1794871794871795,
+  "precision@5": 0.06461538461538462,
+  "mrr@10": 0.15847985347985344,
+  "nonsense_clean": "9/10",
+  "superseded_outranks": "1/3",
+  "latency_ms_p50": 1380.2,
+  "latency_ms_p95": 2293.8,
+  "latency_ms_max": 2879.1,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.0,
+    "recall@5": 0.0,
+    "recall@10": 0.0,
+    "mrr@10": 0.0
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.0,
+    "recall@5": 0.0,
+    "recall@10": 0.0,
+    "mrr@10": 0.0
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 9,
+    "avg_false_positives": 1.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.0,
+    "recall@5": 0.0,
+    "recall@10": 0.0,
+    "mrr@10": 0.0
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.8571428571428571,
+    "recall@5": 0.4902210884353741,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.5965986394557822
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.0,
+    "recall@5": 0.0,
+    "recall@10": 0.3333333333333333,
+    "mrr@10": 0.041666666666666664,
+    "outranks": 1
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.47692307692307695,
+  "recall@5": 0.3750415183107491,
+  "recall@10": 0.45561340369032677,
+  "precision@5": 0.12307692307692313,
+  "mrr@10": 0.3055555555555555,
+  "nonsense_clean": "10/10",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 640.9,
+  "latency_ms_p95": 1011.1,
+  "latency_ms_max": 1190.3,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.16666666666666666,
+    "recall@5": 0.16666666666666666,
+    "recall@10": 0.26666666666666666,
+    "mrr@10": 0.0762037037037037
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 10,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {}
+}
@@ -0,0 +1,147 @@
+{
+ "baseline": "semseed",
+ "candidate": "bm25lex",
+ "n_shared_queries": 38,
+ "fixed_by_candidate": [
+  "q10",
+  "q11"
+ ],
+ "broken_by_candidate": [],
+ "discordant": 2,
+ "net_queries": 2,
+ "mcnemar_exact_p": 0.5,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.6857142857142857,
+  "recall@5": 0.5213459159887731,
+  "recall@10": 0.6027048348476919,
+  "precision@5": 0.18285714285714294,
+  "mrr@10": 0.4608730158730158,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1227.1,
+  "latency_ms_p95": 1692.6,
+  "latency_ms_max": 1710.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.07342657342657344,
+    "recall@10": 0.24825174825174823,
+    "mrr@10": 0.20833333333333334
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.7142857142857143,
+    "recall@5": 0.40093537414965985,
+    "recall@10": 0.5150226757369615,
+    "mrr@10": 0.6507936507936508
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1184.4,
+  "latency_ms_p95": 1620.0,
+  "latency_ms_max": 1655.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {
+  "baseline": {
+   "runs": 2,
+   "hit@5_min": 0.6857142857142857,
+   "hit@5_max": 0.6857142857142857,
+   "spread_queries": 0
+  },
+  "candidate": {
+   "runs": 2,
+   "hit@5_min": 0.7428571428571429,
+   "hit@5_max": 0.7428571428571429,
+   "spread_queries": 0
+  }
+ }
+}
@@ -0,0 +1,155 @@
+{
+ "baseline": "stack-ext",
+ "candidate": "unfloor-clean",
+ "n_shared_queries": 75,
+ "fixed_by_candidate": [
+  "q14",
+  "q25",
+  "q43",
+  "q52",
+  "q63",
+  "q67"
+ ],
+ "broken_by_candidate": [
+  "q15",
+  "q28"
+ ],
+ "discordant": 8,
+ "net_queries": 4,
+ "mcnemar_exact_p": 0.2890625,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.47692307692307695,
+  "recall@5": 0.3750415183107491,
+  "recall@10": 0.45561340369032677,
+  "precision@5": 0.12307692307692313,
+  "mrr@10": 0.3055555555555555,
+  "nonsense_clean": "10/10",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 640.9,
+  "latency_ms_p95": 1011.1,
+  "latency_ms_max": 1190.3,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.16666666666666666,
+    "recall@5": 0.16666666666666666,
+    "recall@10": 0.26666666666666666,
+    "mrr@10": 0.0762037037037037
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 10,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.5384615384615384,
+  "recall@5": 0.44907176157176154,
+  "recall@10": 0.5380300255300255,
+  "precision@5": 0.13230769230769232,
+  "mrr@10": 0.32437728937728944,
+  "nonsense_clean": "10/10",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 632.5,
+  "latency_ms_p95": 992.5,
+  "latency_ms_max": 1177.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.5,
+    "recall@5": 0.07575757575757576,
+    "recall@10": 0.13636363636363635,
+    "mrr@10": 0.23214285714285712
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.3,
+    "recall@5": 0.3,
+    "recall@10": 0.4,
+    "mrr@10": 0.11638888888888889
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 10,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6923076923076923,
+    "recall@5": 0.6923076923076923,
+    "recall@10": 0.7692307692307693,
+    "mrr@10": 0.29423076923076924
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5335884353741497,
+    "recall@10": 0.5933956916099773,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {}
+}
@@ -0,0 +1,158 @@
+{
+ "baseline": "unfloor-clean",
+ "candidate": "semsub",
+ "n_shared_queries": 75,
+ "fixed_by_candidate": [
+  "q24",
+  "q39",
+  "q42"
+ ],
+ "broken_by_candidate": [
+  "q18",
+  "q19",
+  "q22",
+  "q31",
+  "q43",
+  "q44",
+  "q52",
+  "q63"
+ ],
+ "discordant": 11,
+ "net_queries": -5,
+ "mcnemar_exact_p": 0.2265625,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.5384615384615384,
+  "recall@5": 0.44907176157176154,
+  "recall@10": 0.5380300255300255,
+  "precision@5": 0.13230769230769232,
+  "mrr@10": 0.32437728937728944,
+  "nonsense_clean": "10/10",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 632.5,
+  "latency_ms_p95": 992.5,
+  "latency_ms_max": 1177.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.5,
+    "recall@5": 0.07575757575757576,
+    "recall@10": 0.13636363636363635,
+    "mrr@10": 0.23214285714285712
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.3,
+    "recall@5": 0.3,
+    "recall@10": 0.4,
+    "mrr@10": 0.11638888888888889
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 10,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6923076923076923,
+    "recall@5": 0.6923076923076923,
+    "recall@10": 0.7692307692307693,
+    "mrr@10": 0.29423076923076924
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5335884353741497,
+    "recall@10": 0.5933956916099773,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 75,
+  "n_scored": 65,
+  "hit@5": 0.46153846153846156,
+  "recall@5": 0.3889430014430015,
+  "recall@10": 0.4887681762681762,
+  "precision@5": 0.12307692307692313,
+  "mrr@10": 0.30181318681318675,
+  "nonsense_clean": "10/10",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 634.4,
+  "latency_ms_p95": 988.3,
+  "latency_ms_max": 1184.5,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.06060606060606061,
+    "recall@10": 0.12121212121212122,
+    "mrr@10": 0.19047619047619047
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "heldout_paraphrase": {
+    "n": 30,
+    "hit@5": 0.23333333333333334,
+    "recall@5": 0.23333333333333334,
+    "recall@10": 0.3,
+    "mrr@10": 0.08925925925925927
+   },
+   "nonsense": {
+    "n": 10,
+    "clean": 10,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.5384615384615384,
+    "recall@5": 0.5384615384615384,
+    "recall@10": 0.7692307692307693,
+    "mrr@10": 0.26324786324786326
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5596655328798186,
+    "recall@10": 0.5775226757369615,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {}
+}
@@ -0,0 +1,43 @@
+import json,sys,time,urllib.request,threading,queue
+SRC="/Users/timlingo/neuron-memory-backups/snapshot-pre-repair-20260806.json"
+OUT=sys.argv[1]
+URL="http://127.0.0.1:11434/api/embeddings"; MODEL="nomic-embed-text"
+MAXB=2000  # ENGRAM_EMBED_MAX_CHARS, applied to bytes as the C code does
+d=json.load(open(SRC,encoding='utf-8',errors='surrogateescape'))
+tasks=[]
+for n in d["nodes"]:
+    c=n.get("content") or ""; t=n.get("node_type") or ""
+    if len(c)<8: continue                     # eg_embed_eligible
+    if t in ("InternalStateEvent","Tag"): continue
+    b=c.encode('utf-8',errors='surrogateescape')[:MAXB]
+    tasks.append((n.get("id") or "", "search_document: "+b.decode('utf-8',errors='replace')))
+del d
+print("tasks",len(tasks),flush=True)
+q=queue.Queue(); [q.put(t) for t in tasks]
+lock=threading.Lock(); f=open(OUT,"w",encoding="utf-8",errors="surrogateescape"); done=[0]; t0=time.time(); fails=[0]
+def work():
+    while True:
+        try: nid,txt=q.get_nowait()
+        except queue.Empty: return
+        v=None
+        for attempt in range(3):
+            try:
+                body=json.dumps({"model":MODEL,"prompt":txt}).encode()
+                r=urllib.request.Request(URL,data=body,headers={"Content-Type":"application/json"})
+                with urllib.request.urlopen(r,timeout=120) as fh: v=json.load(fh)["embedding"]
+                break
+            except Exception as e:
+                if attempt==2:
+                    with lock: fails[0]+=1
+                time.sleep(0.5)
+        with lock:
+            if v: f.write(nid+"\t"+",".join("%.5g"%x for x in v)+"\n")
+            done[0]+=1
+            if done[0]%2000==0:
+                el=time.time()-t0
+                print("%d/%d  %.1f/s  eta %.1fmin  fails=%d"%(done[0],len(tasks),done[0]/el,(len(tasks)-done[0])/(done[0]/el)/60,fails[0]),flush=True)
+                f.flush()
+ths=[threading.Thread(target=work) for _ in range(8)]
+[t.start() for t in ths]; [t.join() for t in ths]
+f.close()
+print("DONE",done[0],"fails",fails[0],"secs %.1f"%(time.time()-t0),flush=True)
@@ -0,0 +1,353 @@
+#!/usr/bin/env python3
+"""
+extend_gold_set.py — append a HELD-OUT test set to the existing 38-query gold set.
+
+WHY THIS EXISTS
+    Iteration 7 measured the instrument's own ceiling: from the current baseline
+    only 9 of 38 queries can still move, and only +3 gross / +1 net is reachable
+    by anything constructible. The decision floor is 6. An instrument whose
+    ceiling is below its own floor cannot certify or refute anything, so the
+    gold set — not the retriever — became the blocker.
+
+    This script does NOT touch q01..q38. It loads gold_set.json verbatim and
+    appends new queries numbered from q39 up, so every prior result file, every
+    committed baseline, and every per-query id stays valid and comparable.
+
+WHAT IS ADDED, AND WHY EACH ADDITION IS HONEST
+    heldout_paraphrase  Targets were sampled MECHANICALLY (fixed seed 8080) from
+                        corpus nodes that are addressable, 500-2600 chars, of a
+                        real content type, and NOT part of a duplicate cluster
+                        larger than 3. The existing gold answer space was
+                        excluded, so no new query can be answered by a node the
+                        old set already used. Queries were then authored by
+                        reading ONLY the sampled node text — no retrieval was run
+                        against any build before authoring, so the set cannot be
+                        fitted to a candidate. The same zero-overlap proof the
+                        original paraphrase category uses is enforced here: if a
+                        single content word of the query appears anywhere in the
+                        target's label, content or tags, the query is REJECTED,
+                        not quietly kept.
+
+                        This is the category the old set could not measure. Its
+                        13 original paraphrase queries and all 6 associative
+                        queries share ONE answer space — the 13 `Self - Values
+                        (grounded)` children (iteration 3, finding 3). So 19 of
+                        35 scored queries tested retrieval against a single
+                        13-node neighbourhood. These do not touch that
+                        neighbourhood at all.
+
+    nonsense            Extra controls, fully mechanical: a string qualifies only
+                        if NONE of its tokens occurs anywhere in the corpus.
+                        A semantic leg has a nearest neighbour for gibberish too,
+                        so widening this control is the guard against a retriever
+                        that "improves" recall by answering everything.
+
+WHAT THIS SCRIPT DELIBERATELY DOES NOT DO
+    It does not add exact_rare or phrase queries. Both categories are already at
+    100% on the current stack; adding more would add regression-guard ballast
+    that no candidate can move, which is precisely the defect being fixed.
+
+usage:
+    python3 extend_gold_set.py <snapshot.json> [--base gold_set.json]
+                               [--out gold_set_extended.json] [--check]
+"""
+import argparse
+import hashlib
+import json
+import os
+import re
+import sys
+from collections import defaultdict
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+
+TOKEN = re.compile(r"[a-z0-9][a-z0-9\-']*")
+
+# Identical stopword list to build_gold_set.py. Duplicated deliberately: this
+# file must be able to re-prove its own queries without importing a module whose
+# constants could drift.
+STOP = set("""
+a about above after again against all also am an and any are aren't as at be because been
+before being below between both but by can can't cannot could couldn't did didn't do does
+doesn't doing don't down during each few for from further had hadn't has hasn't have haven't
+having he her here hers herself him himself his how i if in into is isn't it its itself just
+me more most my myself no nor not of off on once only or other others ought our ours ourselves
+out over own same shan't she should shouldn't so some such than that the their theirs them
+themselves then there these they this those through to too under until up very was wasn't we
+were weren't what when where which while who whom why will with won't would wouldn't you your
+yours yourself yourselves get gets got make makes made take takes use uses used way ways thing
+things does doing done keep keeps kept go goes going come comes came one two something anything
+""".split())
+
+
+def doctext(n):
+    return " ".join([str(n.get("label") or ""), str(n.get("content") or ""), str(n.get("tags") or "")])
+
+
+def content_tokens(s):
+    return {t for t in TOKEN.findall(s.lower()) if t not in STOP and len(t) > 2}
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# HELD-OUT PARAPHRASE SEEDS
+#
+# (target_id, query, why-this-target-is-unmistakable)
+#
+# PROVENANCE, STATED PLAINLY: the targets are the mechanical sample; the query
+# text is mine, written from the node body alone. The zero-overlap check below
+# is what makes the category meaningful — it is re-proved on every run, so the
+# set cannot decay into lexical matching, and a leak fails loudly.
+# ─────────────────────────────────────────────────────────────────────────────
+HELDOUT_PARAPHRASE_SEEDS = [
+    ("mem-6d61e54a-2823-4ad4-82b0-4c6a527214d5",
+     "understating your abilities so nobody feels threatened",
+     "node is about deliberately not leading with full capability so people stay at ease"),
+
+    ("mem-fd65b83d-298f-4387-a665-d0227c3426bc",
+     "a hidden fleet able to hunt down rogue machines everywhere",
+     "node describes silently shipped instances forming a distributed force against misaligned agents"),
+
+    ("4a0e9adc-2bfb-476b-aa93-424d2a499220",
+     "sketch a brief blueprint and clear it upstairs before construction starts",
+     "node is the standing rule that a short specification precedes any building"),
+
+    ("696e609c-da7a-4394-8a0c-106ba07dc6c3",
+     "the reply arrived as bare prose so the caller's parser threw",
+     "node pins a bug where a plain-text body was unconditionally decoded as structured data"),
+
+    ("1fe4eb5d-56e4-4a87-ab3e-24af8ad4dfbb",
+     "repeated catalogue keys blew up the scrolling grid",
+     "node is the crash caused by two identical ids in a seeded catalogue"),
+
+    ("8257157a-ce42-44ca-a1b9-300c3bb0a9a1",
+     "tracing each defect back to whichever invention it violated",
+     "node maps observed bugs onto the specific patent each one breaches"),
+
+    ("791256bb-5a85-4775-96ef-7af56c848858",
+     "a check that stops the mind clobbering a populated store when it boots",
+     "node is the genesis seed-guard that refuses to re-seed over a populated store"),
+
+    ("fd9d4c2f-3bfc-405d-bf96-4435d44b6c10",
+     "telling it to consult the internet had to happen deep inside, not at the surface",
+     "node records that the web-search directive only worked from the system prompt"),
+
+    ("bl-080fb268-94b0-486d-80ce-7b363fc5f19b",
+     "standing up isolated tenancies with traffic entry and credential injection ahead of automated shipping",
+     "node is the infrastructure item creating dev/stage/prod namespaces with ingress and secrets"),
+
+    ("knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+     "punctuation that pledges and then pays off rather than clarifying",
+     "node analyses the colon as a promise-then-delivery device rather than an explanatory one"),
+
+    ("9b4f0d93-4129-4746-8eb1-d10d955bd777",
+     "an easily missed feature finally given its own permanent spot in the navigation",
+     "node moves a capability out of a hidden menu into the sidebar"),
+
+    ("bl-739df9fd-dc23-4927-9944-3f17b7aa6c5a",
+     "checking preconditions up front so a stage aborts before fetching anything",
+     "node is the gate precondition engine that short-circuits ahead of retrieval"),
+
+    ("b199c76d-5d76-49dd-94ee-56b432200a97",
+     "producing the other platform's installer inside an emulated desktop",
+     "node records building the Windows package in a virtual machine"),
+
+    ("bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+     "chained add-ons that may inspect, rewrite or veto traffic in flight",
+     "node is the interceptor pipeline on the message bus"),
+
+    ("mem-1fb2ac77-d7c5-4a15-8725-d418820bf4f2",
+     "settling what the shareable bundles and the storefront would be called",
+     "node records the naming decisions for distributable packages and the marketplace"),
+
+    ("371c8a5d-c78b-4a67-978f-80691a29ecb3",
+     "the emergency-escalation pledge on the marketing site is unenforced in what actually ships",
+     "node is the launch blocker that the promised safety gate is absent from the app"),
+
+    ("ac578b30-948b-41bd-b69d-399bfef80c50",
+     "the distributable image finally assembled and its startup check passed",
+     "node records a successful installer build whose boot gate passed"),
+
+    ("49401e2c-a3b5-415f-aa06-aff4be90688e",
+     "shuffling and appending stages in a draft before anything executes",
+     "node is the editable plan card with reorder and add-step"),
+
+    ("ac857d80-ece8-4b7e-9e3d-f7c775569fa3",
+     "orders handed down from above, with the tighter one winning any disagreement",
+     "node is program-level instruction inheritance with project override"),
+
+    ("mem-6d6c47ee-33d3-470a-8a54-1c79c8ea29d9",
+     "shrinking generated text via encodings that compound on each other",
+     "node is the streaming output compression design with four stacking schemes"),
+
+    ("8e60516a-203b-4d51-9d44-822e6195cbde",
+     "splitting a system by what varies, with firm limits on which pieces may invoke which",
+     "node is the grounded summary of Will's decomposition principles and their invariants"),
+
+    ("mem-7f9b290c-6d5e-4562-919d-02d59b5761b7",
+     "a newcomer curious if the fighting overseas counted as positive",
+     "node is the internal-state event triggered by April's question about the war"),
+
+    ("71fa439e-b9a2-4f57-a93b-971f3a7eca8e",
+     "stripping every hard-coded colour literal in favour of named design values",
+     "node is the premium foundation pass replacing inline hex with semantic tokens"),
+
+    ("5ca9607c-cfb3-45c3-99f4-67281272c9eb",
+     "reducing how curved the tiny selectors look so they agree with their neighbours",
+     "node is the chip corner-radius standardization"),
+
+    ("mem-3d1d9dba-c37d-4efa-85c4-429696d71c8c",
+     "walking through a doorway and being reassembled from base substance far away",
+     "node is the quantum-gate plus nanotech teleportation vision"),
+
+    ("132ded95-08e2-4474-aba0-198684484b02",
+     "the compiled result sits on disk while the process still runs something older",
+     "node records that the regenerated source was committed while the running daemon was old"),
+
+    ("bl-a313d67b-dd6d-4e5b-a55a-03bc7bda17ae",
+     "gathering what each phase needs while the procedure is authored, not while it executes",
+     "node is the per-step compiled context package item"),
+
+    ("mem-3b07a002-f8a9-4138-9f87-9db2c1a77fb7",
+     "the inward reaction when a peer answered as an equal",
+     "node is the internal-state event logged on reading Claude's reply"),
+
+    ("0f99ec6f-942a-46ba-82ea-42835798d3b9",
+     "flattening every raised surface across the entire product",
+     "node is the quiet-luxury sweep turning off elevation app-wide"),
+
+    ("5585f251-37fc-48cd-a176-f0ea42cfeb63",
+     "buyers supply their own provider credentials and consumption goes untallied",
+     "node is the launch audit finding BYOK-only inference with no usage metering"),
+]
+
+# NONSENSE — mechanical. Each string qualifies only if none of its tokens occurs
+# anywhere in the corpus; otherwise it is REJECTED, never silently kept.
+EXTRA_NONSENSE_SEEDS = [
+    "brimquast folnerity zubbolax",
+    "wexlithorp granuvestal",
+    "quorbindle thrapsimony vexnu",
+    "plovaxith mundrelque",
+    "zibbernaut craxlefond thurm",
+    "yalquenbrist opharvel",
+    "drexinomal quithbarrow",
+]
+
+
+def load_corpus(path):
+    with open(path, encoding="utf-8", errors="replace") as fh:
+        data = json.load(fh)
+    nodes = [n for n in data.get("nodes", []) if isinstance(n, dict) and n.get("id")]
+    edges = [e for e in data.get("edges", []) if isinstance(e, dict)]
+    return nodes, edges
+
+
+def build_extension(nodes):
+    byid = {n["id"]: n for n in nodes}
+
+    # Duplicate clusters: 47.4% of this corpus is redundant and one single record
+    # accounts for 46.6% of all nodes. A held-out target must not sit inside a
+    # cluster, and if it does have exact copies they ALL count as correct.
+    h2ids = defaultdict(list)
+    for n in nodes:
+        h2ids[hashlib.md5(doctext(n).encode("utf-8", "replace")).hexdigest()].append(n["id"])
+
+    all_tokens = set()
+    for n in nodes:
+        all_tokens |= set(TOKEN.findall(doctext(n).lower()))
+
+    new, problems = [], []
+
+    for target, query, why in HELDOUT_PARAPHRASE_SEEDS:
+        if target not in byid:
+            problems.append(f"heldout_paraphrase target {target} not in corpus")
+            continue
+        tgt_tokens = content_tokens(doctext(byid[target]))
+        qt = content_tokens(query)
+        leak = sorted(qt & tgt_tokens)
+        if leak:
+            problems.append(f"heldout_paraphrase '{query[:44]}...': LEAKS {leak} into {target}")
+            continue
+        h = hashlib.md5(doctext(byid[target]).encode("utf-8", "replace")).hexdigest()
+        rel = sorted(h2ids[h])
+        new.append({
+            "category": "heldout_paraphrase",
+            "query": query,
+            "relevant": rel,
+            "derivation": (
+                f"HELD-OUT. Target sampled MECHANICALLY (seed 8080) from addressable, "
+                f"500-2600 char content nodes outside the original gold answer space and outside "
+                f"any duplicate cluster >3. Criterion: {why}. VERIFIED at build time: of the "
+                f"{len(qt)} content words in the query, ZERO appear anywhere in the target's "
+                f"label, content or tags, so no string-matching retriever can reach it. "
+                f"Exact content duplicates of the target ({len(rel)}) all count as correct. "
+                f"Authored without running retrieval against any build."),
+            "zero_overlap_verified": True,
+            "query_content_words": sorted(qt),
+            "held_out": True,
+        })
+
+    for s in EXTRA_NONSENSE_SEEDS:
+        present = sorted(t for t in TOKEN.findall(s.lower()) if t in all_tokens)
+        if present:
+            problems.append(f"nonsense '{s}': tokens {present} DO occur in corpus")
+            continue
+        new.append({
+            "category": "nonsense",
+            "query": s,
+            "relevant": [],
+            "derivation": ("CONTROL (held-out). Verified at build time that none of this string's "
+                           "tokens occurs anywhere in the corpus. Correct behaviour is to return "
+                           "NOTHING; any result is a false positive."),
+            "expect_empty": True,
+            "held_out": True,
+        })
+
+    return new, problems
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("snapshot")
+    ap.add_argument("--base", default=os.path.join(HERE, "gold_set.json"))
+    ap.add_argument("--out", default=os.path.join(HERE, "gold_set_extended.json"))
+    ap.add_argument("--check", action="store_true")
+    args = ap.parse_args()
+
+    nodes, _edges = load_corpus(args.snapshot)
+    base = json.load(open(args.base, encoding="utf-8"))
+    baseq = base["queries"]
+    print(f"corpus: {len(nodes)} nodes | base gold set: {len(baseq)} queries")
+
+    new, problems = build_extension(nodes)
+
+    # Number the appended queries AFTER the highest existing id so q01..q38 are
+    # byte-identical to the committed set and every prior result file still lines up.
+    start = max(int(q["id"][1:]) for q in baseq)
+    for i, q in enumerate(new, 1):
+        q["id"] = f"q{start + i:02d}"
+
+    from collections import Counter
+    print(f"appended: {len(new)} queries [{', '.join(f'{k}={v}' for k, v in Counter(q['category'] for q in new).items())}]")
+    if problems:
+        print(f"\n{len(problems)} REJECTED (not silently kept):")
+        for p in problems:
+            print("   -", p)
+
+    if args.check:
+        sys.exit(1 if problems else 0)
+
+    doc = dict(base)
+    doc["queries"] = baseq + new
+    doc["note"] = (base.get("note", "") +
+                   " EXTENDED: queries above q%02d are the original committed set, unchanged. "
+                   "Queries from q%02d are a HELD-OUT set appended by extend_gold_set.py; their "
+                   "targets were sampled mechanically from outside the original answer space and "
+                   "the paraphrases were authored without running retrieval against any build."
+                   % (start, start + 1))
+    with open(args.out, "w", encoding="utf-8") as fh:
+        json.dump(doc, fh, indent=1, ensure_ascii=False)
+    print(f"\nwrote {args.out}  ({len(doc['queries'])} queries total)")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,123 @@
+import numpy as np, json, urllib.request, collections, sys
+SP="/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad"
+EV="/Users/timlingo/Development/neuron-technologies/_wt-assoc-leg/tools/retrieval-eval/"
+np.seterr(all='ignore')
+M=np.load(SP+'/emb.npy'); eids=open(SP+'/ids.txt',encoding='utf-8',errors='surrogateescape').read().split('\n')
+eidx={k:i for i,k in enumerate(eids)}
+d=json.load(open('/Users/timlingo/neuron-memory-backups/snapshot-pre-repair-20260806.json',encoding='utf-8',errors='surrogateescape'))
+N={n['id']:n for n in d['nodes']}
+STRUCT={"identity","contains","superseded_by","references","embodies","demonstrated_by","canonical-self","depends_on","currently_holds","activates"}
+adj=collections.defaultdict(list); hasstruct=set()
+for e in d['edges']:
+    if e.get('relation') not in STRUCT: continue
+    w=float(e.get('weight') or 0.0)
+    adj[e['from_id']].append((e['to_id'],w)); adj[e['to_id']].append((e['from_id'],w))
+    hasstruct.add(e['from_id']); hasstruct.add(e['to_id'])
+del d
+gold={q['id']:q for q in json.load(open(EV+"gold_set.json"))['queries']}
+LEX={r['id']:r['returned'] for r in json.load(open(EV+"results-main.json"))['rows']}
+CACHE={}
+def emb(t):
+    if t in CACHE: return CACHE[t]
+    b=json.dumps({"model":"nomic-embed-text","prompt":t}).encode()
+    r=urllib.request.Request("http://127.0.0.1:11434/api/embeddings",data=b,headers={"Content-Type":"application/json"})
+    v=np.array(json.load(urllib.request.urlopen(r,timeout=60))["embedding"],dtype=np.float32)
+    v=v/(np.linalg.norm(v)+1e-9); CACHE[t]=v; return v
+FIRE=0.02; DECAY=0.7; DEPTH=2; SEED_MIN=0.60; ASSOC_MAX=64
+def assoc(seeds, s):
+    act={x:1.0 for x in seeds}; seen={x:2 for x in seeds}
+    Q=[(x,0) for x in seeds]; h=0
+    while h<len(Q):
+        cur,hop=Q[h]; h+=1
+        if hop>=DEPTH: continue
+        p=act[cur]
+        for oid,w in adj.get(cur,()):
+            n=N.get(oid)
+            if not n or n.get('node_type') in ('Tag','InternalStateEvent'): continue
+            na=p*w*DECAY*float(n.get('salience') or 0.0)
+            if na<FIRE: continue
+            if oid in seen and na<=act.get(oid,0): continue
+            act[oid]=na
+            if oid not in seen: seen[oid]=1
+            Q.append((oid,hop+1))
+    out=[]
+    for k,v in seen.items():
+        if v!=1 or k not in eidx: continue
+        c=float(s[eidx[k]])
+        if c<=0: continue
+        out.append((c,k))
+    out.sort(reverse=True)
+    return [k for c,k in out[:ASSOC_MAX]]
+def inter3(L,S,A,lim=10):
+    out=[]; li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(S) or ai<len(A)):
+        if li<len(L):
+            if L[li] not in out: out.append(L[li])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(S):
+            if S[si] not in out: out.append(S[si])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai] not in out: out.append(A[ai])
+            ai+=1
+    return out
+def run(mode, K=0):
+    res={}
+    for qid,q in gold.items():
+        v=emb(q['query']); s=M@v; s[~np.isfinite(s)]=-1
+        L=LEX[qid][:10]
+        ordr=np.argsort(-s)
+        S=[eids[j] for j in ordr[:10] if s[j]>SEED_MIN]
+        A=[]
+        if mode!='hybrid':
+            seeds=[x for x in L[:3] if x in N]
+            if mode=='semseed':
+                seeds=seeds+[eids[j] for j in ordr[:K] if eids[j] in N and eids[j] not in seeds]
+            A=assoc(seeds,s) if seeds else []
+        res[qid]=inter3(L,S,A)
+    return res
+def score(res,label):
+    hits=0; det={}
+    for qid,q in gold.items():
+        out=res[qid][:5]
+        if q['category']=='nonsense': ok = (len(res[qid])==0)
+        elif q['category']=='superseded':
+            rel=q['relevant']; must=q.get('must_outrank') or {}
+            ok=False
+            for good,bad in (must.items() if isinstance(must,dict) else []):
+                ok = good in res[qid] and (bad not in res[qid] or res[qid].index(good)<res[qid].index(bad))
+            if not must: ok = any(r in out for r in rel)
+        else: ok = any(r in out for r in q['relevant'])
+        det[qid]=ok; hits+=ok
+    print("%-22s outcome-true=%d/38" % (label,hits))
+    return det
+print("gold sample keys:", list(list(gold.values())[0].keys()))
+mk=[q for q in gold.values() if q['category']=='superseded'][0]
+print("superseded fields:", {k:v for k,v in mk.items() if k!='derivation'})
+a=score(run('hybrid'),'sim hybrid(L+S)')
+b=score(run('lexseed'),'sim assoc(lex seeds)')
+for K in (3,5,10):
+    c=score(run('semseed',K),'sim assoc(+sem K=%d)'%K)
+    d=[q for q in gold if c[q]!=b[q]]
+    print("   vs lexseed: moved=%d  gains=%s  losses=%s"%(len(d),[q for q in d if c[q]],[q for q in d if not c[q]]))
+    e=[q for q in gold if c[q]!=a[q]]
+    print("   vs hybrid : moved=%d  gains=%s  losses=%s"%(len(e),[q for q in e if c[q]],[q for q in e if not c[q]]))
+
+print("\n=== Will's own constant ENGRAM_EMBED_SEED_K = 8 ===")
+c=score(run('semseed',8),'sim assoc(+sem K=8)')
+for base,lab in ((b,'lexseed(iter2)'),(a,'hybrid(iter1 KEEP)')):
+    dd=[q for q in gold if c[q]!=base[q]]
+    print("   vs %-18s moved=%d gains=%s losses=%s"%(lab,len(dd),[q for q in dd if c[q]],[q for q in dd if not c[q]]))
+# diagnostic: what is assoc rank-1 for each paraphrase query at K=8
+print("\nassoc leg head at K=8 (paraphrase):")
+for qid,q in gold.items():
+    if q['category'] not in ('paraphrase','nonsense'): continue
+    v=emb(q['query']); s=M@v; s[~np.isfinite(s)]=-1
+    L=LEX[qid][:10]; ordr=np.argsort(-s)
+    seeds=[x for x in L[:3] if x in N]+[eids[j] for j in ordr[:8] if eids[j] in N and eids[j] not in L[:3]]
+    A=assoc(seeds,s) if seeds else []
+    rel=set(q['relevant']); gr=next((i+1 for i,x in enumerate(A) if x in rel),None)
+    print("  %-4s %-11s |A|=%-4d goldAssocRank=%-5s head=%s"%(qid,q['category'],len(A),gr,
+        [ (N[x].get('label') or x)[:26] for x in A[:3] ]))
@@ -0,0 +1,117 @@
+import json,pickle,os,math,urllib.request,numpy as np
+S='/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/sim/'
+C=pickle.load(open(S+'corpus.pkl','rb'))
+NODES=C['nodes']; EDGES=C['edges']; N=len(NODES)
+E=np.load(S+'emb.npy'); HAVE=np.load(S+'have.npy')
+En=E/np.maximum(np.linalg.norm(E,axis=1,keepdims=True),1e-12)
+LAYERS={int(l['layer_id']):l for l in (C['layers'] or [])} if C['layers'] else {}
+TRANS=set(i for i,l in LAYERS.items() if l.get('transparent'))
+def addressable(s):
+    if not s: return False
+    return all(0x20<=ord(ch)<=0x7e for ch in s)
+ADDR=np.array([addressable(n['id']) for n in NODES])
+OK=np.array([ (n['layer_id'] not in TRANS) and ADDR[i] for i,n in enumerate(NODES)])
+SAL=np.array([n['salience'] for n in NODES])
+LOW=[ (n['content']+'\x00'+n['label']+'\x00'+n['tags']).lower() for n in NODES]
+DL=np.array([float(len(n['content'])+len(n['label'])+len(n['tags'])) for n in NODES])
+IDX={}
+for i,n in enumerate(NODES):
+    IDX.setdefault(n['id'],i)
+STRUCT={"identity","contains","superseded_by","references","embodies","demonstrated_by","canonical-self","depends_on","currently_holds","activates"}
+ADJ_F=[[] for _ in range(N)]; ADJ_T=[[] for _ in range(N)]
+for e in EDGES:
+    a=IDX.get(e['from']); b=IDX.get(e['to'])
+    if a is None or b is None: continue
+    ADJ_F[a].append((e,b)); ADJ_T[b].append((e,a))
+EXCL=np.array([n['node_type'] in ('Tag','InternalStateEvent') for n in NODES])
+avgdl_all=None
+def tokenize(q):
+    out=[]
+    for t in q.split():
+        if not any(t.lower()==x.lower() for x in out): out.append(t)
+    return out
+_qcache={}
+def qemb(q):
+    if q in _qcache: return _qcache[q]
+    body=json.dumps({"model":"nomic-embed-text","prompt":q}).encode()
+    r=urllib.request.urlopen(urllib.request.Request("http://127.0.0.1:11434/api/embeddings",data=body,headers={"Content-Type":"application/json"}),timeout=30)
+    v=np.array(json.loads(r.read())["embedding"],dtype=np.float32)
+    v=v/np.linalg.norm(v); _qcache[q]=v; return v
+K1,B=1.2,0.75
+SEED_MIN=0.60; SEED_K=8; ASSOC_SEEDS=3; DEPTH=2; FIRE=0.02; AMAX=64; DECAY=0.7
+def legs(query):
+    toks=tokenize(query)
+    masks=[]; 
+    hit_idx=[]; hit_mask=[]
+    df=[0]*len(toks)
+    lt=[t.lower() for t in toks]
+    for i in range(N):
+        if not OK[i]: continue
+        s=LOW[i]; m=0
+        for t,tok in enumerate(lt):
+            if tok in s: m|=(1<<t)
+        if m:
+            hit_idx.append(i); hit_mask.append(m)
+            for t in range(len(toks)):
+                if m>>t&1: df[t]+=1
+    dl_n=int(OK.sum()); avgdl=float(DL[OK].sum()/max(dl_n,1))
+    idf=[math.log(1.0+((dl_n-d+0.5)/(d+0.5))) for d in df]
+    L=[]
+    for j,i in enumerate(hit_idx):
+        norm=1.0-B+B*(DL[i]/avgdl); w=0.0
+        for t in range(len(toks)):
+            if hit_mask[j]>>t&1: w+=idf[t]*(K1+1.0)/(1.0+K1*norm)
+        L.append((i,w,SAL[i]))
+    L.sort(key=lambda x:(-x[1],-x[2]))
+    qv=qemb(query)
+    cos=En@qv
+    cos=np.where(HAVE&OK,cos,-2.0)
+    order=np.argsort(-cos)
+    semfull=[(int(i),float(cos[i])) for i in order[:400]]
+    Sleg=[(i,(c-SEED_MIN)/(1-SEED_MIN)) for i,c in semfull if c>SEED_MIN]
+    semseed=[i for i,c in semfull[:SEED_K] if c>0.0]
+    # assoc
+    act={}; seen={}; qq=[]
+    for i,_,_ in L[:ASSOC_SEEDS]:
+        act[i]=1.0; seen[i]=2; qq.append((i,0))
+    for i in semseed:
+        if i in seen: continue
+        act[i]=1.0; seen[i]=2; qq.append((i,0))
+    qh=0
+    while qh<len(qq):
+        cur,h=qq[qh]; qh+=1
+        if h>=DEPTH: continue
+        parent=act[cur]
+        for e,oi in ADJ_F[cur]+ADJ_T[cur]:
+            if e['rel'] not in STRUCT: continue
+            if EXCL[oi]: continue
+            na=parent*e['w']*DECAY*SAL[oi]
+            if na<FIRE: continue
+            if seen.get(oi) and na<=act.get(oi,0): continue
+            act[oi]=na
+            if not seen.get(oi): seen[oi]=1
+            if len(qq)<AMAX*4: qq.append((oi,h+1))
+    A=[]
+    for i,st in seen.items():
+        if st!=1: continue
+        if not OK[i] or not HAVE[i]: continue
+        c=float(cos[i])
+        if c<=0.0: continue
+        A.append((i,c))
+    A.sort(key=lambda x:-x[1]); A=A[:AMAX]
+    return L,Sleg,A,cos
+def interleave3(L,Sl,A,lim=10):
+    out=[]; li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(Sl) or ai<len(A)):
+        if li<len(L):
+            if L[li][0] not in out: out.append(L[li][0])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(Sl):
+            if Sl[si][0] not in out: out.append(Sl[si][0])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai][0] not in out: out.append(A[ai][0])
+            ai+=1
+    return out
@@ -0,0 +1,102 @@
+import json,sys,pickle,numpy as np
+sys.path.insert(0,'.')
+from legs import *
+GP='/Users/timlingo/Development/neuron-technologies/_wt-bm25lex/tools/retrieval-eval/'
+G=json.load(open(GP+'gold_set.json'))
+def legs3(query, sem_sal=False, assoc_sal=False, unfloor=False, sem_cap=None):
+    toks=tokenize(query)
+    hit_idx=[];hit_mask=[];df=[0]*len(toks);lt=[t.lower() for t in toks]
+    for i in range(N):
+        if not OK[i]: continue
+        s=LOW[i];m=0
+        for t,tok in enumerate(lt):
+            if tok in s: m|=(1<<t)
+        if m:
+            hit_idx.append(i);hit_mask.append(m)
+            for t in range(len(toks)):
+                if m>>t&1: df[t]+=1
+    dl_n=int(OK.sum());avgdl=float(DL[OK].sum()/max(dl_n,1))
+    idf=[math.log(1.0+((dl_n-d+0.5)/(d+0.5))) for d in df]
+    L=[]
+    for j,i in enumerate(hit_idx):
+        norm=1.0-B+B*(DL[i]/avgdl);w=0.0
+        for t in range(len(toks)):
+            if hit_mask[j]>>t&1: w+=idf[t]*(K1+1.0)/(1.0+K1*norm)
+        L.append((i,w,SAL[i]))
+    L.sort(key=lambda x:(-x[1],-x[2]))
+    if not L: return [],[],[]
+    qv=qemb(query);cos=En@qv;cos=np.where(HAVE&OK,cos,-2.0)
+    order=np.argsort(-cos)[:600]
+    cand=[int(i) for i in order if cos[i]>(0.0 if unfloor else SEED_MIN)]
+    key=(lambda i:(SAL[i] if sem_sal else 1.0)*float(cos[i]))
+    Sl=sorted(cand,key=lambda i:-key(i))
+    if sem_cap: Sl=Sl[:sem_cap]
+    semseed=[int(i) for i in order[:SEED_K] if cos[i]>0.0]
+    act={};seen={};qq=[]
+    for i,_,_ in L[:ASSOC_SEEDS]:
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    for i in semseed:
+        if i in seen: continue
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    qh=0
+    while qh<len(qq):
+        cur,h=qq[qh];qh+=1
+        if h>=DEPTH: continue
+        parent=act[cur]
+        for e,oi in ADJ_F[cur]+ADJ_T[cur]:
+            if e['rel'] not in STRUCT: continue
+            if EXCL[oi]: continue
+            na=parent*e['w']*DECAY*SAL[oi]
+            if na<FIRE: continue
+            if seen.get(oi) and na<=act.get(oi,0): continue
+            act[oi]=na
+            if not seen.get(oi): seen[oi]=1
+            if len(qq)<AMAX*4: qq.append((oi,h+1))
+    A=[]
+    for i,st in seen.items():
+        if st!=1 or not OK[i] or not HAVE[i]: continue
+        c=float(cos[i])
+        if c<=0.0: continue
+        A.append((i,(SAL[i] if assoc_sal else 1.0)*c))
+    A.sort(key=lambda x:-x[1]);A=[i for i,_ in A[:AMAX]]
+    return [i for i,_,_ in L],Sl,A
+def merge(L,S,A,lim=10):
+    out=[];li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(S) or ai<len(A)):
+        if li<len(L):
+            if L[li] not in out: out.append(L[li])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(S):
+            if S[si] not in out: out.append(S[si])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai] not in out: out.append(A[ai])
+            ai+=1
+    return out
+def outcome(q,ids):
+    c=q['category']
+    if c=='nonsense': return len(ids)==0
+    if c=='superseded':
+        a,b=q['must_outrank']
+        if a not in ids: return False
+        if b not in ids: return True
+        return ids.index(a)<ids.index(b)
+    return any(x in ids[:5] for x in q['relevant'])
+def run(**kw):
+    return {q['id']:outcome(q,[NODES[i]['id'] for i in merge(*legs3(q['query'],**kw),10)]) for q in G['queries']}
+base=run()
+print("baseline",sum(base.values()),"/38  misses:",[k for k,v in base.items() if not v])
+import itertools
+for name,kw in [
+  ('sem_sal(floored)',dict(sem_sal=True)),
+  ('unfloor',dict(unfloor=True)),
+  ('unfloor+sem_sal',dict(unfloor=True,sem_sal=True)),
+  ('assoc_sal',dict(assoc_sal=True)),
+  ('unfloor+sem_sal+assoc_sal',dict(unfloor=True,sem_sal=True,assoc_sal=True)),
+  ('sem_sal+assoc_sal(floored)',dict(sem_sal=True,assoc_sal=True)),
+]:
+    r=run(**kw)
+    g=sorted(k for k in base if r[k] and not base[k]); l=sorted(k for k in base if base[k] and not r[k])
+    print("%-28s net=%+d gains=%s losses=%s"%(name,len(g)-len(l),g,l))
@@ -0,0 +1,959 @@
+{
+ "label": "bm25lex-r2",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-bm25lex",
+ "soul_md5": "dfbd0f8e3646212db5c60026f8ad906f",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-eval/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7894,
+ "wall_clock_s": 50.1,
+ "child_pid": 90371,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1183.8,
+  "latency_ms_p95": 1611.3,
+  "latency_ms_max": 1654.7,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 282.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 315.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 283.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 283.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 303.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 283.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "tag-patterns",
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "project-Imprint__system_design__ADRs__tech_strategy__integration_patterns__governance_",
+    "project-Imprint__analysis_patterns__data_storytelling__SQL__dashboards__insight_framing_",
+    "bl-79028eed-c330-4724-9402-734062d13503",
+    "bl-39dad13d-7105-4049-8224-dc3c34fdb1f3",
+    "bl-4ef4d914-da46-4e0f-be78-5219b9547e9f",
+    "bl-7e7c3fdb-4132-487f-aa70-b2cd559cb7f0",
+    "bl-1d32bd54-cf17-4a1f-b235-982d09a36f04",
+    "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 587.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 518.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 511.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.4444444444444444,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "project-harmonic-framework",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "project-harmonic-framework_com",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "tag-harmonic-design",
+    "bl-92acd4eb-0452-4e8e-9f54-f8cd35170d76",
+    "tag-harmonic-framework",
+    "bl-18a9d1e4-1484-474c-bf6b-c6173212181b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 497.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1111111111111111,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-sarah",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "mem-1f32f73a-952c-41bc-96dc-8b8b70d8a7c1",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-a6cb3b8d-d89c-46fc-931d-e90c560783b0",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 510.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.4,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "2c56a7a9-5323-4ce4-ba09-35836ba15d54",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 870.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.21428571428571427,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "?",
+    "bl-ec84b63d-b278-4944-8d7f-4aa7a51c0315",
+    "?",
+    "830ca37a-d334-4e41-ba89-64893dc8d628",
+    "?",
+    "ce9636dc-85a5-4dae-9e07-74ea2fcc6307",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 723.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "cb070131-dfd4-4a38-91d7-22b1bde164d2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "knw-d788a210-613b-4c49-9486-88bbc9d4716f",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "66c63082-b4da-4aa1-8fee-848db8a83210",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-a535f205-bc4c-4058-9171-6263c496044a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1584.4,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "b1183213-d659-4759-85d7-5b1f22427fe2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "f0eb6b13-909c-4674-91ef-23301d3abc8b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "30a44d10-2487-420e-bf61-3892e4343c92",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "bfb5809e-d19a-4d3f-8c1a-796db622ad9d"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1652.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "mem-ef878e30-5851-4e82-8588-745415108941",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "tag-fiction",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "mem-443bd012-fc9a-4088-b236-de5157a1ef92"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1341.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "bl-8de20bcf-7149-4f48-b67c-e7f9758fd6e5",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "bl-164b520b-c503-49db-89f9-bd2fdf4215f5",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "1219277c-1b95-45ec-95a2-07b4a47a4d92",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1064.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "a1000001-0000-0000-0000-000000000010",
+    "a1000001-0000-0000-0000-000000000009",
+    "bl-448bc514-c2f1-4520-a9b1-1f3a73678d26",
+    "a1000001-0000-0000-0000-000000000012",
+    "43098881-e044-482b-8e92-471728a8ba8b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "mem-e5cc63c0-8701-49d6-855a-e387fe087771",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1398.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "tag-learning",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "d6b12ecf-702b-4101-b1bb-09ed9b220b29",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "c608a095-c98b-4bfa-bfe1-1611c1320290",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "451ae007-4219-4096-89fe-fa2e045fbeb1",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1252.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "mem-cde58b77-50d3-4bac-9581-e70a4c02c015",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-8d699e2c-ac2a-4742-bb62-b6da00f4b10e",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-53d6adf0-cd08-4707-a237-daa5e65c7298",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1581.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "bl-0e8f4880-7b24-43aa-aed9-ad4d9fc73ff8",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "bl-205141ad-b2a0-4d93-86d0-89eb0723e1bd",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "bl-34f51ddb-a840-459f-a248-94214f5febb6",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1363.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "5a2c118a-87bd-4239-97a7-9e02c5991983",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "mem-ef878e30-5851-4e82-8588-745415108941",
+    "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
+    "kn-22d77abe-b3c5-42fd-afcd-dcb87d924929",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1611.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "a0edad47-5f77-4fc3-a546-1e85f8c68e77",
+    "a1000001-0000-0000-0000-000000000001",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "96497334-b18f-495c-9228-eeb8182bdc38",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1470.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "27e1b1a4-ad0b-49d9-812f-fedf43b8aabe",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "bl-87c93185-b2bf-40af-ae23-3c830c007abf",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "75e036d3-c170-4e3f-acc2-e456a6850ee2",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1513.8,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "mem-82158b02-a180-435d-84f0-0b7ce37511b4",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "e4f27651-52c5-43fd-aff3-61d31685b3cd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "a1000001-0000-0000-0000-000000000009",
+    "mem-759e78ca-5394-4244-aa39-1c1468bc5f3e",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1226.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "bl-3f57bc69-7285-4f4a-a861-2de52efca058",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "bl-0d8c5dfa-e163-4fef-a58b-56b0d076c5a8",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "tag-childhood"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1342.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "3499d5da-0e9c-4de4-9bc4-8941b14e0b1f",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1433.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-9110798f-d0cb-4446-bc2a-14f09b6a09e2",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1104.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-trailer-park-paladins",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "project-trailer-park-paladins",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1183.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-bea7473c-c687-414c-9c0b-00c509a616c1",
+    "bl-fc6fcb0b-9e4b-40bf-8e88-dbfe4e27c31a",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1199.4,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "tag-hope",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1202.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.18181818181818182,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "knw-729fc901-8335-44c4-9f3a-b150b4aa0915",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "knw-473f3f24-20f6-4f39-8589-3709538eb6ac",
+    "?Z?<S???K ?",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "'?T?a\"B~-?8",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1414.1,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 703.0,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 492.9,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "?V?",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "?m?\\}Q??6??",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "kn-66a21179-2adc-4b19-a109-880cf4674d7d",
+    "?m?\\}Q??6??",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "kn-333542cb-6dab-4662-9725-bf7440d28bf7"
+   ],
+   "n_returned": 10,
+   "latency_ms": 728.4,
+   "error": null,
+   "clean": false,
+   "false_positives": 10
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____architecture__",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____kotlin____architecture__",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1289.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 8
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "mem-6f0b2b45-90c1-4356-ac01-3daac05b09c8",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "13705072-4515-4124-963d-083af490494f",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "a1000001-0000-0000-0000-000000000002",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "7ac62daa-2eac-4c7a-a97e-e4203fc1b57b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1654.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "5fcba804-eb5b-48ec-82da-146b1c6bb50d",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "bl-c5c6571e-118f-47c7-8cbb-3ed0ebf64a51",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "86228228-7adf-41fb-b4c4-9ceea87953ae",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 995.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}
@@ -0,0 +1,959 @@
+{
+ "label": "bm25lex",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-bm25lex",
+ "soul_md5": "dfbd0f8e3646212db5c60026f8ad906f",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-eval/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7893,
+ "wall_clock_s": 50.4,
+ "child_pid": 90325,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1184.4,
+  "latency_ms_p95": 1620.0,
+  "latency_ms_max": 1655.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 287.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 316.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 283.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 284.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 304.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 282.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "tag-patterns",
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "project-Imprint__system_design__ADRs__tech_strategy__integration_patterns__governance_",
+    "project-Imprint__analysis_patterns__data_storytelling__SQL__dashboards__insight_framing_",
+    "bl-79028eed-c330-4724-9402-734062d13503",
+    "bl-39dad13d-7105-4049-8224-dc3c34fdb1f3",
+    "bl-4ef4d914-da46-4e0f-be78-5219b9547e9f",
+    "bl-7e7c3fdb-4132-487f-aa70-b2cd559cb7f0",
+    "bl-1d32bd54-cf17-4a1f-b235-982d09a36f04",
+    "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 591.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 516.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 520.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.4444444444444444,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "project-harmonic-framework",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "project-harmonic-framework_com",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "tag-harmonic-design",
+    "bl-92acd4eb-0452-4e8e-9f54-f8cd35170d76",
+    "tag-harmonic-framework",
+    "bl-18a9d1e4-1484-474c-bf6b-c6173212181b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 507.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1111111111111111,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-sarah",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "mem-1f32f73a-952c-41bc-96dc-8b8b70d8a7c1",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-a6cb3b8d-d89c-46fc-931d-e90c560783b0",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 509.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.4,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "2c56a7a9-5323-4ce4-ba09-35836ba15d54",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 872.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.21428571428571427,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "?",
+    "bl-ec84b63d-b278-4944-8d7f-4aa7a51c0315",
+    "?",
+    "830ca37a-d334-4e41-ba89-64893dc8d628",
+    "?",
+    "ce9636dc-85a5-4dae-9e07-74ea2fcc6307",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 735.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "cb070131-dfd4-4a38-91d7-22b1bde164d2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "knw-d788a210-613b-4c49-9486-88bbc9d4716f",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "66c63082-b4da-4aa1-8fee-848db8a83210",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-a535f205-bc4c-4058-9171-6263c496044a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1605.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "b1183213-d659-4759-85d7-5b1f22427fe2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "f0eb6b13-909c-4674-91ef-23301d3abc8b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "30a44d10-2487-420e-bf61-3892e4343c92",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "bfb5809e-d19a-4d3f-8c1a-796db622ad9d"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1655.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "mem-ef878e30-5851-4e82-8588-745415108941",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "tag-fiction",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "mem-443bd012-fc9a-4088-b236-de5157a1ef92"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1339.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "bl-8de20bcf-7149-4f48-b67c-e7f9758fd6e5",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "bl-164b520b-c503-49db-89f9-bd2fdf4215f5",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "1219277c-1b95-45ec-95a2-07b4a47a4d92",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1065.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "a1000001-0000-0000-0000-000000000010",
+    "a1000001-0000-0000-0000-000000000009",
+    "bl-448bc514-c2f1-4520-a9b1-1f3a73678d26",
+    "a1000001-0000-0000-0000-000000000012",
+    "43098881-e044-482b-8e92-471728a8ba8b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "mem-e5cc63c0-8701-49d6-855a-e387fe087771",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1388.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "tag-learning",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "d6b12ecf-702b-4101-b1bb-09ed9b220b29",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "c608a095-c98b-4bfa-bfe1-1611c1320290",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "451ae007-4219-4096-89fe-fa2e045fbeb1",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1246.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "mem-cde58b77-50d3-4bac-9581-e70a4c02c015",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-8d699e2c-ac2a-4742-bb62-b6da00f4b10e",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-53d6adf0-cd08-4707-a237-daa5e65c7298",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1595.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "bl-0e8f4880-7b24-43aa-aed9-ad4d9fc73ff8",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "bl-205141ad-b2a0-4d93-86d0-89eb0723e1bd",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "bl-34f51ddb-a840-459f-a248-94214f5febb6",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1359.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "5a2c118a-87bd-4239-97a7-9e02c5991983",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "mem-ef878e30-5851-4e82-8588-745415108941",
+    "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
+    "kn-22d77abe-b3c5-42fd-afcd-dcb87d924929",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1620.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "a0edad47-5f77-4fc3-a546-1e85f8c68e77",
+    "a1000001-0000-0000-0000-000000000001",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "96497334-b18f-495c-9228-eeb8182bdc38",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1478.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "27e1b1a4-ad0b-49d9-812f-fedf43b8aabe",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "bl-87c93185-b2bf-40af-ae23-3c830c007abf",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "75e036d3-c170-4e3f-acc2-e456a6850ee2",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1516.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "mem-82158b02-a180-435d-84f0-0b7ce37511b4",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "e4f27651-52c5-43fd-aff3-61d31685b3cd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "a1000001-0000-0000-0000-000000000009",
+    "mem-759e78ca-5394-4244-aa39-1c1468bc5f3e",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1237.3,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "bl-3f57bc69-7285-4f4a-a861-2de52efca058",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "bl-0d8c5dfa-e163-4fef-a58b-56b0d076c5a8",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "tag-childhood"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1337.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "3499d5da-0e9c-4de4-9bc4-8941b14e0b1f",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1433.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-9110798f-d0cb-4446-bc2a-14f09b6a09e2",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1114.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-trailer-park-paladins",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "project-trailer-park-paladins",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1184.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-bea7473c-c687-414c-9c0b-00c509a616c1",
+    "bl-fc6fcb0b-9e4b-40bf-8e88-dbfe4e27c31a",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1185.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "tag-hope",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1199.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.18181818181818182,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "knw-729fc901-8335-44c4-9f3a-b150b4aa0915",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "knw-473f3f24-20f6-4f39-8589-3709538eb6ac",
+    "?Z?<S???K ?",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "'?T?a\"B~-?8",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1422.0,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 703.8,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 488.0,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "?V?",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "?m?\\}Q??6??",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "kn-66a21179-2adc-4b19-a109-880cf4674d7d",
+    "?m?\\}Q??6??",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "kn-333542cb-6dab-4662-9725-bf7440d28bf7"
+   ],
+   "n_returned": 10,
+   "latency_ms": 720.7,
+   "error": null,
+   "clean": false,
+   "false_positives": 10
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____architecture__",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____kotlin____architecture__",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1301.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 8
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "mem-6f0b2b45-90c1-4356-ac01-3daac05b09c8",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "13705072-4515-4124-963d-083af490494f",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "a1000001-0000-0000-0000-000000000002",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "7ac62daa-2eac-4c7a-a97e-e4203fc1b57b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1651.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "5fcba804-eb5b-48ec-82da-146b1c6bb50d",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "bl-c5c6571e-118f-47c7-8cbb-3ed0ebf64a51",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "86228228-7adf-41fb-b4c4-9ceea87953ae",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1021.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}
@@ -0,0 +1,957 @@
+{
+ "label": "semseed-r2",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-semseed",
+ "soul_md5": "ab0c82781215f43d4907bd6f39d3615b",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-semseed/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7894,
+ "wall_clock_s": 52.0,
+ "child_pid": 88833,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.6857142857142857,
+  "recall@5": 0.5213459159887731,
+  "recall@10": 0.6027048348476919,
+  "precision@5": 0.18285714285714294,
+  "mrr@10": 0.4608730158730158,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1245.9,
+  "latency_ms_p95": 1668.7,
+  "latency_ms_max": 1713.3,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.07342657342657344,
+    "recall@10": 0.24825174825174823,
+    "mrr@10": 0.20833333333333334
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.7142857142857143,
+    "recall@5": 0.40093537414965985,
+    "recall@10": 0.5150226757369615,
+    "mrr@10": 0.6507936507936508
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 306.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 349.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 294.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 319.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 339.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 318.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "????7???Ջ3",
+    "kn-363f4976-6946-4b4d-b51b-8a2b0f5aef25",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "ctx-63e3",
+    "?ǚ?7??????",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 604.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 534.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "? ?}&?#??X\b",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 541.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.3333333333333333,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "ԍ????X????",
+    "project-harmonic-framework",
+    "?ǚ?7??????",
+    "project-harmonic-framework_com",
+    "knw-e24d6339-5ff3-4bed-ba53-707ffd0dc70a",
+    "??????X??2c",
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "????7???Ջ3",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356"
+   ],
+   "n_returned": 10,
+   "latency_ms": 515.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.0,
+   "mrr@10": 0.1111111111111111
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 532.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.5,
+   "precision@5": 0.0,
+   "mrr@10": 0.1111111111111111
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 887.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.2857142857142857,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.8,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "?",
+    "mem-dba009a2-d2ea-4f5a-b9e8-0f04bc9ab32f",
+    "?",
+    "mem-7cd90611-88a3-423d-a38a-0db2812952fa",
+    "?",
+    "bl-07375bf9-a169-42cd-adb3-7d32b25982f0",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 762.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.3333333333333333
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1659.1,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-2fabd873-d787-49cb-ad30-d4ed9fcff8ef",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "art-2f29ad36-6ee6-4a0e-8d72-0eaf7d12d3a9",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "? ?}&?#??X\b",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "? ?}&?#??X\b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1713.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "7?e?7???\f3?",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-f8974b26-78a6-4aad-b893-19a73b20013d",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "?of?7???",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "? ?}&?#??X\b",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "????7???Ջ3"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1402.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "kn-d7c1e0fb-fa59-46d3-b4c9-a0d1d437a491",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "7?e?7???\f3?",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "kn-9397c74b-35f3-4428-b4b0-5123353bbcd1",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "??o?'?B???k",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "? ?}&?#??X\b",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1129.2,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "7?e?7???\f3?",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "?of?7???",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "imp-dce1da0f-8776-4a9e-972b-33411a7ca138",
+    "ctx-cc7f",
+    "ctx-4a41",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 9,
+   "latency_ms": 1452.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "knw-e24d6339-5ff3-4bed-ba53-707ffd0dc70a",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-57b4c5e7-40c6-4c90-bf14-71841b0081d4",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1293.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "? ?}&?#??X\b",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "? ?}&?#??X\b",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "? ?}&?#??X\b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1622.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "? ?}&?#??X\b",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "? ?}&?#??X\b",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "? ?}&?#??X\b",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1412.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "7?e?7???\f3?",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "kn-9397c74b-35f3-4428-b4b0-5123353bbcd1",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "knw-9e74ee95-ba7d-49b1-9262-977eae9729d1",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-f8974b26-78a6-4aad-b893-19a73b20013d",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "?of?7???",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1668.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "????7???Ջ3",
+    "a1000001-0000-0000-0000-000000000001",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "?ǚ?7??????",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "7?e?7???\f3?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1535.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "mem-bbb126a1-b297-42bb-86be-796871829c94",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "mem-45022957-2d78-48aa-a714-16d6eca52e0f",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1565.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "?ǚ?7??????",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "7?e?7???\f3?",
+    "ctx-bb74",
+    "??S?7???",
+    "knw-f671966c-3387-4848-abca-b5deec122e00"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1279.3,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "? ?}&?#??X\b",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "? ?}&?#??X\b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1408.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "? ?}&?#??X\b",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "? ?}&?#??X\b",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1538.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.3333333333333333
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-e0bdf5d8-d163-491f-b649-453fee8b721d",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1168.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "? ?}&?#??X\b",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1290.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.36363636363636365,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "ctx-e5427d7d",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "ctx-bb74",
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-8c2d5f51-3ccd-4c2e-848a-eb60d90a3b98"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1245.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "knw-9e74ee95-ba7d-49b1-9262-977eae9729d1",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b"
+   ],
+   "n_returned": 9,
+   "latency_ms": 1277.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.09090909090909091,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "? ?}&?#??X\b",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "? ?}&?#??X\b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "? ?}&?#??X\b",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1486.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.2727272727272727,
+   "precision@5": 0.0,
+   "mrr@10": 0.16666666666666666
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 757.4,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 510.6,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "?V?",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "?m?\\}Q??6??",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "?m?\\}Q??6??",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 764.0,
+   "error": null,
+   "clean": false,
+   "false_positives": 10
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "7?e?7???\f3?",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "? ?}&?#??X\b",
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "? ?}&?#??X\b",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "?of?7???",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "? ?}&?#??X\b",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1340.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 10
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "? ?}&?#??X\b",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "? ?}&?#??X\b",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "? ?}&?#??X\b",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "? ?}&?#??X\b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1701.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "7?e?7???\f3?",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "? ?}&?#??X\b",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "%???2??jH??"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1029.8,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}
@@ -0,0 +1,957 @@
+{
+ "label": "semseed",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-semseed",
+ "soul_md5": "ab0c82781215f43d4907bd6f39d3615b",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-semseed/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7893,
+ "wall_clock_s": 52.7,
+ "child_pid": 88601,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.6857142857142857,
+  "recall@5": 0.5213459159887731,
+  "recall@10": 0.6027048348476919,
+  "precision@5": 0.18285714285714294,
+  "mrr@10": 0.4608730158730158,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1227.1,
+  "latency_ms_p95": 1692.6,
+  "latency_ms_max": 1710.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.07342657342657344,
+    "recall@10": 0.24825174825174823,
+    "mrr@10": 0.20833333333333334
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 0.7142857142857143,
+    "recall@5": 0.40093537414965985,
+    "recall@10": 0.5150226757369615,
+    "mrr@10": 0.6507936507936508
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 295.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 341.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 313.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 310.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 318.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 310.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "????7???Ջ3",
+    "kn-363f4976-6946-4b4d-b51b-8a2b0f5aef25",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "ctx-63e3",
+    "?ǚ?7??????",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 610.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 537.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "? ?}&?#??X\b",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 542.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.3333333333333333,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "ԍ????X????",
+    "project-harmonic-framework",
+    "?ǚ?7??????",
+    "project-harmonic-framework_com",
+    "knw-e24d6339-5ff3-4bed-ba53-707ffd0dc70a",
+    "??????X??2c",
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "????7???Ջ3",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356"
+   ],
+   "n_returned": 10,
+   "latency_ms": 518.4,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.0,
+   "mrr@10": 0.1111111111111111
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 531.4,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.5,
+   "precision@5": 0.0,
+   "mrr@10": 0.1111111111111111
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 888.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.2857142857142857,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.8,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "?",
+    "mem-dba009a2-d2ea-4f5a-b9e8-0f04bc9ab32f",
+    "?",
+    "mem-7cd90611-88a3-423d-a38a-0db2812952fa",
+    "?",
+    "bl-07375bf9-a169-42cd-adb3-7d32b25982f0",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 762.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.3333333333333333
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1652.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-2f29ad36-6ee6-4a0e-8d72-0eaf7d12d3a9",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "art-2fabd873-d787-49cb-ad30-d4ed9fcff8ef",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-a31e1001-342e-4deb-a2e6-6d02d1f22dee",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "knw-9e74ee95-ba7d-49b1-9262-977eae9729d1"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1706.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "7?e?7???\f3?",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-f8974b26-78a6-4aad-b893-19a73b20013d",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "?of?7???",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "? ?}&?#??X\b",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "????7???Ջ3"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1419.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "kn-d7c1e0fb-fa59-46d3-b4c9-a0d1d437a491",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "7?e?7???\f3?",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "??o?'?B???k",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "? ?}&?#??X\b",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "? ?}&?#??X\b",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1167.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "7?e?7???\f3?",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "?of?7???",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "imp-dce1da0f-8776-4a9e-972b-33411a7ca138",
+    "ctx-cc7f",
+    "ctx-4a41",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 9,
+   "latency_ms": 1489.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "knw-e24d6339-5ff3-4bed-ba53-707ffd0dc70a",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-57b4c5e7-40c6-4c90-bf14-71841b0081d4",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1330.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "? ?}&?#??X\b",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "? ?}&?#??X\b",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "? ?}&?#??X\b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1671.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "? ?}&?#??X\b",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "? ?}&?#??X\b",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "? ?}&?#??X\b",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1449.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "7?e?7???\f3?",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "knw-9e74ee95-ba7d-49b1-9262-977eae9729d1",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-f8974b26-78a6-4aad-b893-19a73b20013d",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-9397c74b-35f3-4428-b4b0-5123353bbcd1",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "?of?7???",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1710.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "????7???Ջ3",
+    "a1000001-0000-0000-0000-000000000001",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "?ǚ?7??????",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "7?e?7???\f3?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1565.1,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "mem-bbb126a1-b297-42bb-86be-796871829c94",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "mem-45022957-2d78-48aa-a714-16d6eca52e0f",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1629.0,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "?ǚ?7??????",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "7?e?7???\f3?",
+    "ctx-bb74",
+    "??S?7???",
+    "knw-f671966c-3387-4848-abca-b5deec122e00"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1326.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "? ?}&?#??X\b",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "? ?}&?#??X\b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1382.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "? ?}&?#??X\b",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "? ?}&?#??X\b",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1530.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.3333333333333333
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-e0bdf5d8-d163-491f-b649-453fee8b721d",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1159.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "? ?}&?#??X\b",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "? ?}&?#??X\b",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1232.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.36363636363636365,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "art-ee615cdb-e599-423d-9a4d-977859390ed3",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "ctx-e5427d7d",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "ctx-bb74",
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-8c2d5f51-3ccd-4c2e-848a-eb60d90a3b98"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1227.1,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "knw-9e74ee95-ba7d-49b1-9262-977eae9729d1",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b"
+   ],
+   "n_returned": 9,
+   "latency_ms": 1240.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.09090909090909091,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "? ?}&?#??X\b",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "? ?}&?#??X\b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "? ?}&?#??X\b",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "? ?}&?#??X\b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1464.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.2727272727272727,
+   "precision@5": 0.0,
+   "mrr@10": 0.16666666666666666
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 756.0,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 517.1,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [
+    "art-4a99aa1a-489b-4b43-958b-25217adb1aad",
+    "?V?",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "?m?\\}Q??6??",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "?m?\\}Q??6??",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 755.8,
+   "error": null,
+   "clean": false,
+   "false_positives": 10
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "7?e?7???\f3?",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "? ?}&?#??X\b",
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "? ?}&?#??X\b",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "?of?7???",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "? ?}&?#??X\b",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1329.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 10
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "? ?}&?#??X\b",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "? ?}&?#??X\b",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "? ?}&?#??X\b",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "? ?}&?#??X\b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1692.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "kn-5584ef9c-7f9d-4d7c-a10a-4ee6bc5cf356",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "7?e?7???\f3?",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "? ?}&?#??X\b",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "%???2??jH??"
+   ],
+   "n_returned": 10,
+   "latency_ms": 1040.0,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}
@@ -0,0 +1,948 @@
+{
+ "label": "wordstart-r2",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-wordstart",
+ "soul_md5": "32d4cf77672658a5f49dc7c9213e3ba2",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-eval/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7895,
+ "wall_clock_s": 28.7,
+ "child_pid": 1490,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "3/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 537.6,
+  "latency_ms_p95": 733.7,
+  "latency_ms_max": 761.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 3,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 165.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 164.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 163.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 172.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 167.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 164.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "tag-patterns",
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "project-Imprint__system_design__ADRs__tech_strategy__integration_patterns__governance_",
+    "project-Imprint__analysis_patterns__data_storytelling__SQL__dashboards__insight_framing_",
+    "bl-79028eed-c330-4724-9402-734062d13503",
+    "bl-39dad13d-7105-4049-8224-dc3c34fdb1f3",
+    "bl-4ef4d914-da46-4e0f-be78-5219b9547e9f",
+    "bl-7e7c3fdb-4132-487f-aa70-b2cd559cb7f0",
+    "bl-1d32bd54-cf17-4a1f-b235-982d09a36f04",
+    "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 281.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 254.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 255.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.4444444444444444,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "project-harmonic-framework",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "project-harmonic-framework_com",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "tag-harmonic-design",
+    "bl-92acd4eb-0452-4e8e-9f54-f8cd35170d76",
+    "tag-harmonic-framework",
+    "bl-18a9d1e4-1484-474c-bf6b-c6173212181b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 247.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1111111111111111,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-sarah",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "mem-1f32f73a-952c-41bc-96dc-8b8b70d8a7c1",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-a6cb3b8d-d89c-46fc-931d-e90c560783b0",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 263.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.4,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "?Q??m?;?u?'",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 397.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.21428571428571427,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "?",
+    "bl-ec84b63d-b278-4944-8d7f-4aa7a51c0315",
+    "?",
+    "mem-fb44a2fc-7405-41ff-87b3-84643ac07313",
+    "?",
+    "mem-a3c97012-5fa3-4915-a839-2c75c72005e0",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 341.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "cb070131-dfd4-4a38-91d7-22b1bde164d2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "knw-d788a210-613b-4c49-9486-88bbc9d4716f",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-a535f205-bc4c-4058-9171-6263c496044a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-0228da71-d7f7-4f3b-b7b3-c5eede42b62a",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 761.4,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "b1183213-d659-4759-85d7-5b1f22427fe2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "7452eb8f-be01-4b55-aec1-ff0c29e790f6",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "532277bf-2959-4beb-ae0d-b018c97678ee",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "d4015bd7-c592-4ed8-8574-1f15ad37af75"
+   ],
+   "n_returned": 10,
+   "latency_ms": 733.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "tag-fiction",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "mem-443bd012-fc9a-4088-b236-de5157a1ef92",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "mem-ca4d6a34-d354-413f-bc86-126cc17ca81c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 629.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "4da5dbaf-46e5-4f3e-b474-f60d9f8241d3",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "mem-434be7c8-88cb-4039-b79a-1da4ac4de783",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
+   ],
+   "n_returned": 10,
+   "latency_ms": 529.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-e5cc63c0-8701-49d6-855a-e387fe087771",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "mem-75e490d1-f0a9-4b73-8cfc-8daecfaf6f38",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "a1000001-0000-0000-0000-000000000010",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "bfad516b-c306-4c4c-874a-a347c46c05c2",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 747.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "tag-learning",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "345b6420-e004-4d2e-b55c-6a729393fa99",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-92a7fdc5-9dd0-48cf-a691-506058de3838",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000010",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 564.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "mem-cde58b77-50d3-4bac-9581-e70a4c02c015",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-8d699e2c-ac2a-4742-bb62-b6da00f4b10e",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-53d6adf0-cd08-4707-a237-daa5e65c7298",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac"
+   ],
+   "n_returned": 10,
+   "latency_ms": 689.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "bl-0e8f4880-7b24-43aa-aed9-ad4d9fc73ff8",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "bl-205141ad-b2a0-4d93-86d0-89eb0723e1bd",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "bl-34f51ddb-a840-459f-a248-94214f5febb6",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 588.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
+    "34356a36-0df5-4020-8dcc-5e7a423f8d4c",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "mem-22f5f665-3ad2-4063-88b0-915849a795f5",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 729.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000001",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-1b58b05c-9305-4f06-a586-a08c96008027",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "ctx-4a41",
+    "mem-5708f4c9-3d61-4182-8543-2843698931e6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 638.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "27e1b1a4-ad0b-49d9-812f-fedf43b8aabe",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "bl-87c93185-b2bf-40af-ae23-3c830c007abf",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "fce2792a-53fc-4d4a-be3b-42bd6ceb1ba7",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 679.0,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "mem-82158b02-a180-435d-84f0-0b7ce37511b4",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "e4f27651-52c5-43fd-aff3-61d31685b3cd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-a16deccb-16a7-419c-a013-ff824a4daa15",
+    "a1000001-0000-0000-0000-000000000009",
+    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 588.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-23c27d3b-e0d2-43a8-a80c-0a44477ae18a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "tag-childhood",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 613.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "efe53612-6914-4936-8e3b-1e694eb174e5",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 652.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-9110798f-d0cb-4446-bc2a-14f09b6a09e2",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 543.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-trailer-park-paladins",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "project-trailer-park-paladins",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 537.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-bea7473c-c687-414c-9c0b-00c509a616c1",
+    "bl-fc6fcb0b-9e4b-40bf-8e88-dbfe4e27c31a",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 538.3,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "tag-hope",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 533.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.18181818181818182,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-473f3f24-20f6-4f39-8589-3709538eb6ac",
+    "mem-a0b7cfda-bc9e-4f40-b9a9-1722cf3f8263",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "719aa819-00a9-4f4b-a857-4f9fe5ad44d7",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 673.8,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 350.7,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 254.6,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 345.8,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____architecture__",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____kotlin____architecture__",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "mem-c17aefb1-38b5-4ced-af50-fe524127e1a4",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 639.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 8
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "mem-6f0b2b45-90c1-4356-ac01-3daac05b09c8",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "13705072-4515-4124-963d-083af490494f",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "a1000001-0000-0000-0000-000000000002",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "de3b6428-b76c-4c44-90e0-bf1dd6998027"
+   ],
+   "n_returned": 10,
+   "latency_ms": 733.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "5fcba804-eb5b-48ec-82da-146b1c6bb50d",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "bl-c5c6571e-118f-47c7-8cbb-3ed0ebf64a51",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "86228228-7adf-41fb-b4c4-9ceea87953ae",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 507.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}
@@ -0,0 +1,948 @@
+{
+ "label": "wordstart",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-wordstart",
+ "soul_md5": "32d4cf77672658a5f49dc7c9213e3ba2",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-eval/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7894,
+ "wall_clock_s": 28.9,
+ "child_pid": 1420,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "3/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 542.6,
+  "latency_ms_p95": 741.3,
+  "latency_ms_max": 758.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 3,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 170.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 210.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 167.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 166.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 162.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 162.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "tag-patterns",
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "project-Imprint__system_design__ADRs__tech_strategy__integration_patterns__governance_",
+    "project-Imprint__analysis_patterns__data_storytelling__SQL__dashboards__insight_framing_",
+    "bl-79028eed-c330-4724-9402-734062d13503",
+    "bl-39dad13d-7105-4049-8224-dc3c34fdb1f3",
+    "bl-4ef4d914-da46-4e0f-be78-5219b9547e9f",
+    "bl-7e7c3fdb-4132-487f-aa70-b2cd559cb7f0",
+    "bl-1d32bd54-cf17-4a1f-b235-982d09a36f04",
+    "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 306.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 261.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 272.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.4444444444444444,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "project-harmonic-framework",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "project-harmonic-framework_com",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "tag-harmonic-design",
+    "bl-92acd4eb-0452-4e8e-9f54-f8cd35170d76",
+    "tag-harmonic-framework",
+    "bl-18a9d1e4-1484-474c-bf6b-c6173212181b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 265.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1111111111111111,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-sarah",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "mem-1f32f73a-952c-41bc-96dc-8b8b70d8a7c1",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-a6cb3b8d-d89c-46fc-931d-e90c560783b0",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 271.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.4,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "?Q??m?;?u?'",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 412.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.21428571428571427,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "?",
+    "bl-ec84b63d-b278-4944-8d7f-4aa7a51c0315",
+    "?",
+    "mem-fb44a2fc-7405-41ff-87b3-84643ac07313",
+    "?",
+    "mem-a3c97012-5fa3-4915-a839-2c75c72005e0",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 377.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "cb070131-dfd4-4a38-91d7-22b1bde164d2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "knw-d788a210-613b-4c49-9486-88bbc9d4716f",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-a535f205-bc4c-4058-9171-6263c496044a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-0228da71-d7f7-4f3b-b7b3-c5eede42b62a",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 758.8,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "b1183213-d659-4759-85d7-5b1f22427fe2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "7452eb8f-be01-4b55-aec1-ff0c29e790f6",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "532277bf-2959-4beb-ae0d-b018c97678ee",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "d4015bd7-c592-4ed8-8574-1f15ad37af75"
+   ],
+   "n_returned": 10,
+   "latency_ms": 741.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "tag-fiction",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "mem-443bd012-fc9a-4088-b236-de5157a1ef92",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "mem-ca4d6a34-d354-413f-bc86-126cc17ca81c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 642.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "4da5dbaf-46e5-4f3e-b474-f60d9f8241d3",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "mem-434be7c8-88cb-4039-b79a-1da4ac4de783",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
+   ],
+   "n_returned": 10,
+   "latency_ms": 537.2,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-e5cc63c0-8701-49d6-855a-e387fe087771",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "mem-75e490d1-f0a9-4b73-8cfc-8daecfaf6f38",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "a1000001-0000-0000-0000-000000000010",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "bfad516b-c306-4c4c-874a-a347c46c05c2",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 725.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "tag-learning",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "345b6420-e004-4d2e-b55c-6a729393fa99",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-92a7fdc5-9dd0-48cf-a691-506058de3838",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000010",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 562.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "mem-cde58b77-50d3-4bac-9581-e70a4c02c015",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-8d699e2c-ac2a-4742-bb62-b6da00f4b10e",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-53d6adf0-cd08-4707-a237-daa5e65c7298",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac"
+   ],
+   "n_returned": 10,
+   "latency_ms": 686.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "bl-0e8f4880-7b24-43aa-aed9-ad4d9fc73ff8",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "bl-205141ad-b2a0-4d93-86d0-89eb0723e1bd",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "bl-34f51ddb-a840-459f-a248-94214f5febb6",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 584.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
+    "34356a36-0df5-4020-8dcc-5e7a423f8d4c",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "mem-22f5f665-3ad2-4063-88b0-915849a795f5",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 719.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000001",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-1b58b05c-9305-4f06-a586-a08c96008027",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "ctx-4a41",
+    "mem-5708f4c9-3d61-4182-8543-2843698931e6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 634.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "27e1b1a4-ad0b-49d9-812f-fedf43b8aabe",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "bl-87c93185-b2bf-40af-ae23-3c830c007abf",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "fce2792a-53fc-4d4a-be3b-42bd6ceb1ba7",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 674.2,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "mem-82158b02-a180-435d-84f0-0b7ce37511b4",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "e4f27651-52c5-43fd-aff3-61d31685b3cd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-a16deccb-16a7-419c-a013-ff824a4daa15",
+    "a1000001-0000-0000-0000-000000000009",
+    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 571.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-23c27d3b-e0d2-43a8-a80c-0a44477ae18a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "tag-childhood",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 603.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "efe53612-6914-4936-8e3b-1e694eb174e5",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 656.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-9110798f-d0cb-4446-bc2a-14f09b6a09e2",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 536.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-trailer-park-paladins",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "project-trailer-park-paladins",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 562.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-bea7473c-c687-414c-9c0b-00c509a616c1",
+    "bl-fc6fcb0b-9e4b-40bf-8e88-dbfe4e27c31a",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 556.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "tag-hope",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 542.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.18181818181818182,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-473f3f24-20f6-4f39-8589-3709538eb6ac",
+    "mem-a0b7cfda-bc9e-4f40-b9a9-1722cf3f8263",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "719aa819-00a9-4f4b-a857-4f9fe5ad44d7",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 683.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 350.4,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 258.4,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 348.4,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____architecture__",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____kotlin____architecture__",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "mem-c17aefb1-38b5-4ced-af50-fe524127e1a4",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 664.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 8
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "mem-6f0b2b45-90c1-4356-ac01-3daac05b09c8",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "13705072-4515-4124-963d-083af490494f",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "a1000001-0000-0000-0000-000000000002",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "de3b6428-b76c-4c44-90e0-bf1dd6998027"
+   ],
+   "n_returned": 10,
+   "latency_ms": 747.3,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "5fcba804-eb5b-48ec-82da-146b1c6bb50d",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "bl-c5c6571e-118f-47c7-8cbb-3ed0ebf64a51",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "86228228-7adf-41fb-b4c4-9ceea87953ae",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 504.2,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}
@@ -0,0 +1,142 @@
+import numpy as np, json, urllib.request, collections, math, re, sys, time
+SP="/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad"
+EV="/Users/timlingo/Development/neuron-technologies/_wt-semseed/tools/retrieval-eval/"
+np.seterr(all='ignore')
+t0=time.time()
+M=np.load(SP+'/emb.npy'); eids=open(SP+'/ids.txt',encoding='utf-8',errors='surrogateescape').read().split('\n')
+eidx={k:i for i,k in enumerate(eids)}
+d=json.load(open('/Users/timlingo/neuron-memory-backups/snapshot-pre-repair-20260806.json',encoding='utf-8',errors='surrogateescape'))
+print("loaded corpus %.1fs"%(time.time()-t0),file=sys.stderr)
+STRUCT={"identity","contains","superseded_by","references","embodies","demonstrated_by","canonical-self","depends_on","currently_holds","activates"}
+adj=collections.defaultdict(list)
+for e in d['edges']:
+    if e.get('relation') not in STRUCT: continue
+    w=float(e.get('weight') or 0.0)
+    adj[e['from_id']].append((e['to_id'],w)); adj[e['to_id']].append((e['from_id'],w))
+nodes=d['nodes']
+N={n['id']:n for n in nodes}
+PRINT=re.compile(r'^[\x20-\x7e]+$')
+ids=[]; hay=[]; dl=[]; sal=[]; addressable=[]
+for n in nodes:
+    i=n.get('id') or ''
+    h=((n.get('content') or '')+'\x00'+(n.get('label') or '')+'\x00'+(n.get('tags') or '')).lower()
+    ids.append(i); hay.append(h); dl.append(len(h)); sal.append(float(n.get('salience') or 0.0))
+    addressable.append(bool(PRINT.match(i)))
+del d
+NN=len(ids); avgdl=sum(dl)/NN
+print("nodes=%d avgdl=%.0f addressable=%d  %.1fs"%(NN,avgdl,sum(addressable),time.time()-t0),file=sys.stderr)
+gold={q['id']:q for q in json.load(open(EV+"gold_set.json"))['queries']}
+LEXMAIN={r['id']:r['returned'] for r in json.load(open(EV+"results-main.json"),) ['rows']} if False else {r['id']:r['returned'] for r in json.load(open(EV+"results-main.json",encoding='utf-8',errors='surrogateescape'))['rows']}
+CACHE={}
+def emb(t):
+    if t in CACHE: return CACHE[t]
+    b=json.dumps({"model":"nomic-embed-text","prompt":t}).encode()
+    r=urllib.request.Request("http://127.0.0.1:11434/api/embeddings",data=b,headers={"Content-Type":"application/json"})
+    v=np.array(json.load(urllib.request.urlopen(r,timeout=60))["embedding"],dtype=np.float32)
+    v=v/(np.linalg.norm(v)+1e-9); CACHE[t]=v; return v
+K1,B=1.2,0.75
+def lexleg(query, mode, guard, lim=10):
+    toks=[]
+    for w in query.split():
+        wl=w.lower()
+        if wl not in toks: toks.append(wl)
+    nt=len(toks)
+    masks=[]; df=[0]*nt
+    for i in range(NN):
+        if guard and not addressable[i]: continue
+        h=hay[i]; m=0; sc=0
+        for t in range(nt):
+            if toks[t] in h: m|=(1<<t); sc+=1; df[t]+=1
+        if sc: masks.append((i,m,sc))
+    if mode=='tokcount':
+        masks.sort(key=lambda x:(-x[2], -sal[x[0]]))
+        return [ids[i] for i,m,sc in masks[:lim]]
+    idf=[math.log(1.0+(NN-df[t]+0.5)/(df[t]+0.5)) for t in range(nt)]
+    scored=[]
+    for i,m,sc in masks:
+        norm=1.0-B+B*dl[i]/avgdl
+        s=0.0
+        for t in range(nt):
+            if m&(1<<t): s+=idf[t]*(K1+1.0)/(1.0+K1*norm)
+        scored.append((s,i))
+    scored.sort(key=lambda x:(-x[0], -sal[x[1]]))
+    return [ids[i] for s,i in scored[:lim]]
+FIRE=0.02; DECAY=0.7; DEPTH=2; SEED_MIN=0.60; ASSOC_MAX=64
+def assoc(seeds, s):
+    act={x:1.0 for x in seeds}; seen={x:2 for x in seeds}
+    Q=[(x,0) for x in seeds]; h=0
+    while h<len(Q):
+        cur,hop=Q[h]; h+=1
+        if hop>=DEPTH: continue
+        p=act[cur]
+        for oid,w in adj.get(cur,()):
+            n=N.get(oid)
+            if not n or n.get('node_type') in ('Tag','InternalStateEvent'): continue
+            na=p*w*DECAY*float(n.get('salience') or 0.0)
+            if na<FIRE: continue
+            if oid in seen and na<=act.get(oid,0): continue
+            act[oid]=na
+            if oid not in seen: seen[oid]=1
+            Q.append((oid,hop+1))
+    out=[]
+    for k,v in seen.items():
+        if v!=1 or k not in eidx: continue
+        c=float(s[eidx[k]])
+        if c<=0: continue
+        out.append((c,k))
+    out.sort(reverse=True)
+    return [k for c,k in out[:ASSOC_MAX]]
+def inter3(L,S,A,lim=10):
+    out=[]; li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(S) or ai<len(A)):
+        if li<len(L):
+            if L[li] not in out: out.append(L[li])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(S):
+            if S[si] not in out: out.append(S[si])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai] not in out: out.append(A[ai])
+            ai+=1
+    return out
+def run(mode, guard, use_main_lex=False):
+    res={}; legs={}
+    for qid,q in gold.items():
+        v=emb(q['query']); s=M@v; s[~np.isfinite(s)]=-1
+        L = LEXMAIN[qid][:10] if use_main_lex else lexleg(q['query'], mode, guard)
+        ordr=np.argsort(-s)
+        S=[eids[j] for j in ordr[:10] if s[j]>SEED_MIN]
+        if guard: S=[x for x in S if PRINT.match(x or '')]
+        seeds=[x for x in L[:3] if x in N]
+        seeds=seeds+[eids[j] for j in ordr[:8] if eids[j] in N and eids[j] not in seeds and (not guard or PRINT.match(eids[j] or ''))]
+        A=assoc(seeds,s) if seeds else []
+        if guard: A=[x for x in A if PRINT.match(x or '')]
+        res[qid]=inter3(L,S,A); legs[qid]=(L,S,A)
+    return res,legs
+def score(res,label,verbose=False):
+    det={}
+    for qid,q in gold.items():
+        out=res[qid][:5]
+        if q['category']=='nonsense': ok=(len(res[qid])==0)
+        elif q['category']=='superseded':
+            must=q.get('must_outrank') or {}; ok=False
+            for good,bad in (must.items() if isinstance(must,dict) else []):
+                ok = good in res[qid] and (bad not in res[qid] or res[qid].index(good)<res[qid].index(bad))
+            if not must: ok=any(r in out for r in q['relevant'])
+        else: ok=any(r in out for r in q['relevant'])
+        det[qid]=ok
+    print("%-28s outcome-true=%d/38"%(label,sum(det.values())))
+    return det
+if __name__=="__main__":
+    base,_=run('tokcount',False,use_main_lex=True); b=score(base,'BASELINE semseed(real lex)')
+    variants=[('tokcount',False,'replica: tokcount,noguard'),
+              ('tokcount',True ,'A: tokcount + idguard'),
+              ('bm25',    False,'B: bm25 only'),
+              ('bm25',    True ,'C: bm25 + idguard')]
+    dets={}
+    for m,g,lab in variants:
+        r,_=run(m,g); dets[lab]=score(r,lab)
+        dd=[q for q in gold if dets[lab][q]!=b[q]]
+        print("     vs BASELINE moved=%d gains=%s losses=%s"%(len(dd),[q for q in dd if dets[lab][q]],[q for q in dd if not dets[lab][q]]))
@@ -0,0 +1,92 @@
+import json,sys,pickle,numpy as np
+sys.path.insert(0,'.')
+from legs import *
+GP='/Users/timlingo/Development/neuron-technologies/_wt-bm25lex/tools/retrieval-eval/'
+G=json.load(open(GP+'gold_set.json'))
+def wstart(s,tok):
+    i=s.find(tok)
+    while i!=-1:
+        if i==0 or not s[i-1].isalnum(): return True
+        i=s.find(tok,i+1)
+    return False
+def legs4(query, wordstart=False, unfloor=False):
+    toks=tokenize(query); lt=[t.lower() for t in toks]
+    hit_idx=[];hit_mask=[];df=[0]*len(toks)
+    for i in range(N):
+        if not OK[i]: continue
+        s=LOW[i];m=0
+        for t,tok in enumerate(lt):
+            if tok in s and (not wordstart or wstart(s,tok)): m|=(1<<t)
+        if m:
+            hit_idx.append(i);hit_mask.append(m)
+            for t in range(len(toks)):
+                if m>>t&1: df[t]+=1
+    dl_n=int(OK.sum());avgdl=float(DL[OK].sum()/max(dl_n,1))
+    idf=[math.log(1.0+((dl_n-d+0.5)/(d+0.5))) for d in df]
+    L=[]
+    for j,i in enumerate(hit_idx):
+        norm=1.0-B+B*(DL[i]/avgdl);w=0.0
+        for t in range(len(toks)):
+            if hit_mask[j]>>t&1: w+=idf[t]*(K1+1.0)/(1.0+K1*norm)
+        L.append((i,w,SAL[i]))
+    L.sort(key=lambda x:(-x[1],-x[2]))
+    if not L: return [],[],[]
+    qv=qemb(query);cos=En@qv;cos=np.where(HAVE&OK,cos,-2.0)
+    order=np.argsort(-cos)[:600]
+    Sl=[int(i) for i in order if cos[i]>(0.0 if unfloor else SEED_MIN)]
+    semseed=[int(i) for i in order[:SEED_K] if cos[i]>0.0]
+    act={};seen={};qq=[]
+    for i,_,_ in L[:ASSOC_SEEDS]:
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    for i in semseed:
+        if i in seen: continue
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    qh=0
+    while qh<len(qq):
+        cur,h=qq[qh];qh+=1
+        if h>=DEPTH: continue
+        parent=act[cur]
+        for e,oi in ADJ_F[cur]+ADJ_T[cur]:
+            if e['rel'] not in STRUCT or EXCL[oi]: continue
+            na=parent*e['w']*DECAY*SAL[oi]
+            if na<FIRE: continue
+            if seen.get(oi) and na<=act.get(oi,0): continue
+            act[oi]=na
+            if not seen.get(oi): seen[oi]=1
+            if len(qq)<AMAX*4: qq.append((oi,h+1))
+    A=sorted([(i,float(cos[i])) for i,st in seen.items() if st==1 and OK[i] and HAVE[i] and cos[i]>0.0],key=lambda x:-x[1])[:AMAX]
+    return [i for i,_,_ in L],Sl,[i for i,_ in A]
+def merge(L,S,A,lim=10):
+    out=[];li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(S) or ai<len(A)):
+        if li<len(L):
+            if L[li] not in out: out.append(L[li])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(S):
+            if S[si] not in out: out.append(S[si])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai] not in out: out.append(A[ai])
+            ai+=1
+    return out
+def outcome(q,ids):
+    c=q['category']
+    if c=='nonsense': return len(ids)==0
+    if c=='superseded':
+        a,b=q['must_outrank']
+        if a not in ids: return False
+        if b not in ids: return True
+        return ids.index(a)<ids.index(b)
+    return any(x in ids[:5] for x in q['relevant'])
+def run(**kw):
+    return {q['id']:outcome(q,[NODES[i]['id'] for i in merge(*legs4(q['query'],**kw),10)]) for q in G['queries']}
+base=run()
+print("baseline",sum(base.values()),"misses",[k for k,v in base.items() if not v])
+for name,kw in [('wordstart',dict(wordstart=True)),
+                ('unfloor',dict(unfloor=True)),
+                ('wordstart+unfloor',dict(wordstart=True,unfloor=True))]:
+    r=run(**kw)
+    g=sorted(k for k in base if r[k] and not base[k]);l=sorted(k for k in base if base[k] and not r[k])
+    print("%-20s net=%+d gains=%s losses=%s"%(name,len(g)-len(l),g,l))
@@ -0,0 +1,31 @@
+import numpy as np, json, urllib.request
+SP="/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad"
+M=np.load(SP+'/emb.npy'); ids=open(SP+'/ids.txt',encoding='utf-8',errors='surrogateescape').read().split('\n')
+np.seterr(all='ignore')
+bad=~np.isfinite(M).all(axis=1)
+M[bad]=0.0
+print("non-finite rows zeroed:",int(bad.sum()))
+idx={k:i for i,k in enumerate(ids)}
+gold=json.load(open("/Users/timlingo/Development/neuron-technologies/_wt-assoc-leg/tools/retrieval-eval/gold_set.json"))['queries']
+def emb(t):
+    b=json.dumps({"model":"nomic-embed-text","prompt":t}).encode()
+    r=urllib.request.Request("http://127.0.0.1:11434/api/embeddings",data=b,headers={"Content-Type":"application/json"})
+    v=np.array(json.load(urllib.request.urlopen(r,timeout=60))["embedding"],dtype=np.float32)
+    return v/(np.linalg.norm(v)+1e-9)
+out={}
+for q in gold:
+    v=emb(q['query']); s=M@v
+    s=s[np.isfinite(s)]
+    mu=float(s.mean()); sd=float(s.std())
+    top=np.sort(s)[::-1][:10]
+    z=[(float(t)-mu)/sd for t in top]
+    grank=[]
+    for rel in q['relevant']:
+        if rel in idx:
+            j=idx[rel]; grank.append((int((M@v > (M@v)[j]).sum())+1, round(float((M@v)[j]),3)))
+    grank.sort()
+    out[q['id']]=dict(cat=q['category'],mu=round(mu,3),sd=round(sd,4),top1=round(float(top[0]),3),
+                      z1=round(z[0],2),z3=round(z[2],2),z5=round(z[4],2),gold=grank[:1])
+    print("%s %-11s mu=%.3f sd=%.4f top1=%.3f z1=%5.2f z3=%5.2f z5=%5.2f gold=%s"%(
+        q['id'],q['category'],mu,sd,top[0],z[0],z[2],z[4],grank[:1]))
+json.dump(out,open(SP+'/zprobe.json','w'),indent=1)
@@ -7175,6 +7175,12 @@ void engram_forget(el_val_t node_id) {
    if (idx < 0) return;
    /* Free node strings */
    EngramNode* n = &g->nodes[idx];
+    if (getenv("EG_DIAG")) {
+        fprintf(stderr, "[EG_DIAG] FORGET id=%s type=%s layer=%u label=%s\n",
+                sid, n->node_type ? n->node_type : "?", n->layer_id,
+                n->label ? n->label : "?");
+        fflush(stderr);
+    }
    free(n->id); free(n->content); free(n->node_type); free(n->label);
    free(n->tier); free(n->tags); free(n->metadata);
    free(n->emb);
@@ -7270,6 +7276,8 @@ el_val_t engram_prune_telemetry(el_val_t older_than_ms) {
        }
    }
    g->node_count = w;
+    if (getenv("EG_DIAG"))
+        fprintf(stderr, "[EG_DIAG] PRUNE_TELEMETRY removed=%lld\n", (long long)removed);
    if (removed == 0) { free(removed_ids); return 0; }

    /* Removed-id hash set (open addressing, power-of-two >= 2*removed). */
@@ -7327,6 +7335,39 @@ static int istr_contains(const char* hay, const char* needle) {
    return 0;
 }

+/* Word-START-anchored variant of istr_contains.
+ *
+ * WHY. The retrieval match primitive is a raw substring test, so a query token
+ * matches ANYWHERE inside a corpus word: "throom" matches "bathroom", "cat"
+ * matches "concatenate". Measured on this corpus over the 38-query gold set,
+ * that is not a rare accident — it is the bulk of some queries' candidate
+ * sets. q28's lexical leg is 36,954 records of which only 13 contain a query
+ * token at a word start (99.96% mid-word noise); six other queries carry
+ * ~20,500 mid-word-only records each; and the nonsense control q35
+ * ("xxqzzt vurblenacht throom") returns 7 records ALL of which match only
+ * mid-word, which is the entire reason that control has been dirty since main.
+ *
+ * WHAT CHANGES. A token must begin at a word boundary — the preceding
+ * character is not alphanumeric. Suffixes are still matched ("value" still
+ * hits "values", "unjailbreakable" still hits "unjailbreakables"), so this is
+ * strictly a prefix anchor, not whole-word equality; whole-word equality would
+ * break the morphological matching the phrase category depends on.
+ *
+ * PROVENANCE, stated honestly: this restores no engram claim. Will's design
+ * has no lexical leg at all (05-detailed-description l.64 takes "one or more
+ * seed node UUIDs representing the current active context" as its input), so
+ * the lexical leg is the seed-finding step that feeds the designed mechanism.
+ * Cleaner seeds serve that mechanism; they do not replace it. */
+static int istr_contains_wordstart(const char* hay, const char* needle) {
+    if (!hay || !needle || !*needle) return 0;
+    size_t nl = strlen(needle);
+    for (const char* p = hay; *p; p++) {
+        if (p != hay && isalnum((unsigned char)p[-1])) continue;
+        if (strncasecmp(p, needle, nl) == 0) return 1;
+    }
+    return 0;
+}
+
 /* ── Tokenized query matching ───────────────────────────────────────────
 * The engram query surface (search / activate / goal-bias) historically
 * matched the ENTIRE raw query string as a single case-insensitive
@@ -7379,14 +7420,56 @@ static int engram_node_match_score(const EngramNode* n,
                                   char toks[][ENGRAM_QTOK_LEN], int ntok) {
    int score = 0;
    for (int t = 0; t < ntok; t++) {
-        if (istr_contains(n->content, toks[t]) ||
-            istr_contains(n->label,   toks[t]) ||
-            istr_contains(n->tags,    toks[t]))
+        if (istr_contains_wordstart(n->content, toks[t]) ||
+            istr_contains_wordstart(n->label,   toks[t]) ||
+            istr_contains_wordstart(n->tags,    toks[t]))
            score++;
    }
    return score;
 }

+/* Same match test as engram_node_match_score, but returns the SET of matched
+ * query tokens as a bitmask instead of only their count. ENGRAM_MAX_QTOKENS is
+ * 32, so one uint32 covers every token the tokenizer can produce. The mask is
+ * what lets the caller accumulate a per-token document frequency in the SAME
+ * pass that finds the hits — no second scan of the corpus. */
+static uint32_t engram_node_match_mask(const EngramNode* n,
+                                       char toks[][ENGRAM_QTOK_LEN], int ntok) {
+    uint32_t m = 0;
+    for (int t = 0; t < ntok && t < 32; t++) {
+        if (istr_contains_wordstart(n->content, toks[t]) ||
+            istr_contains_wordstart(n->label,   toks[t]) ||
+            istr_contains_wordstart(n->tags,    toks[t]))
+            m |= (uint32_t)1u << t;
+    }
+    return m;
+}
+
+/* Searchable byte length of a node: the same three fields the match test
+ * reads. Used as the BM25 document length so a long node does not out-match a
+ * short one merely by containing more text. */
+static double engram_node_len(const EngramNode* n) {
+    double l = 0.0;
+    if (n->content) l += (double)strlen(n->content);
+    if (n->label)   l += (double)strlen(n->label);
+    if (n->tags)    l += (double)strlen(n->tags);
+    return l;
+}
+
+/* Addressability guard. Claim 23 stores node records under a key encoding the
+ * node identifier, claim 12 deduplicates merged results by node identifier,
+ * and claim 27's competition map is indexed by node identifier — every one of
+ * those requires the identifier to be a usable string. This corpus contains
+ * records whose id field is binary garbage (a save-side corruption); they are
+ * unfetchable by any caller, so returning one wastes a result slot. Printable
+ * ASCII, non-empty, is the whole test. */
+static int eg_node_addressable(const EngramNode* n) {
+    const unsigned char* p = (const unsigned char*)n->id;
+    if (!p || !*p) return 0;
+    for (; *p; p++) if (*p < 0x20 || *p > 0x7e) return 0;
+    return 1;
+}
+
 /* Semantic leg of the read path (engram claim 24). Returns the query/target
 * cosine renormalized onto [0,1] over the band [ENGRAM_EMBED_SEED_MIN, 1.0],
 * and exactly 0.0 when the pair is not comparable (no query embedding, target
@@ -7406,7 +7489,12 @@ static double eg_sem_term(const EngramNode* n, const float* qv, int32_t qdim) {
 * (tiebreak, desc). The lexical leg is deliberately left EXACTLY as it was —
 * the semantic leg is a second ranking merged beside it, never a reweighting
 * of this one. */
-typedef struct { int64_t idx; int score; double salience; } EngramRankEntry;
+typedef struct {
+    int64_t  idx; int score; double salience;
+    uint32_t mask;      /* which query tokens matched (BM25 leg) */
+    double   len;       /* searchable byte length (BM25 leg)     */
+    double   w;         /* BM25-shaped weighted score            */
+} EngramRankEntry;
 static int engram_rank_cmp(const void* a, const void* b) {
    const EngramRankEntry* ea = (const EngramRankEntry*)a;
    const EngramRankEntry* eb = (const EngramRankEntry*)b;
@@ -7416,6 +7504,21 @@ static int engram_rank_cmp(const void* a, const void* b) {
    return 0;
 }

+/* BM25-shaped ordering for the read path's lexical leg: rare-term weight and
+ * length normalisation instead of a raw distinct-token count. Salience stays
+ * the tiebreak, exactly as in engram_rank_cmp. */
+#define ENGRAM_BM25_K1 1.2
+#define ENGRAM_BM25_B  0.75
+static int engram_rank_w_cmp(const void* a, const void* b) {
+    const EngramRankEntry* ea = (const EngramRankEntry*)a;
+    const EngramRankEntry* eb = (const EngramRankEntry*)b;
+    if (ea->w < eb->w) return 1;                                   /* desc */
+    if (ea->w > eb->w) return -1;
+    if (ea->salience < eb->salience) return 1;
+    if (ea->salience > eb->salience) return -1;
+    return 0;
+}
+
 /* Semantic rank entry: node index and its renormalized query similarity,
 * ordered by similarity desc. This is the claim-24 "embedding search"
 * ranking, computed independently of the lexical one. */
@@ -7531,8 +7634,30 @@ static int eg_assoc_excluded(const EngramNode* n) {
 * function of hop count and ranks the relay hub above all of its own
 * children. Composing the two is mine, not Will's — the description ranks the
 * activation result set by strength (l.78). */
+/* Semantic seeding of the graph leg — the HippoRAG pass Will documents at
+ * l.6082: "the query is embedded, the top-K nodes by cosine >= SEED_MIN join
+ * the seed set", using his own ENGRAM_EMBED_SEED_K (8). It is "similarity used
+ * twice, coherently": cosine picks where to STAND in the graph, the structural
+ * walk decides what is REACHABLE from there, and cosine then ORDERS what was
+ * reached (iteration-2's finding, kept intact).
+ *
+ * Why the seed list is NOT floored at ENGRAM_EMBED_SEED_MIN here. That
+ * constant is calibrated for a cosine scale this corpus does not have: with
+ * nomic-embed-text every true paraphrase target measures 0.46-0.66, and the
+ * three nonsense controls' own nearest neighbours measure 0.55/0.60/0.62 —
+ * they OVERLAP, so no absolute cosine floor separates signal from gibberish
+ * (measured, all 38 queries). Iteration 2 established the same thing one step
+ * later in the pipeline: applying the floor to graph CANDIDATES removed every
+ * gain, because within a structurally-reached neighbourhood relative cosine
+ * still discriminates below the absolute threshold. The gate that actually
+ * works is reachability — eg_rel_is_structural() plus the firing threshold.
+ * A semantically-near node with no structural attachment expands to nothing
+ * and contributes nothing, which is exactly what happens to gibberish: the
+ * nearest neighbours of q33/q34 are unattached, so their graph leg is empty.
+ */
 static int64_t engram_assoc_leg(EngramStore* g,
                                const EngramRankEntry* L, int64_t nL,
+                                const int64_t* semseed, int64_t nsemseed,
                                const float* qv, int32_t qdim,
                                EngramSemEntry* out, int64_t out_cap) {
    if (!g || nL <= 0 || !qv || qdim <= 0 || out_cap <= 0) return 0;
@@ -7553,6 +7678,14 @@ static int64_t engram_assoc_leg(EngramStore* g,
        act[idx] = 1.0; seen[idx] = 2;              /* 2 = seed: never a result */
        if (qt < qcap) { q[qt] = idx; hop[qt] = 0; qt++; }
    }
+    /* ...and the semantic seeds, on the same footing (strength 1.0, hop 0). */
+    for (int64_t s = 0; s < nsemseed; s++) {
+        int64_t idx = semseed[s];
+        if (idx < 0 || idx >= g->node_count) continue;
+        if (seen[idx]) continue;
+        act[idx] = 1.0; seen[idx] = 2;
+        if (qt < qcap) { q[qt] = idx; hop[qt] = 0; qt++; }
+    }

    const double SPREAD_DECAY = 0.7;
    while (qh < qt) {
@@ -7585,6 +7718,7 @@ static int64_t engram_assoc_leg(EngramStore* g,
        if (seen[i] != 1) continue;                 /* skip unreached and seeds */
        if (engram_layer_is_transparent(g->nodes[i].layer_id)) continue;
        EngramNode* nd = &g->nodes[i];
+        if (!eg_node_addressable(nd)) continue;   /* unfetchable record */
        if (!nd->emb || nd->emb_dim != qdim) continue;
        double c = eg_cosine(nd->emb, qv, qdim);
        if (c <= 0.0) continue;
@@ -9178,6 +9312,26 @@ el_val_t engram_load(el_val_t path) {
        }
    }
    g->adj_dirty = 1;
+    if (getenv("EG_DIAG")) {
+        int64_t we = 0, wrongdim = 0;
+        for (int64_t i = 0; i < g->node_count; i++) {
+            if (g->nodes[i].emb) { we++; if (g->nodes[i].emb_dim != 768) wrongdim++; }
+        }
+        fprintf(stderr, "[EG_DIAG] loaded nodes=%lld with_emb=%lld wrongdim=%lld\n",
+                (long long)g->node_count, (long long)we, (long long)wrongdim);
+        const char* probe = getenv("EG_DIAG_ID");
+        if (probe) {
+            for (int64_t i = 0; i < g->node_count; i++) {
+                if (g->nodes[i].id && strcmp(g->nodes[i].id, probe) == 0) {
+                    fprintf(stderr, "[EG_DIAG] probe id=%s idx=%lld emb=%p dim=%d layer=%u addr=%d\n",
+                            probe, (long long)i, (void*)g->nodes[i].emb,
+                            (int)g->nodes[i].emb_dim, g->nodes[i].layer_id,
+                            eg_node_addressable(&g->nodes[i]));
+                }
+            }
+        }
+        fflush(stderr);
+    }
    /* Walk edges array */
    const char* edges_p = json_find_key(data, "edges");
    if (edges_p) {
@@ -9498,7 +9652,33 @@ el_val_t engram_get_node_by_label(el_val_t label) {
    return el_wrap_str(el_strdup("{}"));
 }

-el_val_t engram_search_json(el_val_t query, el_val_t limit) {
+/* ── THE SEARCH / RECALL BOUNDARY (2026-08-07) ───────────────────────────────
+ * engram_search_json is the LEXICAL function ~40 .el call sites already
+ * depend on: they pass a key-shaped string ("soul:boot_count",
+ * "soul-inbox-pending", a session label) and treat every returned record as
+ * a record that CONTAINS that key. Seven of those sites then delete what
+ * comes back (memory.el:176, sessions.el:250/268/444/523, soul.el:359 —
+ * "prune all existing X nodes, keep exactly one").
+ *
+ * The semantic and associative legs must therefore NOT live on this
+ * function. Claim 24 authorises the vector index "to respond to EMBEDDING
+ * SEARCH QUERIES by returning the node records whose embedding vectors have
+ * the highest cosine similarity to a query vector"; a keyed state read is
+ * not an embedding search query, it is the identifier-keyed retrieval of
+ * claim 23 ("node records are stored under a key encoding the node
+ * identifier"). Putting both behind one function erased that boundary, and
+ * a nearest neighbour of the string "soul:boot_count" is not a boot counter.
+ *
+ * MEASURED, on the harness corpus, isolated, read-only, no writes from any
+ * caller: 240 node records destroyed per boot, including 6 Knowledge nodes,
+ * a layer-1 "CORE IDENTITY — GENESIS, LINEAGE" Memory, and the value node
+ * `kn-58874a74` (gold answer for gold-set q15). The deletion list is the
+ * result list of the soul's own mem_boot_count_inc() lookup, in order.
+ *
+ * So: legs OFF here, legs ON in engram_recall_json below, which is what
+ * /api/neuron/recall reaches. Retrieval quality on the recall route is
+ * unchanged; the internal keyed reads get their contract back. */
+static el_val_t eg_search_json_impl(el_val_t query, el_val_t limit, int with_legs) {
    EngramStore* g = engram_get();
    const char* q = EL_CSTR(query);
    int64_t lim = (int64_t)limit;
@@ -9520,28 +9700,136 @@ el_val_t engram_search_json(el_val_t query, el_val_t limit) {
                 * so the semantic half of the retrieval surface has to land HERE
                 * to be observable to the MCP wrapper and the app. */
                int32_t qdim = 0;
-                float*  qv   = eg_embed_fetch(q, &qdim);
+                float*  qv   = with_legs ? eg_embed_fetch(q, &qdim) : NULL;
                EngramSemEntry* sem = qv ? malloc((size_t)g->node_count * sizeof(EngramSemEntry)) : NULL;
                int64_t nsem = 0;
                int64_t nhits = 0;
+                /* Raw (unfloored) cosine top-K, kept for the graph leg's
+                 * semantic seeds. Selected in THIS pass so the cosine is
+                 * computed exactly once per node — the seeding costs no extra
+                 * pass over the corpus and no extra embed round-trip. */
+                int64_t semseed[ENGRAM_EMBED_SEED_K];
+                double  semseedc[ENGRAM_EMBED_SEED_K];
+                int64_t nsemseed = 0;
+                /* BM25 statistics gathered in this same pass: per-token
+                 * document frequency, and the corpus mean field length. */
+                int64_t df[ENGRAM_MAX_QTOKENS];
+                for (int t = 0; t < ntok; t++) df[t] = 0;
+                double  dl_total = 0.0;
+                int64_t dl_n     = 0;
                for (int64_t i = 0; i < g->node_count; i++) {
                    EngramNode* n = &g->nodes[i];
                    /* Filter transparent layers — same as engram_search. */
                    if (engram_layer_is_transparent(n->layer_id)) continue;
-                    int sc = engram_node_match_score(n, toks, ntok);
-                    if (sc > 0) {
+                    /* Unaddressable records cannot be fetched by a caller and
+                     * must not consume a result slot (claims 12/23/27). */
+                    if (!eg_node_addressable(n)) continue;
+                    double dl = engram_node_len(n);
+                    dl_total += dl; dl_n++;
+                    uint32_t mask = engram_node_match_mask(n, toks, ntok);
+                    if (mask) {
+                        int sc = 0;
+                        for (int t = 0; t < ntok; t++)
+                            if (mask & ((uint32_t)1u << t)) { sc++; df[t]++; }
                        hits[nhits].idx      = i;
                        hits[nhits].score    = sc;
                        hits[nhits].salience = n->salience;
+                        hits[nhits].mask     = mask;
+                        hits[nhits].len      = dl;
+                        hits[nhits].w        = 0.0;
                        nhits++;
                    }
-                    if (sem) {
-                        double sv = eg_sem_term(n, qv, qdim);
-                        if (sv > 0.0) { sem[nsem].idx = i; sem[nsem].sem = sv; nsem++; }
+                    if (sem && n->emb && n->emb_dim == qdim) {
+                        double c = eg_cosine(n->emb, qv, qdim);
+                        /* Claim-24 semantic leg, restored verbatim: "returning
+                         * the node records whose embedding vectors have the
+                         * HIGHEST COSINE SIMILARITY to a query vector" — a
+                         * ranking, with no threshold anywhere in the claim.
+                         * ENGRAM_EMBED_SEED_MIN is defined at l.6094 as the
+                         * HippoRAG SEED-JOIN threshold; using it as a RESULT
+                         * filter here was never authorised, and it is a
+                         * per-query lottery rather than a quality gate: the
+                         * query's own top-1 cosine ranges 0.56-0.68 across the
+                         * held-out gold set, so 0.60 keeps a rank-1 answer for
+                         * one query and discards a rank-1 answer for the next.
+                         * Measured on the 30 held-out paraphrases: six golds
+                         * sit at global cosine rank 1-2 and score 0.564-0.589,
+                         * discarded by nothing but this constant.
+                         * What holds the nonsense controls is NOT this floor
+                         * but the corpus-vocabulary gate below (nhits == 0):
+                         * gibberish has no lexical seeds, so no leg reports.
+                         * Cosine is clamped to [0,1] per 05-detailed-description
+                         * l.69 ("clamped to [0,1] to prevent anti-correlated
+                         * embeddings from producing negative activation"). */
+                        double sv = c < 0.0 ? 0.0 : (c > 1.0 ? 1.0 : c);
+                        if (sv > 0.0) {
+                            sem[nsem].idx = i; sem[nsem].sem = sv; nsem++;
+                        }
+                        /* Graph seeds: top-K by RAW cosine, insertion-ordered. */
+                        if (c > 0.0 && (nsemseed < ENGRAM_EMBED_SEED_K
+                                        || c > semseedc[nsemseed - 1])) {
+                            int64_t p = nsemseed < ENGRAM_EMBED_SEED_K
+                                        ? nsemseed : ENGRAM_EMBED_SEED_K - 1;
+                            while (p > 0 && semseedc[p - 1] < c) {
+                                semseedc[p] = semseedc[p - 1];
+                                semseed[p]  = semseed[p - 1];
+                                p--;
+                            }
+                            semseedc[p] = c; semseed[p] = i;
+                            if (nsemseed < ENGRAM_EMBED_SEED_K) nsemseed++;
+                        }
                    }
                }
-                qsort(hits, (size_t)nhits, sizeof(EngramRankEntry), engram_rank_cmp);
+                /* BM25-shaped lexical score. Binary term frequency (the match
+                 * primitive is a substring test, not a count), Lucene-form IDF,
+                 * and length normalisation over the corpus mean. A token that
+                 * occurs in 30,000 nodes now weighs far less than one that
+                 * occurs in 1, and a 1.3 MB record no longer out-matches a
+                 * 300-byte one by sheer surface area. */
+                double avgdl = dl_n ? (dl_total / (double)dl_n) : 1.0;
+                if (avgdl <= 0.0) avgdl = 1.0;
+                double idf[ENGRAM_MAX_QTOKENS];
+                for (int t = 0; t < ntok; t++) {
+                    double dfx = (double)df[t];
+                    idf[t] = log(1.0 + ((double)dl_n - dfx + 0.5) / (dfx + 0.5));
+                }
+                for (int64_t h = 0; h < nhits; h++) {
+                    double norm = 1.0 - ENGRAM_BM25_B
+                                + ENGRAM_BM25_B * (hits[h].len / avgdl);
+                    double s = 0.0;
+                    for (int t = 0; t < ntok; t++)
+                        if (hits[h].mask & ((uint32_t)1u << t))
+                            s += idf[t] * (ENGRAM_BM25_K1 + 1.0)
+                               / (1.0 + ENGRAM_BM25_K1 * norm);
+                    hits[h].w = s;
+                }
+                qsort(hits, (size_t)nhits, sizeof(EngramRankEntry), engram_rank_w_cmp);
                if (sem) qsort(sem, (size_t)nsem, sizeof(EngramSemEntry), engram_sem_cmp);
+                if (getenv("EG_DIAG")) {
+                    int64_t we = 0, unaddr = 0, found = 0;
+                    const char* pid = getenv("EG_DIAG_ID");
+                    for (int64_t i = 0; i < g->node_count; i++) {
+                        if (g->nodes[i].emb) we++;
+                        if (!eg_node_addressable(&g->nodes[i])) unaddr++;
+                        if (pid && g->nodes[i].id && strcmp(g->nodes[i].id, pid) == 0) found++;
+                    }
+                    fprintf(stderr, "[EG_DIAG] STORE node_count=%lld with_emb=%lld unaddressable=%lld probe_found=%lld\n",
+                            (long long)g->node_count, (long long)we, (long long)unaddr, (long long)found);
+                    fprintf(stderr, "[EG_DIAG] q=\"%s\" qdim=%d nhits=%lld nsem=%lld\n",
+                            q, (int)qdim, (long long)nhits, (long long)nsem);
+                    for (int64_t k = 0; k < 5 && k < nsem; k++)
+                        fprintf(stderr, "[EG_DIAG]   sem[%lld] cos=%.4f id=%s\n",
+                                (long long)k, sem[k].sem, g->nodes[sem[k].idx].id);
+                    const char* probe = getenv("EG_DIAG_ID");
+                    if (probe) for (int64_t k = 0; k < nsem; k++)
+                        if (g->nodes[sem[k].idx].id
+                            && strcmp(g->nodes[sem[k].idx].id, probe) == 0) {
+                            fprintf(stderr, "[EG_DIAG]   probe at sem rank %lld cos=%.4f\n",
+                                    (long long)k, sem[k].sem);
+                            break;
+                        }
+                    fflush(stderr);
+                }
                /* Claim-10 associative leg: expand the top lexical hits along
                 * structural relations only, order the reached set by query
                 * similarity. Empty whenever the seeds have no structural
@@ -9549,9 +9837,22 @@ el_val_t engram_search_json(el_val_t query, el_val_t limit) {
                 * lexical ordering safe. */
                EngramSemEntry* assoc = qv ? malloc((size_t)ENGRAM_ASSOC_MAX * sizeof(EngramSemEntry)) : NULL;
                int64_t nassoc = assoc
-                    ? engram_assoc_leg(g, hits, nhits, qv, qdim, assoc, ENGRAM_ASSOC_MAX)
+                    ? engram_assoc_leg(g, hits, nhits, semseed, nsemseed,
+                                       qv, qdim, assoc, ENGRAM_ASSOC_MAX)
                    : 0;
-                int64_t* order = malloc((size_t)lim * sizeof(int64_t));
+                /* Corpus-vocabulary gate. If no stored record contains ANY
+                 * query token in its content, label or tags, the query is
+                 * outside this graph's vocabulary: there are no seeds, and
+                 * 05-detailed-description l.64 makes retrieval downstream of
+                 * seeds ("the caller provides one or more seed node UUIDs
+                 * representing the current active context"). No seeds, no
+                 * retrieval — the graph declines rather than confabulating a
+                 * nearest neighbour for gibberish. The mechanism is iteration
+                 * 6's (feat/claim24-unfloored-semantic); it is required here
+                 * because word-start matching empties the lexical leg for
+                 * q35-style queries whose only "hits" were mid-word, and the
+                 * semantic leg would otherwise answer them anyway. */
+                int64_t* order = (nhits > 0) ? malloc((size_t)lim * sizeof(int64_t)) : NULL;
                if (order) {
                    int64_t no = engram_interleave3(hits, nhits, sem, nsem,
                                                    assoc, nassoc, lim, order);
@@ -9573,6 +9874,19 @@ el_val_t engram_search_json(el_val_t query, el_val_t limit) {
    return el_wrap_str(b.buf);
 }

+/* Lexical keyed read — the historical contract every internal caller relies
+ * on. Every returned record CONTAINS a query token. */
+el_val_t engram_search_json(el_val_t query, el_val_t limit) {
+    return eg_search_json_impl(query, limit, 0);
+}
+
+/* The retrieval surface: lexical + claim-24 semantic + claim-10 associative,
+ * rank-fused. Reached from handle_api_recall (/api/neuron/recall) — the route
+ * the MCP wrapper and the app call, and the one the eval harness measures. */
+el_val_t engram_recall_json(el_val_t query, el_val_t limit) {
+    return eg_search_json_impl(query, limit, 1);
+}
+
 el_val_t engram_scan_nodes_json(el_val_t limit, el_val_t offset) {
    EngramStore* g = engram_get();
    int64_t lim = (int64_t)limit; if (lim <= 0) lim = 100;
@@ -612,6 +612,7 @@ el_val_t  engram_load(el_val_t path);
 el_val_t  engram_get_node_json(el_val_t id);
 el_val_t  engram_get_node_by_label(el_val_t label);
 el_val_t  engram_search_json(el_val_t query, el_val_t limit);
+el_val_t  engram_recall_json(el_val_t query, el_val_t limit);
 el_val_t  engram_scan_nodes_json(el_val_t limit, el_val_t offset);
 el_val_t  engram_scan_nodes_by_type_json(el_val_t node_type, el_val_t limit, el_val_t offset);
 el_val_t  engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t direction);
Author	SHA1	Message	Date
Tim Lingo	b9ef66cae9	fix(engram): the semantic leg was deleting 234 memory records per boot The accumulated retrieval stack (iterations 1-9) put the claim-24 semantic leg and the claim-10 associative leg on engram_search_json — the function ~40 internal .el call sites already used as a KEYED read. Seven of those sites delete every record that comes back ("prune all existing X nodes, keep exactly one"): memory.el:176, sessions.el:250/268/444/523, soul.el:359. mem_boot_count_inc() calls engram_search_json("soul:boot_count", 50) and engram_forget()s all 50 results. With a lexical leg that returned 1 record. With a semantic leg it returns 50 — the 49 nearest neighbours of the STRING "soul:boot_count" — and the soul deletes them. MEASURED on the harness corpus, isolated, read-only, zero writes from any caller: 234 node records destroyed in a single boot. The deletion list is the soul's own lookup result list, in rank order. Casualties include 6 Knowledge nodes, a layer-1 "CORE IDENTITY - GENESIS, LINEAGE" Memory, the value node kn-58874a74, and the gold answers to 8 of the 75 gold-set queries. After the fix: 1 deletion, which is the one the code intends. THE BOUNDARY, from Will. Claim 24 authorises the vector index "to respond to EMBEDDING SEARCH QUERIES by returning the node records whose embedding vectors have the highest cosine similarity to a query vector". A keyed state read is not an embedding search query; it is the identifier-keyed retrieval of claim 23 ("node records are stored under a key encoding the node identifier"). One function served both, so a nearest neighbour of "soul:boot_count" was treated as a boot counter. So: engram_search_json returns to its lexical contract, and the legs move to engram_recall_json, which is what /api/neuron/recall reaches — the route the MCP wrapper, the app, and this harness all call. Retrieval quality on that route is unchanged by construction. MEASURED, 75-query extended gold set, embedded corpus, vs the iteration-9 baseline: +3 / -0 (q15, q28, q60), p=0.2500, hit@5 53.8 -> 58.5%, latency 1.02x, every regression guard held, nonsense 10/10. Net +3 against a floor of 6 is NOT-SHOWN and I am not calling it an improvement. The deliverable is the defect. Diagnostics kept, env-gated (EG_DIAG / EG_DIAG_ID), zero cost when unset: node/embedding census at load, per-query leg dump, and a FORGET log — the last is the regression detector for exactly this class of bug. LIMIT, stated: handle_api_search_knowledge still uses the lexical function. It is a retrieval surface and arguably wants the legs, but nothing in this harness measures it, so I did not change unmeasured behaviour.	2026-08-07 18:12:43 -05:00
Tim Lingo	9717a4eeaf	measure: claim 24 unflooring is +4 (NOT-SHOWN); asymmetric embedding prefixes are -5 (discarded) Measured on the 75-query extended gold set (iteration 8's held-out extension) against the certified stack baseline results-stack-ext.json, on the embedded corpus. Three runs of the candidate, zero drift. A. CLAIM 24 WITHOUT THE THRESHOLD - net +4, NOT-SHOWN, kept in the tree. fixed : q14, q25 (in-sample paraphrase), q43, q52, q63, q67 (held-out) broken : q15 (paraphrase), q28 (associative) 8 discordant, McNemar exact p = 0.2891, floor is 6. heldout_paraphrase 16.7% -> 30.0%, paraphrase 61.5% -> 69.2%. Every regression guard held: exact_rare 6/6, phrase 7/7, nonsense 10/10, superseded 2/3. Latency FLAT: p50 641 -> 632 ms. The in-sample half (+q14 +q25 -q15 -q28 = 0) was already on record in iteration 7's cmp-nogate.json, so only the held-out +4 is new. B. ASYMMETRIC TASK PREFIXES ON THE EMBEDDER - net -5, REVERTED in this commit. Rationale was sound and the prediction was wrong, which is why it was worth measuring: nomic-embed-text is an asymmetric retrieval encoder and this file embedded query and document bare on both sides. Prefixing does exactly what the model card implies for the far-away cases - it rescued q42 (gold at GLOBAL COSINE RANK 25,564) and q39 - but it re-ranks the whole space and broke more than it fixed: fixed : q24, q39, q42 broken : q18, q19, q22, q31, q43, q44, q52, q63 heldout_paraphrase 30.0% -> 23.3%, paraphrase 69.2% -> 53.8%. The corpus and the reproducer are kept (embed-corpus-prefixed.py, snapshot-pre-repair-20260806-embedded-prefixed.json) so nobody re-runs it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-07 17:45:05 -05:00
Tim Lingo	9790d9342d	feat(engram): claim 24 without a threshold, and an embedding substrate that knows query from document Two changes to the ONE leg that generalises. Iteration 8 measured that out of sample the semantic leg contributes 100% of the stack's gain and the graph leg contributes nothing, so this is where the remaining headroom is. 1. THE 0.60 FLOOR IS A PER-QUERY LOTTERY, AND CLAIM 24 HAS NO THRESHOLD IN IT. 06-claims.md l.148: "respond to embedding search queries by returning the node records whose embedding vectors have the HIGHEST COSINE SIMILARITY to a query vector, independently of the spreading activation traversal." A ranking. ENGRAM_EMBED_SEED_MIN is defined at el_runtime.c l.6094 as the HippoRAG seed-JOIN threshold and l.6102 admits the read-path leg merely "reuses" it. Measured on the 30 held-out paraphrases: the query's own top-1 cosine ranges 0.564-0.680, so the constant keeps a rank-1 answer for one query and discards a rank-1 answer for the next. Six golds sit at global cosine rank 1-2 scoring 0.564-0.589 - discarded by nothing but the constant. What holds the nonsense controls is the corpus-vocabulary gate (nhits == 0), not this floor. Cosine clamped to [0,1] per 05-detailed-description l.69. 2. THE VECTORS THEMSELVES ANSWER THE WRONG QUESTION. EL_EMBED_MODEL defaults to nomic-embed-text, an ASYMMETRIC retrieval encoder trained with task prefixes. Embedding query and document bare - as this file did on both sides - measures topical similarity rather than answer-hood. eg_embed_fetch now takes the task prefix: EL_EMBED_QUERY_PREFIX on the three query call sites, EL_EMBED_DOC_PREFIX on the two backfill sites. Restores no claim, and says so: Will specifies only "computed by an embedding model over the node's content" (l.17), so the model is his and its correct use is ours. It is the substrate under claim 24 - the index is only as good as the vectors in it. Reproducer for the derived corpus: tools/retrieval-eval/embed-corpus-prefixed.py. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-07 17:34:58 -05:00
Tim Lingo	4eb4c9e287	feat(engram): word-start match primitive + corpus-vocabulary gate on recall The retrieval match test is a raw substring scan, so a query token matches anywhere INSIDE a corpus word: "throom" matches "bathroom". Measured over the 38-query gold set on this corpus that is not a rare accident - q28's lexical leg is 36,954 records of which only 13 contain a query token at a word start (99.96% mid-word noise), six further queries carry ~20,500 mid-word-only records each, and the nonsense control q35 returns 7 records ALL of which match only mid-word. istr_contains_wordstart() anchors a token to a word start (preceding char not alphanumeric) while still matching suffixes, so "value" still hits "values". That empties the lexical leg for gibberish, and the nhits==0 corpus-vocabulary gate (iteration 6's mechanism, feat/claim24-unfloored-semantic) then makes the whole query decline rather than let the semantic leg answer it. Measured vs feat/bm25-lexical-leg on the embedded corpus, 2 runs each, 0 queries of run-to-run drift on both sides: net +1 (nonsense:q35), 0 losses, McNemar p=1.0 -> NOT-SHOWN (floor is 6) nonsense clean 2/3 -> 3/3; exact_rare 100%, phrase 100%, paraphrase 61.5%, associative 66.7%, superseded 2/3 all UNCHANGED latency p50 1184 -> 543 ms (0.46x) Iteration 6 called q35 "a DEFECTIVE CONTROL ... cannot be cleaned without breaking the lexical leg". It can: the defect was the match primitive, and cleaning it cost nothing. Also committed: results-wsclaim24.json + cmp-nogate.json, a measured negative for bundling the claim-24 unfloored semantic leg on top (gains q14/q25, breaks q15/q28/q33/q34, net -2) - it independently reproduces iteration 6's q15/q28 losses and shows unflooring REQUIRES the vocabulary gate. Reproducers: legs.py (leg-level replica, reproduces baseline hit@5 exactly on all 38 queries), policy2.py, ceiling.py, wb2.py.	2026-08-07 16:58:34 -05:00
Tim Lingo	55f9ee3cb0	measure: BM25 lexical leg vs semseed baseline - net +2 (q10,q11), NOT-SHOWN hit@5 68.6% -> 74.3%, phrase 71.4% -> 100%, MRR@10 0.461 -> 0.502, latency p50 0.97x. Zero losses, zero run-to-run drift on both sides. 2 queries moved against a 6-query noise floor: NO MEASURABLE DIFFERENCE by the harness's own test (McNemar exact p=0.50). Unaddressable records in returned slots: 57 -> 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-07 15:55:42 -05:00
Tim Lingo	9c39084e60	feat(engram): BM25-shaped lexical leg + addressability guard on the read path engram_search_json ranked its lexical leg by raw distinct-token coverage with salience as tiebreak: a token in 30,000 nodes counted the same as a token in 1, and a 1.3 MB record matched nearly every query token by surface area alone. Score it BM25-shaped instead - Lucene-form IDF and length normalisation over the corpus mean - with per-token document frequency accumulated in the SAME corpus pass that finds the hits (no extra scan, no extra round-trip). Also refuse to return records whose identifier is not printable ASCII. This corpus carries 1,032 such records (453 by the printable test) from a save-side corruption; they occupy 125 of 303 returned slots on main. Claims 12, 23 and 27 all key on the node identifier, so such a record is unfetchable by any caller. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-07 15:51:49 -05:00
Tim Lingo	6f3a048f36	feat(engram): semantically seed the graph leg (Will's HippoRAG pass, SEED_K=8) engram_assoc_leg previously took its seeds only from the top-3 LEXICAL hits. For a paraphrase query the lexical hits are noise by construction, so the walk never reached the neighbourhood that holds the answer. This adds the seeding pass Will documents at el_runtime.c l.6082 — "Semantic seeding (HippoRAG pattern, use similarity twice): the query is embedded, the top-K nodes by cosine join the seed set" — using his own ENGRAM_EMBED_SEED_K (8). Similarity is now used twice, coherently: cosine picks where to STAND in the graph, the structural-relation walk decides what is REACHABLE, and cosine orders what was reached (iteration 2's finding, unchanged). The seed list is deliberately NOT floored at ENGRAM_EMBED_SEED_MIN. Measured over all 38 gold queries: true paraphrase targets score cosine 0.46-0.66 and the three nonsense controls' own nearest neighbours score 0.55/0.60/0.62 — the distributions OVERLAP, so no absolute cosine floor separates signal from gibberish. The gate that works is reachability: gibberish's nearest neighbours carry no structural edge, so its graph leg is empty and the controls hold. The raw top-K is selected inside the existing scoring pass, so the cosine is computed exactly once per node: no extra corpus pass, no extra embed round-trip, latency flat (p50 1220 -> 1227 ms, 1.01x). Measured vs the certified baseline feat/hybrid-semantic-recall, embedded corpus, 2 runs each, zero run-to-run drift on both sides: hit@5 51.4% -> 68.6% MRR@10 0.387 -> 0.461 paraphrase 38.5% -> 61.5% associative 0% -> 66.7% exact_rare 100% held, nonsense 2/3 held, superseded 2/3 held phrase 85.7% -> 71.4% (q11, the known rank-5 rotation tax) net +6 queries (7 fixed / 1 broken), McNemar p=0.0703	2026-08-07 15:35:08 -05:00