feat(engram): Will's Layer-2 executive filter (claims 44/45) on the recall read path

Claim 44 requires a second pass that computes a working memory weight
(background activation x goal-state attentional bias x confidence) and
promotes only what clears a per-type threshold; claim 45 keeps the
un-promoted field retained rather than discarded. That pass exists in
engram_activate and nowhere on the route /api/neuron/recall reaches.

engram_search_json now splits each of its three legs into promoted and
suppressed sublists and rotates the promoted material into the head of
the result, background-only behind it (05-detailed-description l.221:
'promoted nodes first ... followed by background-only nodes').

MEASURED: net +0 queries vs its parent feat/bm25-lexical-leg on the
38-query gold set. NOT-SHOWN. hit@5 74.3% both sides; recall@10
61.8 -> 63.2%, MRR@10 0.502 -> 0.524, latency p50 1184 -> 1198ms.

The first cut (results-execfilter.json, kept as evidence) fed pass 2 the
semantic leg's shift-and-floor value instead of raw cosine and lost 6
queries (paraphrase 61.5 -> 23.1%, p=0.0312).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

neuron-api.el

@@ -450,12 +450,7 @@ 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))
     }
-    // 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)
+    let results: String = engram_search_json(eff_q, limit)
     return api_or_empty(results)
 }
 

tools/retrieval-eval/ceiling.py

@@ -1,43 +0,0 @@
-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))

tools/retrieval-eval/cmp-bm25-vs-execfilter.json

@@ -1,24 +1,23 @@
 {
  "baseline": "bm25lex",
- "candidate": "wsclaim24",
+ "candidate": "execfilter",
  "n_shared_queries": 38,
- "fixed_by_candidate": [
-  "q14",
-  "q25"
- ],
+ "fixed_by_candidate": [],
  "broken_by_candidate": [
   "q15",
-  "q28",
-  "q33",
-  "q34"
+  "q16",
+  "q20",
+  "q21",
+  "q26",
+  "q37"
  ],
  "discordant": 6,
- "net_queries": -2,
- "mcnemar_exact_p": 0.6875,
+ "net_queries": -6,
+ "mcnemar_exact_p": 0.03125,
  "min_detectable_swing_queries": 6,
  "observed_run_to_run_drift_queries": 0,
  "noise_floor_queries": 6,
- "verdict": "no measurable difference",
+ "verdict": "candidate worse",
  "baseline_aggregate": {
   "n_queries": 38,
   "n_scored": 35,
@@ -80,24 +79,24 @@
  "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,
+  "hit@5": 0.6,
+  "recall@5": 0.41518699554413835,
+  "recall@10": 0.4869109065537637,
+  "precision@5": 0.18285714285714288,
+  "mrr@10": 0.4493197278911565,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "1/3",
+  "latency_ms_p50": 1183.3,
+  "latency_ms_p95": 1637.5,
+  "latency_ms_max": 1672.5,
   "errors": 0,
   "by_category": {
    "associative": {
     "n": 6,
-    "hit@5": 0.5,
-    "recall@5": 0.07575757575757576,
-    "recall@10": 0.13636363636363635,
-    "mrr@10": 0.23214285714285712
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.11421911421911422,
+    "recall@10": 0.3146853146853147,
+    "mrr@10": 0.2916666666666667
    },
    "exact_rare": {
     "n": 6,
@@ -108,39 +107,32 @@
    },
    "nonsense": {
     "n": 3,
-    "clean": 0,
-    "avg_false_positives": 10.0
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
    },
    "paraphrase": {
     "n": 13,
-    "hit@5": 0.6923076923076923,
-    "recall@5": 0.6923076923076923,
-    "recall@10": 0.7692307692307693,
-    "mrr@10": 0.29423076923076924
+    "hit@5": 0.23076923076923078,
+    "recall@5": 0.23076923076923078,
+    "recall@10": 0.3076923076923077,
+    "mrr@10": 0.12637362637362637
    },
    "phrase": {
     "n": 7,
     "hit@5": 1.0,
-    "recall@5": 0.5335884353741497,
+    "recall@5": 0.5494614512471656,
     "recall@10": 0.5933956916099773,
-    "mrr@10": 0.8214285714285714
+    "mrr@10": 0.8333333333333334
    },
    "superseded": {
     "n": 3,
     "hit@5": 0.3333333333333333,
     "recall@5": 0.3333333333333333,
-    "recall@10": 0.6666666666666666,
-    "mrr@10": 0.20833333333333334,
-    "outranks": 2
+    "recall@10": 0.3333333333333333,
+    "mrr@10": 0.16666666666666666,
+    "outranks": 1
    }
   }
  },
- "repeat_variance": {
-  "baseline": {
-   "runs": 2,
-   "hit@5_min": 0.7428571428571429,
-   "hit@5_max": 0.7428571428571429,
-   "spread_queries": 0
-  }
- }
+ "repeat_variance": {}
 }

tools/retrieval-eval/cmp-bm25-vs-execfilter2.json

@@ -1,13 +1,11 @@
 {
  "baseline": "bm25lex",
- "candidate": "wordstart",
+ "candidate": "execfilter2",
  "n_shared_queries": 38,
- "fixed_by_candidate": [
-  "q35"
- ],
+ "fixed_by_candidate": [],
  "broken_by_candidate": [],
- "discordant": 1,
- "net_queries": 1,
+ "discordant": 0,
+ "net_queries": 0,
  "mcnemar_exact_p": 1.0,
  "min_detectable_swing_queries": 6,
  "observed_run_to_run_drift_queries": 0,
@@ -75,23 +73,23 @@
   "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",
+  "recall@5": 0.5580441384012813,
+  "recall@10": 0.631553763696621,
+  "precision@5": 0.2114285714285715,
+  "mrr@10": 0.5235714285714286,
+  "nonsense_clean": "2/3",
   "superseded_outranks": "2/3",
-  "latency_ms_p50": 542.6,
-  "latency_ms_p95": 741.3,
-  "latency_ms_max": 758.8,
+  "latency_ms_p50": 1198.3,
+  "latency_ms_p95": 1632.6,
+  "latency_ms_max": 1664.0,
   "errors": 0,
   "by_category": {
    "associative": {
     "n": 6,
     "hit@5": 0.6666666666666666,
-    "recall@5": 0.08857808857808858,
-    "recall@10": 0.23310023310023312,
-    "mrr@10": 0.25
+    "recall@5": 0.11421911421911422,
+    "recall@10": 0.3146853146853147,
+    "mrr@10": 0.2916666666666667
    },
    "exact_rare": {
     "n": 6,
@@ -102,15 +100,15 @@
    },
    "nonsense": {
     "n": 3,
-    "clean": 3,
-    "avg_false_positives": 0.0
+    "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
+    "mrr@10": 0.3230769230769231
    },
    "phrase": {
     "n": 7,
@@ -129,18 +127,5 @@
    }
   }
  },
- "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
-  }
- }
+ "repeat_variance": {}
 }

tools/retrieval-eval/cmp-semseed-vs-execfilter2.json

@@ -0,0 +1,134 @@
+{
+ "baseline": "semseed",
+ "candidate": "execfilter2",
+ "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": 0.5580441384012813,
+  "recall@10": 0.631553763696621,
+  "precision@5": 0.2114285714285715,
+  "mrr@10": 0.5235714285714286,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1198.3,
+  "latency_ms_p95": 1632.6,
+  "latency_ms_max": 1664.0,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.11421911421911422,
+    "recall@10": 0.3146853146853147,
+    "mrr@10": 0.2916666666666667
+   },
+   "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": 0.3230769230769231
+   },
+   "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": {}
+}

tools/retrieval-eval/cmp-splitfix.json

@@ -1,149 +0,0 @@
-{
- "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": {}
-}

tools/retrieval-eval/comparison-main-vs-stack-ext.json

@@ -1,166 +0,0 @@
-{
- "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": {}
-}

tools/retrieval-eval/comparison-stack-vs-unfloor.json

@@ -1,155 +0,0 @@
-{
- "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": {}
-}

tools/retrieval-eval/comparison-unfloor-vs-semsub.json

@@ -1,158 +0,0 @@
-{
- "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": {}
-}

tools/retrieval-eval/embed-corpus-prefixed.py

@@ -1,43 +0,0 @@
-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)

tools/retrieval-eval/extend_gold_set.py

@@ -1,353 +0,0 @@
-#!/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()

tools/retrieval-eval/legs.py

@@ -1,117 +0,0 @@
-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

tools/retrieval-eval/policy2.py

@@ -1,102 +0,0 @@
-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))

tools/retrieval-eval/results-execfilter.json

@@ -1,37 +1,37 @@
 {
- "label": "wordstart-r2",
- "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-wordstart",
- "soul_md5": "32d4cf77672658a5f49dc7c9213e3ba2",
+ "label": "execfilter",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-execfilter",
+ "soul_md5": "1b2dbc92a1b96327c54b7fbd8d448336",
  "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",
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-bm25lex/tools/retrieval-eval/gold_set.json",
  "limit": 10,
- "port": 7895,
- "wall_clock_s": 28.7,
- "child_pid": 1490,
+ "port": 7931,
+ "wall_clock_s": 50.5,
+ "child_pid": 91170,
  "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,
+  "hit@5": 0.6,
+  "recall@5": 0.41518699554413835,
+  "recall@10": 0.4869109065537637,
+  "precision@5": 0.18285714285714288,
+  "mrr@10": 0.4493197278911565,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "1/3",
+  "latency_ms_p50": 1183.3,
+  "latency_ms_p95": 1637.5,
+  "latency_ms_max": 1672.5,
   "errors": 0,
   "by_category": {
    "associative": {
     "n": 6,
     "hit@5": 0.6666666666666666,
-    "recall@5": 0.08857808857808858,
-    "recall@10": 0.23310023310023312,
-    "mrr@10": 0.25
+    "recall@5": 0.11421911421911422,
+    "recall@10": 0.3146853146853147,
+    "mrr@10": 0.2916666666666667
    },
    "exact_rare": {
     "n": 6,
@@ -42,30 +42,30 @@
    },
    "nonsense": {
     "n": 3,
-    "clean": 3,
-    "avg_false_positives": 0.0
+    "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
+    "hit@5": 0.23076923076923078,
+    "recall@5": 0.23076923076923078,
+    "recall@10": 0.3076923076923077,
+    "mrr@10": 0.12637362637362637
    },
    "phrase": {
     "n": 7,
     "hit@5": 1.0,
     "recall@5": 0.5494614512471656,
-    "recall@10": 0.6023242630385487,
-    "mrr@10": 0.8214285714285714
+    "recall@10": 0.5933956916099773,
+    "mrr@10": 0.8333333333333334
    },
    "superseded": {
     "n": 3,
     "hit@5": 0.3333333333333333,
     "recall@5": 0.3333333333333333,
-    "recall@10": 0.6666666666666666,
-    "mrr@10": 0.20833333333333334,
-    "outranks": 2
+    "recall@10": 0.3333333333333333,
+    "mrr@10": 0.16666666666666666,
+    "outranks": 1
    }
   }
  },
@@ -78,7 +78,7 @@
     "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
    ],
    "n_returned": 1,
-   "latency_ms": 165.0,
+   "latency_ms": 284.0,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -93,17 +93,17 @@
    "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"
+    "ctx-74ed",
+    "ctx-fae1",
+    "kn-efeb4a5b-5aff-4759-8a97-7233099be6ee",
+    "ctx-6677",
+    "imp-dce1da0f-8776-4a9e-972b-33411a7ca138"
    ],
    "n_returned": 10,
-   "latency_ms": 164.5,
+   "latency_ms": 320.7,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -119,7 +119,7 @@
     "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
    ],
    "n_returned": 1,
-   "latency_ms": 163.7,
+   "latency_ms": 293.6,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -135,7 +135,7 @@
     "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
    ],
    "n_returned": 1,
-   "latency_ms": 172.2,
+   "latency_ms": 288.0,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -153,7 +153,7 @@
     "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,
+   "latency_ms": 318.6,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -169,7 +169,7 @@
     "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
    ],
    "n_returned": 1,
-   "latency_ms": 164.6,
+   "latency_ms": 282.7,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -194,7 +194,7 @@
     "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
    ],
    "n_returned": 10,
-   "latency_ms": 281.9,
+   "latency_ms": 592.5,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -208,7 +208,6 @@
    "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",
@@ -216,14 +215,15 @@
     "knw-ed33e669-0790-44cb-a036-958d605c6fea",
     "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
     "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
-    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8"
    ],
    "n_returned": 10,
-   "latency_ms": 254.8,
+   "latency_ms": 513.6,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.1875,
-   "recall@10": 0.375,
+   "recall@10": 0.3125,
    "precision@5": 0.6,
    "mrr@10": 1.0
   },
@@ -244,7 +244,7 @@
     "kn-f230b362-b201-4402-9833-4160c89ab3d4"
    ],
    "n_returned": 10,
-   "latency_ms": 255.5,
+   "latency_ms": 516.8,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.3333333333333333,
@@ -258,24 +258,24 @@
    "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"
+    "bl-18a9d1e4-1484-474c-bf6b-c6173212181b",
+    "project-harmonic-framework",
+    "project-harmonic-framework_com"
    ],
    "n_returned": 10,
-   "latency_ms": 247.7,
+   "latency_ms": 505.1,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.1111111111111111,
    "recall@10": 0.1111111111111111,
    "precision@5": 0.2,
-   "mrr@10": 0.25
+   "mrr@10": 0.3333333333333333
   },
   {
    "id": "q11",
@@ -294,7 +294,7 @@
     "kn-6061318f-046b-4935-907d-8eafdce14930"
    ],
    "n_returned": 10,
-   "latency_ms": 263.4,
+   "latency_ms": 517.0,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -312,14 +312,14 @@
     "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-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
     "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
-    "?Q??m?;?u?'",
+    "2c56a7a9-5323-4ce4-ba09-35836ba15d54",
     "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
    ],
    "n_returned": 10,
-   "latency_ms": 397.9,
+   "latency_ms": 869.6,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.21428571428571427,
@@ -333,18 +333,18 @@
    "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",
     "mem-fb44a2fc-7405-41ff-87b3-84643ac07313",
-    "?",
     "mem-a3c97012-5fa3-4915-a839-2c75c72005e0",
-    "?"
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "mem-ce88adf9-3f3c-47ac-a7d3-83af7b290e68",
+    "bl-e20944e5-f4a6-44a0-91b1-73d04ebed120"
    ],
    "n_returned": 10,
-   "latency_ms": 341.6,
+   "latency_ms": 729.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -361,15 +361,15 @@
     "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-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
     "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
-    "mem-0228da71-d7f7-4f3b-b7b3-c5eede42b62a",
-    "ctx-4a41"
+    "mem-2265c223-9e19-47b5-b7ba-5e9c2ce1f22c",
+    "knw-729fc901-8335-44c4-9f3a-b150b4aa0915"
    ],
    "n_returned": 10,
-   "latency_ms": 761.4,
+   "latency_ms": 1600.2,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -382,50 +382,50 @@
    "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"
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
    ],
    "n_returned": 10,
-   "latency_ms": 733.5,
+   "latency_ms": 1660.3,
    "error": null,
-   "hit@5": 1.0,
-   "recall@5": 1.0,
-   "recall@10": 1.0,
-   "precision@5": 0.2,
-   "mrr@10": 0.5
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
   },
   {
    "id": "q16",
    "category": "paraphrase",
    "query": "choosing an uncomfortable fact over a pleasant fiction",
    "returned": [
-    "tag-fiction",
-    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "mem-ef878e30-5851-4e82-8588-745415108941",
     "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
-    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
     "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
-    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-6fae4d4b-dbe8-45c5-8bd4-21ffd5caa240",
     "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
-    "mem-443bd012-fc9a-4088-b236-de5157a1ef92",
     "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
-    "mem-ca4d6a34-d354-413f-bc86-126cc17ca81c"
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0"
    ],
    "n_returned": 10,
-   "latency_ms": 629.3,
+   "latency_ms": 1348.9,
    "error": null,
-   "hit@5": 1.0,
-   "recall@5": 1.0,
-   "recall@10": 1.0,
-   "precision@5": 0.2,
-   "mrr@10": 0.5
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
   },
   {
    "id": "q17",
@@ -434,17 +434,17 @@
    "returned": [
     "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
     "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
-    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "kn-2b961d24-7fb9-47c7-9515-e45a24dce39d",
     "knw-08559f5c-2306-4220-a146-398c74f1643c",
-    "4da5dbaf-46e5-4f3e-b474-f60d9f8241d3",
+    "kn-0710e5b4-799d-4a0e-afd3-62d43b38ea37",
     "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
-    "mem-434be7c8-88cb-4039-b79a-1da4ac4de783",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
     "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
-    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "kn-c72bb6db-bd1e-4d37-bded-0399194496f6",
     "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
    ],
    "n_returned": 10,
-   "latency_ms": 529.7,
+   "latency_ms": 1069.2,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -459,17 +459,17 @@
    "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"
+    "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": 747.9,
+   "latency_ms": 1411.7,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -482,19 +482,19 @@
    "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-0bb4f021-56de-4947-a35b-a37209e7ba21",
     "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"
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-23c27d3b-e0d2-43a8-a80c-0a44477ae18a"
    ],
    "n_returned": 10,
-   "latency_ms": 564.3,
+   "latency_ms": 1273.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -508,24 +508,24 @@
    "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"
+    "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "mem-23d22bc1-a097-446b-8f11-8aff099e0b76",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8"
    ],
    "n_returned": 10,
-   "latency_ms": 689.0,
+   "latency_ms": 1600.8,
    "error": null,
-   "hit@5": 1.0,
-   "recall@5": 1.0,
-   "recall@10": 1.0,
-   "precision@5": 0.2,
-   "mrr@10": 0.5
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
   },
   {
    "id": "q21",
@@ -533,43 +533,43 @@
    "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"
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995",
+    "mem-8fccaeaa-816c-455d-b40e-b9ffb7c52427",
+    "bl-ac94aab1-60a0-48d6-bfe0-db80a94810b5"
    ],
    "n_returned": 10,
-   "latency_ms": 588.0,
+   "latency_ms": 1389.8,
    "error": null,
-   "hit@5": 1.0,
-   "recall@5": 1.0,
-   "recall@10": 1.0,
-   "precision@5": 0.2,
-   "mrr@10": 0.5
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
   },
   {
    "id": "q22",
    "category": "paraphrase",
    "query": "what shifts tells you where to cut a system apart",
    "returned": [
-    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "5a2c118a-87bd-4239-97a7-9e02c5991983",
     "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
-    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "mem-ef878e30-5851-4e82-8588-745415108941",
     "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
-    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
     "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
-    "34356a36-0df5-4020-8dcc-5e7a423f8d4c",
+    "kn-22d77abe-b3c5-42fd-afcd-dcb87d924929",
     "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
-    "mem-22f5f665-3ad2-4063-88b0-915849a795f5",
+    "kn-ac3fa61f-5689-4fbe-8a42-eae016d524c2",
     "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
    ],
    "n_returned": 10,
-   "latency_ms": 729.0,
+   "latency_ms": 1637.5,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -583,18 +583,18 @@
    "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"
+    "a0edad47-5f77-4fc3-a546-1e85f8c68e77",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "96497334-b18f-495c-9228-eeb8182bdc38",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "d0434bdc-c75d-40ef-a989-bba4fa271a7c",
+    "ctx-4a41"
    ],
    "n_returned": 10,
-   "latency_ms": 638.7,
+   "latency_ms": 1499.3,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -607,19 +607,19 @@
    "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-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-da21c52c-04a5-4f92-8fba-f10aac47e027",
     "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
-    "fce2792a-53fc-4d4a-be3b-42bd6ceb1ba7",
+    "kn-66a21179-2adc-4b19-a109-880cf4674d7d",
     "a1000001-0000-0000-0000-000000000001"
    ],
    "n_returned": 10,
-   "latency_ms": 679.0,
+   "latency_ms": 1542.4,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -638,13 +638,13 @@
     "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
     "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
     "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
-    "mem-a16deccb-16a7-419c-a013-ff824a4daa15",
+    "bl-e98cdd4c-01b5-459e-9036-3578cd5d975a",
     "a1000001-0000-0000-0000-000000000009",
-    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "mem-154c3ec1-061c-4314-9e5f-50dc9b9422bc",
     "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
    ],
    "n_returned": 10,
-   "latency_ms": 588.5,
+   "latency_ms": 1230.5,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -657,25 +657,25 @@
    "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",
+    "bl-3f57bc69-7285-4f4a-a861-2de52efca058",
     "kn-f230b362-b201-4402-9833-4160c89ab3d4",
-    "tag-childhood",
-    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+    "bl-0d8c5dfa-e163-4fef-a58b-56b0d076c5a8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "36fa5506-de96-4964-8666-42bbb5dac336",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40"
    ],
    "n_returned": 10,
-   "latency_ms": 613.6,
+   "latency_ms": 1343.9,
    "error": null,
-   "hit@5": 1.0,
-   "recall@5": 1.0,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
    "recall@10": 1.0,
-   "precision@5": 0.2,
-   "mrr@10": 0.2
+   "precision@5": 0.0,
+   "mrr@10": 0.14285714285714285
   },
   {
    "id": "q27",
@@ -688,17 +688,17 @@
     "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
     "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
     "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
-    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
     "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
-    "efe53612-6914-4936-8e3b-1e694eb174e5",
-    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
    ],
    "n_returned": 10,
-   "latency_ms": 652.1,
+   "latency_ms": 1443.2,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.18181818181818182,
-   "recall@10": 0.45454545454545453,
+   "recall@10": 0.5454545454545454,
    "precision@5": 0.4,
    "mrr@10": 0.5
   },
@@ -708,24 +708,24 @@
    "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",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
     "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"
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83"
    ],
    "n_returned": 10,
-   "latency_ms": 543.3,
+   "latency_ms": 1110.5,
    "error": null,
    "hit@5": 1.0,
-   "recall@5": 0.07692307692307693,
-   "recall@10": 0.3076923076923077,
-   "precision@5": 0.2,
-   "mrr@10": 0.25
+   "recall@5": 0.23076923076923078,
+   "recall@10": 0.6153846153846154,
+   "precision@5": 0.6,
+   "mrr@10": 0.5
   },
   {
    "id": "q29",
@@ -736,19 +736,19 @@
     "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"
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
    ],
    "n_returned": 10,
-   "latency_ms": 537.6,
+   "latency_ms": 1183.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.18181818181818182,
-   "recall@10": 0.45454545454545453,
+   "recall@10": 0.5454545454545454,
    "precision@5": 0.4,
    "mrr@10": 0.5
   },
@@ -764,12 +764,12 @@
     "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"
+    "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc",
+    "015644f5-8194-4af0-800d-dd4a0cd71396"
    ],
    "n_returned": 10,
-   "latency_ms": 538.3,
+   "latency_ms": 1194.6,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -787,14 +787,14 @@
     "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"
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "bl-9773fd67-2ac8-42cd-bea0-702e85f4565e",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4"
    ],
    "n_returned": 10,
-   "latency_ms": 533.9,
+   "latency_ms": 1208.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.09090909090909091,
@@ -808,18 +808,18 @@
    "query": "man of the house six years old expectation",
    "returned": [
     "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
-    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-729fc901-8335-44c4-9f3a-b150b4aa0915",
     "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-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
     "knw-35940684-abc4-42f0-b942-818f66b1f69a",
-    "4f698ae6-c40e-464e-9798-50350991a188",
-    "719aa819-00a9-4f4b-a857-4f9fe5ad44d7",
+    "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": 673.8,
+   "latency_ms": 1432.9,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -833,7 +833,7 @@
    "query": "zqxjvw plimforth grebulon",
    "returned": [],
    "n_returned": 0,
-   "latency_ms": 350.7,
+   "latency_ms": 730.1,
    "error": null,
    "clean": true,
    "false_positives": 0
@@ -844,7 +844,7 @@
    "query": "flarnbistle quommetry",
    "returned": [],
    "n_returned": 0,
-   "latency_ms": 254.6,
+   "latency_ms": 501.9,
    "error": null,
    "clean": true,
    "false_positives": 0
@@ -853,12 +853,23 @@
    "id": "q35",
    "category": "nonsense",
    "query": "xxqzzt vurblenacht throom",
-   "returned": [],
-   "n_returned": 0,
-   "latency_ms": 345.8,
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "8cbb60c5-4999-4ec1-8682-2592aedc4249",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "kn-efeb4a5b-5aff-4759-8a97-7233099be6ee"
+   ],
+   "n_returned": 10,
+   "latency_ms": 738.2,
    "error": null,
-   "clean": true,
-   "false_positives": 0
+   "clean": false,
+   "false_positives": 10
   },
   {
    "id": "q36",
@@ -871,13 +882,13 @@
     "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",
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
     "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
-    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
-    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5"
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72"
    ],
    "n_returned": 10,
-   "latency_ms": 639.5,
+   "latency_ms": 1308.1,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -894,46 +905,18 @@
    "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"
+    "a1000001-0000-0000-0000-000000000002",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "7ac62daa-2eac-4c7a-a97e-e4203fc1b57b",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "2aedba58-a4a3-4d14-b0db-fb59f976803f",
+    "a1000001-0000-0000-0000-000000000003"
    ],
    "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,
+   "latency_ms": 1672.5,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -942,7 +925,35 @@
    "mrr@10": 0.0,
    "outranks": false,
    "rank_correct": null,
-   "rank_stale": 5
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "5fcba804-eb5b-48ec-82da-146b1c6bb50d",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "bl-c5c6571e-118f-47c7-8cbb-3ed0ebf64a51",
+    "ctx-3a55",
+    "86228228-7adf-41fb-b4c4-9ceea87953ae",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5",
+    "ctx-60cc",
+    "e936ea19-b63f-47ac-aee2-95c40451e15d",
+    "ctx-b5e8"
+   ],
+   "n_returned": 10,
+   "latency_ms": 999.3,
+   "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": null
   }
  ]
 }

tools/retrieval-eval/results-execfilter2.json

@@ -1,37 +1,37 @@
 {
- "label": "wordstart",
- "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-wordstart",
- "soul_md5": "32d4cf77672658a5f49dc7c9213e3ba2",
+ "label": "execfilter2",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-execfilter2",
+ "soul_md5": "df2c75b74717fa40de2dd17a5bff46b5",
  "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",
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-bm25lex/tools/retrieval-eval/gold_set.json",
  "limit": 10,
- "port": 7894,
- "wall_clock_s": 28.9,
- "child_pid": 1420,
+ "port": 7932,
+ "wall_clock_s": 50.6,
+ "child_pid": 91409,
  "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",
+  "recall@5": 0.5580441384012813,
+  "recall@10": 0.631553763696621,
+  "precision@5": 0.2114285714285715,
+  "mrr@10": 0.5235714285714286,
+  "nonsense_clean": "2/3",
   "superseded_outranks": "2/3",
-  "latency_ms_p50": 542.6,
-  "latency_ms_p95": 741.3,
-  "latency_ms_max": 758.8,
+  "latency_ms_p50": 1198.3,
+  "latency_ms_p95": 1632.6,
+  "latency_ms_max": 1664.0,
   "errors": 0,
   "by_category": {
    "associative": {
     "n": 6,
     "hit@5": 0.6666666666666666,
-    "recall@5": 0.08857808857808858,
-    "recall@10": 0.23310023310023312,
-    "mrr@10": 0.25
+    "recall@5": 0.11421911421911422,
+    "recall@10": 0.3146853146853147,
+    "mrr@10": 0.2916666666666667
    },
    "exact_rare": {
     "n": 6,
@@ -42,15 +42,15 @@
    },
    "nonsense": {
     "n": 3,
-    "clean": 3,
-    "avg_false_positives": 0.0
+    "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
+    "mrr@10": 0.3230769230769231
    },
    "phrase": {
     "n": 7,
@@ -78,7 +78,7 @@
     "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
    ],
    "n_returned": 1,
-   "latency_ms": 170.4,
+   "latency_ms": 289.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -103,7 +103,7 @@
     "ctx-74ed"
    ],
    "n_returned": 10,
-   "latency_ms": 210.4,
+   "latency_ms": 324.1,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -119,7 +119,7 @@
     "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
    ],
    "n_returned": 1,
-   "latency_ms": 167.1,
+   "latency_ms": 291.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -135,7 +135,7 @@
     "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
    ],
    "n_returned": 1,
-   "latency_ms": 166.9,
+   "latency_ms": 288.4,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -153,7 +153,7 @@
     "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,
+   "latency_ms": 310.4,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -169,7 +169,7 @@
     "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
    ],
    "n_returned": 1,
-   "latency_ms": 162.2,
+   "latency_ms": 307.2,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -194,7 +194,7 @@
     "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
    ],
    "n_returned": 10,
-   "latency_ms": 306.7,
+   "latency_ms": 591.0,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -219,7 +219,7 @@
     "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
    ],
    "n_returned": 10,
-   "latency_ms": 261.2,
+   "latency_ms": 521.1,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.1875,
@@ -244,7 +244,7 @@
     "kn-f230b362-b201-4402-9833-4160c89ab3d4"
    ],
    "n_returned": 10,
-   "latency_ms": 272.9,
+   "latency_ms": 537.7,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.3333333333333333,
@@ -269,7 +269,7 @@
     "bl-18a9d1e4-1484-474c-bf6b-c6173212181b"
    ],
    "n_returned": 10,
-   "latency_ms": 265.5,
+   "latency_ms": 503.2,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.1111111111111111,
@@ -294,7 +294,7 @@
     "kn-6061318f-046b-4935-907d-8eafdce14930"
    ],
    "n_returned": 10,
-   "latency_ms": 271.1,
+   "latency_ms": 517.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -315,11 +315,11 @@
     "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
     "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
     "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
-    "?Q??m?;?u?'",
+    "2c56a7a9-5323-4ce4-ba09-35836ba15d54",
     "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
    ],
    "n_returned": 10,
-   "latency_ms": 412.6,
+   "latency_ms": 869.8,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.21428571428571427,
@@ -338,13 +338,13 @@
     "?",
     "bl-ec84b63d-b278-4944-8d7f-4aa7a51c0315",
     "?",
-    "mem-fb44a2fc-7405-41ff-87b3-84643ac07313",
+    "830ca37a-d334-4e41-ba89-64893dc8d628",
     "?",
-    "mem-a3c97012-5fa3-4915-a839-2c75c72005e0",
+    "ce9636dc-85a5-4dae-9e07-74ea2fcc6307",
     "?"
    ],
    "n_returned": 10,
-   "latency_ms": 377.3,
+   "latency_ms": 732.5,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -361,15 +361,15 @@
     "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-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
     "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
-    "mem-0228da71-d7f7-4f3b-b7b3-c5eede42b62a",
-    "ctx-4a41"
+    "mem-2265c223-9e19-47b5-b7ba-5e9c2ce1f22c",
+    "knw-729fc901-8335-44c4-9f3a-b150b4aa0915"
    ],
    "n_returned": 10,
-   "latency_ms": 758.8,
+   "latency_ms": 1594.8,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -382,44 +382,44 @@
    "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"
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
    ],
    "n_returned": 10,
-   "latency_ms": 741.3,
+   "latency_ms": 1664.0,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
    "recall@10": 1.0,
    "precision@5": 0.2,
-   "mrr@10": 0.5
+   "mrr@10": 1.0
   },
   {
    "id": "q16",
    "category": "paraphrase",
    "query": "choosing an uncomfortable fact over a pleasant fiction",
    "returned": [
-    "tag-fiction",
+    "mem-ef878e30-5851-4e82-8588-745415108941",
     "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
     "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
-    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
     "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
-    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-6fae4d4b-dbe8-45c5-8bd4-21ffd5caa240",
     "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
-    "mem-443bd012-fc9a-4088-b236-de5157a1ef92",
     "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
-    "mem-ca4d6a34-d354-413f-bc86-126cc17ca81c"
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea"
    ],
    "n_returned": 10,
-   "latency_ms": 642.2,
+   "latency_ms": 1348.7,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -434,17 +434,17 @@
    "returned": [
     "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
     "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
-    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "kn-2b961d24-7fb9-47c7-9515-e45a24dce39d",
     "knw-08559f5c-2306-4220-a146-398c74f1643c",
-    "4da5dbaf-46e5-4f3e-b474-f60d9f8241d3",
+    "kn-0710e5b4-799d-4a0e-afd3-62d43b38ea37",
     "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
-    "mem-434be7c8-88cb-4039-b79a-1da4ac4de783",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
     "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
-    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "kn-c72bb6db-bd1e-4d37-bded-0399194496f6",
     "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
    ],
    "n_returned": 10,
-   "latency_ms": 537.2,
+   "latency_ms": 1092.8,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -459,17 +459,17 @@
    "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"
+    "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": 725.1,
+   "latency_ms": 1410.6,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -482,19 +482,19 @@
    "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-0bb4f021-56de-4947-a35b-a37209e7ba21",
     "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"
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-23c27d3b-e0d2-43a8-a80c-0a44477ae18a"
    ],
    "n_returned": 10,
-   "latency_ms": 562.8,
+   "latency_ms": 1264.1,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -519,7 +519,7 @@
     "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac"
    ],
    "n_returned": 10,
-   "latency_ms": 686.5,
+   "latency_ms": 1604.8,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -544,7 +544,7 @@
     "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
    ],
    "n_returned": 10,
-   "latency_ms": 584.2,
+   "latency_ms": 1374.4,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -557,19 +557,19 @@
    "category": "paraphrase",
    "query": "what shifts tells you where to cut a system apart",
    "returned": [
-    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "5a2c118a-87bd-4239-97a7-9e02c5991983",
     "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
-    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "mem-ef878e30-5851-4e82-8588-745415108941",
     "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
-    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
     "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
-    "34356a36-0df5-4020-8dcc-5e7a423f8d4c",
+    "kn-22d77abe-b3c5-42fd-afcd-dcb87d924929",
     "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
-    "mem-22f5f665-3ad2-4063-88b0-915849a795f5",
+    "kn-ac3fa61f-5689-4fbe-8a42-eae016d524c2",
     "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
    ],
    "n_returned": 10,
-   "latency_ms": 719.6,
+   "latency_ms": 1632.6,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -584,17 +584,17 @@
    "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",
+    "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",
-    "ctx-4a41",
-    "mem-5708f4c9-3d61-4182-8543-2843698931e6"
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea"
    ],
    "n_returned": 10,
-   "latency_ms": 634.6,
+   "latency_ms": 1481.7,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -607,19 +607,19 @@
    "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-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-da21c52c-04a5-4f92-8fba-f10aac47e027",
     "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
-    "fce2792a-53fc-4d4a-be3b-42bd6ceb1ba7",
+    "kn-66a21179-2adc-4b19-a109-880cf4674d7d",
     "a1000001-0000-0000-0000-000000000001"
    ],
    "n_returned": 10,
-   "latency_ms": 674.2,
+   "latency_ms": 1525.5,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -638,13 +638,13 @@
     "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
     "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
     "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
-    "mem-a16deccb-16a7-419c-a013-ff824a4daa15",
+    "bl-e98cdd4c-01b5-459e-9036-3578cd5d975a",
     "a1000001-0000-0000-0000-000000000009",
-    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "mem-154c3ec1-061c-4314-9e5f-50dc9b9422bc",
     "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
    ],
    "n_returned": 10,
-   "latency_ms": 571.6,
+   "latency_ms": 1233.0,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -657,19 +657,19 @@
    "category": "paraphrase",
    "query": "a childhood offering no solid foundation to inherit",
    "returned": [
-    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "bl-3f57bc69-7285-4f4a-a861-2de52efca058",
     "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",
+    "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",
     "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
    ],
    "n_returned": 10,
-   "latency_ms": 603.4,
+   "latency_ms": 1344.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -688,17 +688,17 @@
     "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
     "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
     "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
-    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
     "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
-    "efe53612-6914-4936-8e3b-1e694eb174e5",
-    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
    ],
    "n_returned": 10,
-   "latency_ms": 656.2,
+   "latency_ms": 1443.6,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.18181818181818182,
-   "recall@10": 0.45454545454545453,
+   "recall@10": 0.5454545454545454,
    "precision@5": 0.4,
    "mrr@10": 0.5
   },
@@ -708,24 +708,24 @@
    "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",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
     "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"
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83"
    ],
    "n_returned": 10,
-   "latency_ms": 536.9,
+   "latency_ms": 1127.1,
    "error": null,
    "hit@5": 1.0,
-   "recall@5": 0.07692307692307693,
-   "recall@10": 0.3076923076923077,
-   "precision@5": 0.2,
-   "mrr@10": 0.25
+   "recall@5": 0.23076923076923078,
+   "recall@10": 0.6153846153846154,
+   "precision@5": 0.6,
+   "mrr@10": 0.5
   },
   {
    "id": "q29",
@@ -736,19 +736,19 @@
     "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"
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
    ],
    "n_returned": 10,
-   "latency_ms": 562.4,
+   "latency_ms": 1198.3,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.18181818181818182,
-   "recall@10": 0.45454545454545453,
+   "recall@10": 0.5454545454545454,
    "precision@5": 0.4,
    "mrr@10": 0.5
   },
@@ -769,7 +769,7 @@
     "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc"
    ],
    "n_returned": 10,
-   "latency_ms": 556.6,
+   "latency_ms": 1205.9,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -789,12 +789,12 @@
     "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
     "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
     "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
-    "tag-hope",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
     "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
     "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
    ],
    "n_returned": 10,
-   "latency_ms": 542.6,
+   "latency_ms": 1216.1,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 0.09090909090909091,
@@ -808,18 +808,18 @@
    "query": "man of the house six years old expectation",
    "returned": [
     "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
-    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-729fc901-8335-44c4-9f3a-b150b4aa0915",
     "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-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
     "knw-35940684-abc4-42f0-b942-818f66b1f69a",
-    "4f698ae6-c40e-464e-9798-50350991a188",
-    "719aa819-00a9-4f4b-a857-4f9fe5ad44d7",
+    "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": 683.5,
+   "latency_ms": 1439.5,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -833,7 +833,7 @@
    "query": "zqxjvw plimforth grebulon",
    "returned": [],
    "n_returned": 0,
-   "latency_ms": 350.4,
+   "latency_ms": 723.6,
    "error": null,
    "clean": true,
    "false_positives": 0
@@ -844,7 +844,7 @@
    "query": "flarnbistle quommetry",
    "returned": [],
    "n_returned": 0,
-   "latency_ms": 258.4,
+   "latency_ms": 505.6,
    "error": null,
    "clean": true,
    "false_positives": 0
@@ -853,12 +853,23 @@
    "id": "q35",
    "category": "nonsense",
    "query": "xxqzzt vurblenacht throom",
-   "returned": [],
-   "n_returned": 0,
-   "latency_ms": 348.4,
+   "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",
+    "?m?\\}Q??6??",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "?m?\\}Q??6??",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 741.2,
    "error": null,
-   "clean": true,
-   "false_positives": 0
+   "clean": false,
+   "false_positives": 10
   },
   {
    "id": "q36",
@@ -871,13 +882,13 @@
     "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",
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
     "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
-    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
-    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5"
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72"
    ],
    "n_returned": 10,
-   "latency_ms": 664.5,
+   "latency_ms": 1319.0,
    "error": null,
    "hit@5": 1.0,
    "recall@5": 1.0,
@@ -898,14 +909,14 @@
     "015644f5-8194-4af0-800d-dd4a0cd71396",
     "13705072-4515-4124-963d-083af490494f",
     "527ecb25-2587-47eb-8269-73be2431abd4",
-    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
     "a1000001-0000-0000-0000-000000000002",
     "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
-    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
-    "de3b6428-b76c-4c44-90e0-bf1dd6998027"
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "7ac62daa-2eac-4c7a-a97e-e4203fc1b57b"
    ],
    "n_returned": 10,
-   "latency_ms": 747.3,
+   "latency_ms": 1660.3,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,
@@ -933,7 +944,7 @@
     "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5"
    ],
    "n_returned": 10,
-   "latency_ms": 504.2,
+   "latency_ms": 1020.7,
    "error": null,
    "hit@5": 0.0,
    "recall@5": 0.0,

tools/retrieval-eval/wb2.py

@@ -1,92 +0,0 @@
-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))

vendor/el-runtime/v1.0.0-20260501/el_runtime.c

@@ -7175,12 +7175,6 @@ 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);
@@ -7276,8 +7270,6 @@ 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). */
@@ -7335,39 +7327,6 @@ 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
@@ -7420,9 +7379,9 @@ 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_wordstart(n->content, toks[t]) ||
-            istr_contains_wordstart(n->label,   toks[t]) ||
-            istr_contains_wordstart(n->tags,    toks[t]))
+        if (istr_contains(n->content, toks[t]) ||
+            istr_contains(n->label,   toks[t]) ||
+            istr_contains(n->tags,    toks[t]))
             score++;
     }
     return score;
@@ -7437,9 +7396,9 @@ 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]))
+        if (istr_contains(n->content, toks[t]) ||
+            istr_contains(n->label,   toks[t]) ||
+            istr_contains(n->tags,    toks[t]))
             m |= (uint32_t)1u << t;
     }
     return m;
@@ -7737,11 +7696,15 @@ static int64_t engram_assoc_leg(EngramStore* g,
  * survivable here only because the structural-relation filter leaves the
  * associative list EMPTY for most queries — a Memory node whose only edges are
  * `tagged` and `related` expands to nothing, so its ranking is untouched. */
+/* `no` is the count ALREADY in `out` — the promoted pass fills the head, the
+ * suppressed pass appends behind it and must dedup against the whole prefix
+ * (the same node can be promoted in one leg and suppressed in another, since
+ * its background activation differs per leg). (2026-08-07, claim 44/45) */
 static int64_t engram_interleave3(const EngramRankEntry* L, int64_t nL,
                                   const EngramSemEntry*  S, int64_t nS,
                                   const EngramSemEntry*  A, int64_t nA,
-                                  int64_t lim, int64_t* out) {
-    int64_t no = 0, li = 0, si = 0, ai = 0;
+                                  int64_t lim, int64_t* out, int64_t no) {
+    int64_t li = 0, si = 0, ai = 0;
     while (no < lim && (li < nL || si < nS || ai < nA)) {
         if (li < nL) {
             int dup = 0;
@@ -9312,26 +9275,6 @@ 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) {
@@ -9652,33 +9595,48 @@ el_val_t engram_get_node_by_label(el_val_t label) {
     return el_wrap_str(el_strdup("{}"));
 }
 
-/* ── 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").
+/* ── Layer 2: the executive filter, on the recall read path (claims 44/45) ──
  *
- * 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.
+ * 06-claims.md claim 44 (verbatim): "execute a first activation pass that
+ * propagates spreading activation from query-matched seed node records ...
+ * WITHOUT ANY THRESHOLD FILTERING, recording a background activation score for
+ * every reachable node record; and execute a second executive filter pass that
+ * computes a working memory weight for each background-activated node record by
+ * multiplying the background activation score by a goal-state attentional bias
+ * derived from the current query and by the node record's confidence value ...
+ * wherein context compilation uses only node records whose working memory
+ * weight exceeds a per-type threshold, and node records that do not exceed the
+ * threshold retain their background activation scores and are not discarded."
+ * Claim 45 keeps the un-promoted field available to callers.
+ * 05-detailed-description l.221: "Results are sorted with promoted nodes first
+ * ... followed by background-only nodes."
  *
- * 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.
+ * This pass exists in engram_activate and NOWHERE on the route the app calls.
+ * /api/neuron/recall reaches engram_search_json, whose three legs each get a
+ * fixed share of the output slots by rotation — so on a query where a leg is
+ * structurally incapable of being right, that leg still consumes its slots.
+ * The promotion gate is Will's own answer to that: a candidate that does not
+ * clear its per-type threshold is not discarded, it is moved behind the ones
+ * that do, and the freed slots go to whichever leg still has promoted material.
  *
- * 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) {
+ * ENGRAM_WM_LEG_SCAN bounds the per-leg work: only the head of each already
+ * sorted leg can reach a result slot at any sane limit.
+ */
+#define ENGRAM_WM_LEG_SCAN 64
+
+static int eg_wm_promote(const EngramNode* n, const char* q, double bg,
+                         double* wm_out) {
+    /* Same product engram_activate's pass 2 computes (l.8519), minus the
+     * inhibitory / inhibition-of-return terms, which need activation state
+     * this read path does not carry. */
+    double bias = engram_goal_bias(n, q);
+    double impf = (n->importance > 0.0) ? (0.5 + n->importance) : 1.0;
+    double wm   = bg * bias * n->confidence * impf;
+    if (wm_out) *wm_out = wm;
+    return wm > engram_type_threshold(n->node_type, n->tier);
+}
+
+el_val_t engram_search_json(el_val_t query, el_val_t limit) {
     EngramStore* g = engram_get();
     const char* q = EL_CSTR(query);
     int64_t lim = (int64_t)limit;
@@ -9700,7 +9658,7 @@ static el_val_t eg_search_json_impl(el_val_t query, el_val_t limit, int with_leg
                  * 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   = with_legs ? eg_embed_fetch(q, &qdim) : NULL;
+                float*  qv   = eg_embed_fetch(q, &qdim);
                 EngramSemEntry* sem = qv ? malloc((size_t)g->node_count * sizeof(EngramSemEntry)) : NULL;
                 int64_t nsem = 0;
                 int64_t nhits = 0;
@@ -9741,28 +9699,12 @@ static el_val_t eg_search_json_impl(el_val_t query, el_val_t limit, int with_leg
                     }
                     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) {
+                        /* Semantic leg: identical to eg_sem_term(), which is
+                         * left in place and still used by engram_search().
+                         * Inlined here only so one cosine serves both uses. */
+                        if (c > ENGRAM_EMBED_SEED_MIN) {
+                            double sv = (c - ENGRAM_EMBED_SEED_MIN) / (1.0 - ENGRAM_EMBED_SEED_MIN);
+                            if (sv > 1.0) sv = 1.0;
                             sem[nsem].idx = i; sem[nsem].sem = sv; nsem++;
                         }
                         /* Graph seeds: top-K by RAW cosine, insertion-ordered. */
@@ -9805,31 +9747,6 @@ static el_val_t eg_search_json_impl(el_val_t query, el_val_t limit, int with_leg
                 }
                 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
@@ -9840,22 +9757,79 @@ static el_val_t eg_search_json_impl(el_val_t query, el_val_t limit, int with_leg
                     ? engram_assoc_leg(g, hits, nhits, semseed, nsemseed,
                                        qv, qdim, assoc, ENGRAM_ASSOC_MAX)
                     : 0;
-                /* 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;
+                int64_t* order = malloc((size_t)lim * sizeof(int64_t));
                 if (order) {
-                    int64_t no = engram_interleave3(hits, nhits, sem, nsem,
-                                                    assoc, nassoc, lim, order);
+                    /* ── Layer 1 → background activation, per leg ──
+                     * Each leg's raw score is put on a common [0,1] footing
+                     * WITHOUT blending the legs against each other (that
+                     * failed in the score-fusion cut of the semantic leg —
+                     * two rankings with different spreads cannot be summed).
+                     * Lexical: BM25 over the score a node would earn covering
+                     * every query token at mean field length, so the scale is
+                     * "how much of this query's rare vocabulary did you
+                     * actually account for". Semantic: the shift-and-floor
+                     * value, already in [0,1]. Associative: cosine to the
+                     * query, which is what orders that leg. */
+                    double idf_sum = 0.0;
+                    for (int t = 0; t < ntok; t++) idf_sum += idf[t];
+                    double w_ideal = idf_sum * (ENGRAM_BM25_K1 + 1.0)
+                                   / (1.0 + ENGRAM_BM25_K1);
+                    if (w_ideal <= 0.0) w_ideal = 1.0;
+
+                    int64_t nLs = nhits  < ENGRAM_WM_LEG_SCAN ? nhits  : ENGRAM_WM_LEG_SCAN;
+                    int64_t nSs = nsem   < ENGRAM_WM_LEG_SCAN ? nsem   : ENGRAM_WM_LEG_SCAN;
+                    int64_t nAs = nassoc < ENGRAM_WM_LEG_SCAN ? nassoc : ENGRAM_WM_LEG_SCAN;
+
+                    EngramRankEntry Lp[ENGRAM_WM_LEG_SCAN], Lq[ENGRAM_WM_LEG_SCAN];
+                    EngramSemEntry  Sp[ENGRAM_WM_LEG_SCAN], Sq[ENGRAM_WM_LEG_SCAN];
+                    EngramSemEntry  Ap[ENGRAM_WM_LEG_SCAN], Aq[ENGRAM_WM_LEG_SCAN];
+                    int64_t nLp = 0, nLq = 0, nSp = 0, nSq = 0, nAp = 0, nAq = 0;
+
+                    /* ── Layer 2 → promote or suppress. Nothing is dropped. */
+                    for (int64_t i = 0; i < nLs; i++) {
+                        double bg = hits[i].w / w_ideal;
+                        if (bg > 1.0) bg = 1.0;
+                        if (eg_wm_promote(&g->nodes[hits[i].idx], q, bg, NULL))
+                            Lp[nLp++] = hits[i];
+                        else
+                            Lq[nLq++] = hits[i];
+                    }
+                    for (int64_t i = 0; i < nSs; i++) {
+                        /* RAW cosine, not the shift-and-floor value. The
+                         * first cut of this filter fed pass 2 the shifted
+                         * value, which for a genuine match (c .60-.70) is
+                         * 0.02-0.25 — under every per-type threshold — so the
+                         * whole semantic leg was suppressed while lexical
+                         * junk cleared its gate. Pass 2's thresholds are
+                         * calibrated against activation strengths in [0,1],
+                         * which is the scale raw cosine is on. Measured cost
+                         * of getting this wrong: paraphrase 61.5% -> 23.1%. */
+                        double bg = sem[i].sem * (1.0 - ENGRAM_EMBED_SEED_MIN)
+                                  + ENGRAM_EMBED_SEED_MIN;
+                        if (eg_wm_promote(&g->nodes[sem[i].idx], q, bg, NULL))
+                            Sp[nSp++] = sem[i];
+                        else
+                            Sq[nSq++] = sem[i];
+                    }
+                    for (int64_t i = 0; i < nAs; i++) {
+                        if (eg_wm_promote(&g->nodes[assoc[i].idx], q, assoc[i].sem, NULL))
+                            Ap[nAp++] = assoc[i];
+                        else
+                            Aq[nAq++] = assoc[i];
+                    }
+
+                    /* Promoted material fills the head, in leg order; the
+                     * background-only field follows behind it (claim 45). */
+                    int64_t no = engram_interleave3(Lp, nLp, Sp, nSp,
+                                                    Ap, nAp, lim, order, 0);
+                    if (no < lim)
+                        no = engram_interleave3(Lq, nLq, Sq, nSq,
+                                                Aq, nAq, lim, order, no);
+                    /* Anything past the scanned head of each leg, only if the
+                     * filter left the result short of the caller's limit. */
+                    if (no < lim)
+                        no = engram_interleave3(hits, nhits, sem, nsem,
+                                                assoc, nassoc, lim, order, no);
                     for (int64_t k = 0; k < no; k++) {
                         if (!first) jb_putc(&b, ',');
                         engram_emit_node_json(&b, &g->nodes[order[k]], 0);
@@ -9874,19 +9848,6 @@ static el_val_t eg_search_json_impl(el_val_t query, el_val_t limit, int with_leg
     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;

vendor/el-runtime/v1.0.0-20260501/el_runtime.h

@@ -612,7 +612,6 @@ 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);