feat(engram): word-start match primitive + corpus-vocabulary gate on recall

The retrieval match test is a raw substring scan, so a query token matches
anywhere INSIDE a corpus word: "throom" matches "bathroom". Measured over the
38-query gold set on this corpus that is not a rare accident - q28's lexical
leg is 36,954 records of which only 13 contain a query token at a word start
(99.96% mid-word noise), six further queries carry ~20,500 mid-word-only
records each, and the nonsense control q35 returns 7 records ALL of which
match only mid-word.

istr_contains_wordstart() anchors a token to a word start (preceding char not
alphanumeric) while still matching suffixes, so "value" still hits "values".
That empties the lexical leg for gibberish, and the nhits==0 corpus-vocabulary
gate (iteration 6's mechanism, feat/claim24-unfloored-semantic) then makes the
whole query decline rather than let the semantic leg answer it.

Measured vs feat/bm25-lexical-leg on the embedded corpus, 2 runs each,
0 queries of run-to-run drift on both sides:
  net +1 (nonsense:q35), 0 losses, McNemar p=1.0 -> NOT-SHOWN (floor is 6)
  nonsense clean 2/3 -> 3/3; exact_rare 100%, phrase 100%, paraphrase 61.5%,
  associative 66.7%, superseded 2/3 all UNCHANGED
  latency p50 1184 -> 543 ms (0.46x)

Iteration 6 called q35 "a DEFECTIVE CONTROL ... cannot be cleaned without
breaking the lexical leg". It can: the defect was the match primitive, and
cleaning it cost nothing.

Also committed: results-wsclaim24.json + cmp-nogate.json, a measured negative
for bundling the claim-24 unfloored semantic leg on top (gains q14/q25, breaks
q15/q28/q33/q34, net -2) - it independently reproduces iteration 6's q15/q28
losses and shows unflooring REQUIRES the vocabulary gate.

Reproducers: legs.py (leg-level replica, reproduces baseline hit@5 exactly on
all 38 queries), policy2.py, ceiling.py, wb2.py.

tools/retrieval-eval/ceiling.py

@@ -0,0 +1,43 @@
+import json,sys,pickle,numpy as np,itertools
+sys.path.insert(0,'.')
+from policy2 import legs3,outcome,G,NODES,merge
+# cache per-query leg id-lists, floored and unfloored
+cache={}
+for q in G['queries']:
+    Lf,Sf,Af=legs3(q['query'])
+    Lu,Su,Au=legs3(q['query'],unfloor=True)
+    cache[q['id']]=dict(L=Lf,Sf=Sf,A=Af,Su=Su,Au=Au)
+pickle.dump(cache,open('ceil.pkl','wb'))
+def mrg(pattern,L,S,A,lim=10):
+    out=[];p={'L':0,'S':0,'A':0};src={'L':L,'S':S,'A':A}
+    i=0
+    while len(out)<lim:
+        prog=False
+        for ch in pattern:
+            lst=src[ch]
+            if p[ch]<len(lst):
+                x=lst[p[ch]];p[ch]+=1;prog=True
+                if x not in out: out.append(x)
+                if len(out)>=lim: return out
+        if not prog: break
+    return out
+def ev(pattern,unfl):
+    res={}
+    for q in G['queries']:
+        c=cache[q['id']]
+        S=c['Su'] if unfl else c['Sf']
+        ids=[NODES[i]['id'] for i in mrg(pattern,c['L'],S,c['A'],10)]
+        res[q['id']]=outcome(q,ids)
+    return res
+base=ev('LSA',False)
+print("baseline",sum(base.values()))
+best=[]
+pats=['LSA','LAS','SLA','ALS','SAL','ASL','LSSA','LSASA','LSAA','LSSAA','LSAS','SSLA','LLSA','SALSA','LSAAS']
+for unfl in (False,True):
+    for p in pats:
+        r=ev(p,unfl)
+        g=sorted(k for k in base if r[k] and not base[k]);l=sorted(k for k in base if base[k] and not r[k])
+        best.append((len(g)-len(l),p,unfl,g,l))
+best.sort(reverse=True)
+for n,p,u,g,l in best[:10]:
+    print("net=%+d  pat=%-6s unfloor=%s gains=%s losses=%s"%(n,p,u,g,l))

tools/retrieval-eval/cmp-nogate.json

@@ -0,0 +1,146 @@
+{
+ "baseline": "bm25lex",
+ "candidate": "wsclaim24",
+ "n_shared_queries": 38,
+ "fixed_by_candidate": [
+  "q14",
+  "q25"
+ ],
+ "broken_by_candidate": [
+  "q15",
+  "q28",
+  "q33",
+  "q34"
+ ],
+ "discordant": 6,
+ "net_queries": -2,
+ "mcnemar_exact_p": 0.6875,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1184.4,
+  "latency_ms_p95": 1620.0,
+  "latency_ms_max": 1655.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5768475572047,
+  "recall@10": 0.6563414759843332,
+  "precision@5": 0.19428571428571437,
+  "mrr@10": 0.5026530612244898,
+  "nonsense_clean": "0/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 524.8,
+  "latency_ms_p95": 738.7,
+  "latency_ms_max": 755.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.5,
+    "recall@5": 0.07575757575757576,
+    "recall@10": 0.13636363636363635,
+    "mrr@10": 0.23214285714285712
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 0,
+    "avg_false_positives": 10.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6923076923076923,
+    "recall@5": 0.6923076923076923,
+    "recall@10": 0.7692307692307693,
+    "mrr@10": 0.29423076923076924
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5335884353741497,
+    "recall@10": 0.5933956916099773,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {
+  "baseline": {
+   "runs": 2,
+   "hit@5_min": 0.7428571428571429,
+   "hit@5_max": 0.7428571428571429,
+   "spread_queries": 0
+  }
+ }
+}

tools/retrieval-eval/comparison-bm25lex-vs-wordstart.json

@@ -0,0 +1,146 @@
+{
+ "baseline": "bm25lex",
+ "candidate": "wordstart",
+ "n_shared_queries": 38,
+ "fixed_by_candidate": [
+  "q35"
+ ],
+ "broken_by_candidate": [],
+ "discordant": 1,
+ "net_queries": 1,
+ "mcnemar_exact_p": 1.0,
+ "min_detectable_swing_queries": 6,
+ "observed_run_to_run_drift_queries": 0,
+ "noise_floor_queries": 6,
+ "verdict": "no measurable difference",
+ "baseline_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "2/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 1184.4,
+  "latency_ms_p95": 1620.0,
+  "latency_ms_max": 1655.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 2,
+    "avg_false_positives": 3.3333333333333335
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "candidate_aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "3/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 542.6,
+  "latency_ms_p95": 741.3,
+  "latency_ms_max": 758.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 3,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "repeat_variance": {
+  "baseline": {
+   "runs": 2,
+   "hit@5_min": 0.7428571428571429,
+   "hit@5_max": 0.7428571428571429,
+   "spread_queries": 0
+  },
+  "candidate": {
+   "runs": 2,
+   "hit@5_min": 0.7428571428571429,
+   "hit@5_max": 0.7428571428571429,
+   "spread_queries": 0
+  }
+ }
+}

tools/retrieval-eval/legs.py

@@ -0,0 +1,117 @@
+import json,pickle,os,math,urllib.request,numpy as np
+S='/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/sim/'
+C=pickle.load(open(S+'corpus.pkl','rb'))
+NODES=C['nodes']; EDGES=C['edges']; N=len(NODES)
+E=np.load(S+'emb.npy'); HAVE=np.load(S+'have.npy')
+En=E/np.maximum(np.linalg.norm(E,axis=1,keepdims=True),1e-12)
+LAYERS={int(l['layer_id']):l for l in (C['layers'] or [])} if C['layers'] else {}
+TRANS=set(i for i,l in LAYERS.items() if l.get('transparent'))
+def addressable(s):
+    if not s: return False
+    return all(0x20<=ord(ch)<=0x7e for ch in s)
+ADDR=np.array([addressable(n['id']) for n in NODES])
+OK=np.array([ (n['layer_id'] not in TRANS) and ADDR[i] for i,n in enumerate(NODES)])
+SAL=np.array([n['salience'] for n in NODES])
+LOW=[ (n['content']+'\x00'+n['label']+'\x00'+n['tags']).lower() for n in NODES]
+DL=np.array([float(len(n['content'])+len(n['label'])+len(n['tags'])) for n in NODES])
+IDX={}
+for i,n in enumerate(NODES):
+    IDX.setdefault(n['id'],i)
+STRUCT={"identity","contains","superseded_by","references","embodies","demonstrated_by","canonical-self","depends_on","currently_holds","activates"}
+ADJ_F=[[] for _ in range(N)]; ADJ_T=[[] for _ in range(N)]
+for e in EDGES:
+    a=IDX.get(e['from']); b=IDX.get(e['to'])
+    if a is None or b is None: continue
+    ADJ_F[a].append((e,b)); ADJ_T[b].append((e,a))
+EXCL=np.array([n['node_type'] in ('Tag','InternalStateEvent') for n in NODES])
+avgdl_all=None
+def tokenize(q):
+    out=[]
+    for t in q.split():
+        if not any(t.lower()==x.lower() for x in out): out.append(t)
+    return out
+_qcache={}
+def qemb(q):
+    if q in _qcache: return _qcache[q]
+    body=json.dumps({"model":"nomic-embed-text","prompt":q}).encode()
+    r=urllib.request.urlopen(urllib.request.Request("http://127.0.0.1:11434/api/embeddings",data=body,headers={"Content-Type":"application/json"}),timeout=30)
+    v=np.array(json.loads(r.read())["embedding"],dtype=np.float32)
+    v=v/np.linalg.norm(v); _qcache[q]=v; return v
+K1,B=1.2,0.75
+SEED_MIN=0.60; SEED_K=8; ASSOC_SEEDS=3; DEPTH=2; FIRE=0.02; AMAX=64; DECAY=0.7
+def legs(query):
+    toks=tokenize(query)
+    masks=[]; 
+    hit_idx=[]; hit_mask=[]
+    df=[0]*len(toks)
+    lt=[t.lower() for t in toks]
+    for i in range(N):
+        if not OK[i]: continue
+        s=LOW[i]; m=0
+        for t,tok in enumerate(lt):
+            if tok in s: m|=(1<<t)
+        if m:
+            hit_idx.append(i); hit_mask.append(m)
+            for t in range(len(toks)):
+                if m>>t&1: df[t]+=1
+    dl_n=int(OK.sum()); avgdl=float(DL[OK].sum()/max(dl_n,1))
+    idf=[math.log(1.0+((dl_n-d+0.5)/(d+0.5))) for d in df]
+    L=[]
+    for j,i in enumerate(hit_idx):
+        norm=1.0-B+B*(DL[i]/avgdl); w=0.0
+        for t in range(len(toks)):
+            if hit_mask[j]>>t&1: w+=idf[t]*(K1+1.0)/(1.0+K1*norm)
+        L.append((i,w,SAL[i]))
+    L.sort(key=lambda x:(-x[1],-x[2]))
+    qv=qemb(query)
+    cos=En@qv
+    cos=np.where(HAVE&OK,cos,-2.0)
+    order=np.argsort(-cos)
+    semfull=[(int(i),float(cos[i])) for i in order[:400]]
+    Sleg=[(i,(c-SEED_MIN)/(1-SEED_MIN)) for i,c in semfull if c>SEED_MIN]
+    semseed=[i for i,c in semfull[:SEED_K] if c>0.0]
+    # assoc
+    act={}; seen={}; qq=[]
+    for i,_,_ in L[:ASSOC_SEEDS]:
+        act[i]=1.0; seen[i]=2; qq.append((i,0))
+    for i in semseed:
+        if i in seen: continue
+        act[i]=1.0; seen[i]=2; qq.append((i,0))
+    qh=0
+    while qh<len(qq):
+        cur,h=qq[qh]; qh+=1
+        if h>=DEPTH: continue
+        parent=act[cur]
+        for e,oi in ADJ_F[cur]+ADJ_T[cur]:
+            if e['rel'] not in STRUCT: continue
+            if EXCL[oi]: continue
+            na=parent*e['w']*DECAY*SAL[oi]
+            if na<FIRE: continue
+            if seen.get(oi) and na<=act.get(oi,0): continue
+            act[oi]=na
+            if not seen.get(oi): seen[oi]=1
+            if len(qq)<AMAX*4: qq.append((oi,h+1))
+    A=[]
+    for i,st in seen.items():
+        if st!=1: continue
+        if not OK[i] or not HAVE[i]: continue
+        c=float(cos[i])
+        if c<=0.0: continue
+        A.append((i,c))
+    A.sort(key=lambda x:-x[1]); A=A[:AMAX]
+    return L,Sleg,A,cos
+def interleave3(L,Sl,A,lim=10):
+    out=[]; li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(Sl) or ai<len(A)):
+        if li<len(L):
+            if L[li][0] not in out: out.append(L[li][0])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(Sl):
+            if Sl[si][0] not in out: out.append(Sl[si][0])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai][0] not in out: out.append(A[ai][0])
+            ai+=1
+    return out

tools/retrieval-eval/policy2.py

@@ -0,0 +1,102 @@
+import json,sys,pickle,numpy as np
+sys.path.insert(0,'.')
+from legs import *
+GP='/Users/timlingo/Development/neuron-technologies/_wt-bm25lex/tools/retrieval-eval/'
+G=json.load(open(GP+'gold_set.json'))
+def legs3(query, sem_sal=False, assoc_sal=False, unfloor=False, sem_cap=None):
+    toks=tokenize(query)
+    hit_idx=[];hit_mask=[];df=[0]*len(toks);lt=[t.lower() for t in toks]
+    for i in range(N):
+        if not OK[i]: continue
+        s=LOW[i];m=0
+        for t,tok in enumerate(lt):
+            if tok in s: m|=(1<<t)
+        if m:
+            hit_idx.append(i);hit_mask.append(m)
+            for t in range(len(toks)):
+                if m>>t&1: df[t]+=1
+    dl_n=int(OK.sum());avgdl=float(DL[OK].sum()/max(dl_n,1))
+    idf=[math.log(1.0+((dl_n-d+0.5)/(d+0.5))) for d in df]
+    L=[]
+    for j,i in enumerate(hit_idx):
+        norm=1.0-B+B*(DL[i]/avgdl);w=0.0
+        for t in range(len(toks)):
+            if hit_mask[j]>>t&1: w+=idf[t]*(K1+1.0)/(1.0+K1*norm)
+        L.append((i,w,SAL[i]))
+    L.sort(key=lambda x:(-x[1],-x[2]))
+    if not L: return [],[],[]
+    qv=qemb(query);cos=En@qv;cos=np.where(HAVE&OK,cos,-2.0)
+    order=np.argsort(-cos)[:600]
+    cand=[int(i) for i in order if cos[i]>(0.0 if unfloor else SEED_MIN)]
+    key=(lambda i:(SAL[i] if sem_sal else 1.0)*float(cos[i]))
+    Sl=sorted(cand,key=lambda i:-key(i))
+    if sem_cap: Sl=Sl[:sem_cap]
+    semseed=[int(i) for i in order[:SEED_K] if cos[i]>0.0]
+    act={};seen={};qq=[]
+    for i,_,_ in L[:ASSOC_SEEDS]:
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    for i in semseed:
+        if i in seen: continue
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    qh=0
+    while qh<len(qq):
+        cur,h=qq[qh];qh+=1
+        if h>=DEPTH: continue
+        parent=act[cur]
+        for e,oi in ADJ_F[cur]+ADJ_T[cur]:
+            if e['rel'] not in STRUCT: continue
+            if EXCL[oi]: continue
+            na=parent*e['w']*DECAY*SAL[oi]
+            if na<FIRE: continue
+            if seen.get(oi) and na<=act.get(oi,0): continue
+            act[oi]=na
+            if not seen.get(oi): seen[oi]=1
+            if len(qq)<AMAX*4: qq.append((oi,h+1))
+    A=[]
+    for i,st in seen.items():
+        if st!=1 or not OK[i] or not HAVE[i]: continue
+        c=float(cos[i])
+        if c<=0.0: continue
+        A.append((i,(SAL[i] if assoc_sal else 1.0)*c))
+    A.sort(key=lambda x:-x[1]);A=[i for i,_ in A[:AMAX]]
+    return [i for i,_,_ in L],Sl,A
+def merge(L,S,A,lim=10):
+    out=[];li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(S) or ai<len(A)):
+        if li<len(L):
+            if L[li] not in out: out.append(L[li])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(S):
+            if S[si] not in out: out.append(S[si])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai] not in out: out.append(A[ai])
+            ai+=1
+    return out
+def outcome(q,ids):
+    c=q['category']
+    if c=='nonsense': return len(ids)==0
+    if c=='superseded':
+        a,b=q['must_outrank']
+        if a not in ids: return False
+        if b not in ids: return True
+        return ids.index(a)<ids.index(b)
+    return any(x in ids[:5] for x in q['relevant'])
+def run(**kw):
+    return {q['id']:outcome(q,[NODES[i]['id'] for i in merge(*legs3(q['query'],**kw),10)]) for q in G['queries']}
+base=run()
+print("baseline",sum(base.values()),"/38  misses:",[k for k,v in base.items() if not v])
+import itertools
+for name,kw in [
+  ('sem_sal(floored)',dict(sem_sal=True)),
+  ('unfloor',dict(unfloor=True)),
+  ('unfloor+sem_sal',dict(unfloor=True,sem_sal=True)),
+  ('assoc_sal',dict(assoc_sal=True)),
+  ('unfloor+sem_sal+assoc_sal',dict(unfloor=True,sem_sal=True,assoc_sal=True)),
+  ('sem_sal+assoc_sal(floored)',dict(sem_sal=True,assoc_sal=True)),
+]:
+    r=run(**kw)
+    g=sorted(k for k in base if r[k] and not base[k]); l=sorted(k for k in base if base[k] and not r[k])
+    print("%-28s net=%+d gains=%s losses=%s"%(name,len(g)-len(l),g,l))

tools/retrieval-eval/results-wordstart-r2.json

@@ -0,0 +1,948 @@
+{
+ "label": "wordstart-r2",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-wordstart",
+ "soul_md5": "32d4cf77672658a5f49dc7c9213e3ba2",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-eval/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7895,
+ "wall_clock_s": 28.7,
+ "child_pid": 1490,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "3/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 537.6,
+  "latency_ms_p95": 733.7,
+  "latency_ms_max": 761.4,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 3,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 165.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 164.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 163.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 172.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 167.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 164.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "tag-patterns",
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "project-Imprint__system_design__ADRs__tech_strategy__integration_patterns__governance_",
+    "project-Imprint__analysis_patterns__data_storytelling__SQL__dashboards__insight_framing_",
+    "bl-79028eed-c330-4724-9402-734062d13503",
+    "bl-39dad13d-7105-4049-8224-dc3c34fdb1f3",
+    "bl-4ef4d914-da46-4e0f-be78-5219b9547e9f",
+    "bl-7e7c3fdb-4132-487f-aa70-b2cd559cb7f0",
+    "bl-1d32bd54-cf17-4a1f-b235-982d09a36f04",
+    "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 281.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 254.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 255.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.4444444444444444,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "project-harmonic-framework",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "project-harmonic-framework_com",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "tag-harmonic-design",
+    "bl-92acd4eb-0452-4e8e-9f54-f8cd35170d76",
+    "tag-harmonic-framework",
+    "bl-18a9d1e4-1484-474c-bf6b-c6173212181b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 247.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1111111111111111,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-sarah",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "mem-1f32f73a-952c-41bc-96dc-8b8b70d8a7c1",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-a6cb3b8d-d89c-46fc-931d-e90c560783b0",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 263.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.4,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "?Q??m?;?u?'",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 397.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.21428571428571427,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "?",
+    "bl-ec84b63d-b278-4944-8d7f-4aa7a51c0315",
+    "?",
+    "mem-fb44a2fc-7405-41ff-87b3-84643ac07313",
+    "?",
+    "mem-a3c97012-5fa3-4915-a839-2c75c72005e0",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 341.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "cb070131-dfd4-4a38-91d7-22b1bde164d2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "knw-d788a210-613b-4c49-9486-88bbc9d4716f",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-a535f205-bc4c-4058-9171-6263c496044a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-0228da71-d7f7-4f3b-b7b3-c5eede42b62a",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 761.4,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "b1183213-d659-4759-85d7-5b1f22427fe2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "7452eb8f-be01-4b55-aec1-ff0c29e790f6",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "532277bf-2959-4beb-ae0d-b018c97678ee",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "d4015bd7-c592-4ed8-8574-1f15ad37af75"
+   ],
+   "n_returned": 10,
+   "latency_ms": 733.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "tag-fiction",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "mem-443bd012-fc9a-4088-b236-de5157a1ef92",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "mem-ca4d6a34-d354-413f-bc86-126cc17ca81c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 629.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "4da5dbaf-46e5-4f3e-b474-f60d9f8241d3",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "mem-434be7c8-88cb-4039-b79a-1da4ac4de783",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
+   ],
+   "n_returned": 10,
+   "latency_ms": 529.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-e5cc63c0-8701-49d6-855a-e387fe087771",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "mem-75e490d1-f0a9-4b73-8cfc-8daecfaf6f38",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "a1000001-0000-0000-0000-000000000010",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "bfad516b-c306-4c4c-874a-a347c46c05c2",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 747.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "tag-learning",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "345b6420-e004-4d2e-b55c-6a729393fa99",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-92a7fdc5-9dd0-48cf-a691-506058de3838",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000010",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 564.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "mem-cde58b77-50d3-4bac-9581-e70a4c02c015",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-8d699e2c-ac2a-4742-bb62-b6da00f4b10e",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-53d6adf0-cd08-4707-a237-daa5e65c7298",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac"
+   ],
+   "n_returned": 10,
+   "latency_ms": 689.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "bl-0e8f4880-7b24-43aa-aed9-ad4d9fc73ff8",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "bl-205141ad-b2a0-4d93-86d0-89eb0723e1bd",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "bl-34f51ddb-a840-459f-a248-94214f5febb6",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 588.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
+    "34356a36-0df5-4020-8dcc-5e7a423f8d4c",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "mem-22f5f665-3ad2-4063-88b0-915849a795f5",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 729.0,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000001",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-1b58b05c-9305-4f06-a586-a08c96008027",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "ctx-4a41",
+    "mem-5708f4c9-3d61-4182-8543-2843698931e6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 638.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "27e1b1a4-ad0b-49d9-812f-fedf43b8aabe",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "bl-87c93185-b2bf-40af-ae23-3c830c007abf",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "fce2792a-53fc-4d4a-be3b-42bd6ceb1ba7",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 679.0,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "mem-82158b02-a180-435d-84f0-0b7ce37511b4",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "e4f27651-52c5-43fd-aff3-61d31685b3cd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-a16deccb-16a7-419c-a013-ff824a4daa15",
+    "a1000001-0000-0000-0000-000000000009",
+    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 588.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-23c27d3b-e0d2-43a8-a80c-0a44477ae18a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "tag-childhood",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 613.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "efe53612-6914-4936-8e3b-1e694eb174e5",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 652.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-9110798f-d0cb-4446-bc2a-14f09b6a09e2",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 543.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-trailer-park-paladins",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "project-trailer-park-paladins",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 537.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-bea7473c-c687-414c-9c0b-00c509a616c1",
+    "bl-fc6fcb0b-9e4b-40bf-8e88-dbfe4e27c31a",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 538.3,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "tag-hope",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 533.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.18181818181818182,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-473f3f24-20f6-4f39-8589-3709538eb6ac",
+    "mem-a0b7cfda-bc9e-4f40-b9a9-1722cf3f8263",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "719aa819-00a9-4f4b-a857-4f9fe5ad44d7",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 673.8,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 350.7,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 254.6,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 345.8,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____architecture__",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____kotlin____architecture__",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "mem-c17aefb1-38b5-4ced-af50-fe524127e1a4",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 639.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 8
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "mem-6f0b2b45-90c1-4356-ac01-3daac05b09c8",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "13705072-4515-4124-963d-083af490494f",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "a1000001-0000-0000-0000-000000000002",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "de3b6428-b76c-4c44-90e0-bf1dd6998027"
+   ],
+   "n_returned": 10,
+   "latency_ms": 733.7,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "5fcba804-eb5b-48ec-82da-146b1c6bb50d",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "bl-c5c6571e-118f-47c7-8cbb-3ed0ebf64a51",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "86228228-7adf-41fb-b4c4-9ceea87953ae",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 507.9,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}

tools/retrieval-eval/results-wordstart.json

@@ -0,0 +1,948 @@
+{
+ "label": "wordstart",
+ "soul_binary": "/private/tmp/claude-501/-Users-timlingo/82369039-a20e-4b5a-8a5e-28234a57b996/scratchpad/soul-wordstart",
+ "soul_md5": "32d4cf77672658a5f49dc7c9213e3ba2",
+ "corpus": "/Users/timlingo/neuron-eval-corpora/snapshot-pre-repair-20260806-embedded.json",
+ "corpus_nodes": 78768,
+ "corpus_edges": 14214,
+ "gold_set": "/Users/timlingo/Development/neuron-technologies/_wt-eval/tools/retrieval-eval/gold_set.json",
+ "limit": 10,
+ "port": 7894,
+ "wall_clock_s": 28.9,
+ "child_pid": 1420,
+ "child_confirmed_dead": true,
+ "aggregate": {
+  "n_queries": 38,
+  "n_scored": 35,
+  "hit@5": 0.7428571428571429,
+  "recall@5": 0.5536485340056769,
+  "recall@10": 0.6175677497106068,
+  "precision@5": 0.20000000000000007,
+  "mrr@10": 0.5021428571428571,
+  "nonsense_clean": "3/3",
+  "superseded_outranks": "2/3",
+  "latency_ms_p50": 542.6,
+  "latency_ms_p95": 741.3,
+  "latency_ms_max": 758.8,
+  "errors": 0,
+  "by_category": {
+   "associative": {
+    "n": 6,
+    "hit@5": 0.6666666666666666,
+    "recall@5": 0.08857808857808858,
+    "recall@10": 0.23310023310023312,
+    "mrr@10": 0.25
+   },
+   "exact_rare": {
+    "n": 6,
+    "hit@5": 1.0,
+    "recall@5": 1.0,
+    "recall@10": 1.0,
+    "mrr@10": 1.0
+   },
+   "nonsense": {
+    "n": 3,
+    "clean": 3,
+    "avg_false_positives": 0.0
+   },
+   "paraphrase": {
+    "n": 13,
+    "hit@5": 0.6153846153846154,
+    "recall@5": 0.6153846153846154,
+    "recall@10": 0.6153846153846154,
+    "mrr@10": 0.2846153846153846
+   },
+   "phrase": {
+    "n": 7,
+    "hit@5": 1.0,
+    "recall@5": 0.5494614512471656,
+    "recall@10": 0.6023242630385487,
+    "mrr@10": 0.8214285714285714
+   },
+   "superseded": {
+    "n": 3,
+    "hit@5": 0.3333333333333333,
+    "recall@5": 0.3333333333333333,
+    "recall@10": 0.6666666666666666,
+    "mrr@10": 0.20833333333333334,
+    "outranks": 2
+   }
+  }
+ },
+ "rows": [
+  {
+   "id": "q01",
+   "category": "exact_rare",
+   "query": "unjailbreakable",
+   "returned": [
+    "mem-7f61beb4-271c-4feb-9f6e-1c9c837a6226"
+   ],
+   "n_returned": 1,
+   "latency_ms": 170.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q02",
+   "category": "exact_rare",
+   "query": "engram-migrate",
+   "returned": [
+    "mem-6fdf6545-5e1a-43a9-8bdc-d2cd248146a5",
+    "bl-ba764d70-e9d7-4f62-848f-719cb665f45e",
+    "mem-22fe5ec8-ae0d-4583-a05c-d1ef50353257",
+    "bl-b28d7256-6f74-4567-bd90-40d0ef2a6d78",
+    "project-engram",
+    "ctx-45bc",
+    "project-engram-lang",
+    "ctx-175f",
+    "mem-60778715-758c-4677-933d-fc39b8f94152",
+    "ctx-74ed"
+   ],
+   "n_returned": 10,
+   "latency_ms": 210.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q03",
+   "category": "exact_rare",
+   "query": "cartabandonedevent",
+   "returned": [
+    "mem-1ba7c67d-85b9-4c2e-9fe2-39f8b0477091"
+   ],
+   "n_returned": 1,
+   "latency_ms": 167.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q04",
+   "category": "exact_rare",
+   "query": "pre-apprenticeship",
+   "returned": [
+    "mem-89c02aae-d3ca-43f9-9e5d-eb369896276c"
+   ],
+   "n_returned": 1,
+   "latency_ms": 166.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q05",
+   "category": "exact_rare",
+   "query": "inferencenodemanager",
+   "returned": [
+    "mem-73969486-143f-4431-b5e6-6845d1cc9848",
+    "bl-c1765767-3e27-449a-8c94-10411d1eb7c0",
+    "project-Add_inference_url_config_to_Neuron_MCP__Route_summarization_gen_tasks_to_Pantheon__keep_frontier_for_complex_reasoning_"
+   ],
+   "n_returned": 3,
+   "latency_ms": 162.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q06",
+   "category": "exact_rare",
+   "query": "clear-eyed",
+   "returned": [
+    "knw-c72597c5-c23d-4c08-8e9e-996dadf26a99"
+   ],
+   "n_returned": 1,
+   "latency_ms": 162.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q07",
+   "category": "phrase",
+   "query": "patterns not returns",
+   "returned": [
+    "tag-patterns",
+    "mem-a4a9dfc3-e40b-49b3-b1e1-060e8be2f482",
+    "project-Imprint__system_design__ADRs__tech_strategy__integration_patterns__governance_",
+    "project-Imprint__analysis_patterns__data_storytelling__SQL__dashboards__insight_framing_",
+    "bl-79028eed-c330-4724-9402-734062d13503",
+    "bl-39dad13d-7105-4049-8224-dc3c34fdb1f3",
+    "bl-4ef4d914-da46-4e0f-be78-5219b9547e9f",
+    "bl-7e7c3fdb-4132-487f-aa70-b2cd559cb7f0",
+    "bl-1d32bd54-cf17-4a1f-b235-982d09a36f04",
+    "bl-b8af6601-a8cb-41b5-aef5-ab8a57432dd5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 306.7,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q08",
+   "category": "phrase",
+   "query": "thirty moves",
+   "returned": [
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 261.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1875,
+   "recall@10": 0.375,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q09",
+   "category": "phrase",
+   "query": "Grandma Lucas",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "art-0f0277a1-4a8e-4645-95dd-fa379976f31c",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4"
+   ],
+   "n_returned": 10,
+   "latency_ms": 272.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.3333333333333333,
+   "recall@10": 0.4444444444444444,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q10",
+   "category": "phrase",
+   "query": "Directed Harmonic",
+   "returned": [
+    "bl-dcee1887-34c4-4ffa-9119-1e291685ba08",
+    "project-harmonic-framework",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "mem-7eeacad7-d7c2-4c2b-8348-19a59aa6dbaf",
+    "project-harmonic-framework_com",
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "tag-harmonic-design",
+    "bl-92acd4eb-0452-4e8e-9f54-f8cd35170d76",
+    "tag-harmonic-framework",
+    "bl-18a9d1e4-1484-474c-bf6b-c6173212181b"
+   ],
+   "n_returned": 10,
+   "latency_ms": 265.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.1111111111111111,
+   "recall@10": 0.1111111111111111,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q11",
+   "category": "phrase",
+   "query": "Sarah Bishop",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-sarah",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "mem-1f32f73a-952c-41bc-96dc-8b8b70d8a7c1",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-a6cb3b8d-d89c-46fc-931d-e90c560783b0",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 271.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.4,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q12",
+   "category": "phrase",
+   "query": "Directed Autonomous Runtime Modification",
+   "returned": [
+    "mem-e6327f52-2bda-4ce7-9471-2fffd1e172de",
+    "bl-31abf75b-998f-4a4f-a6dd-8204119e0451",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5",
+    "bl-6f99e111-7055-4635-9831-a489747ce418",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-967536a0-d49d-44fb-8cfb-b31b40bcbfae",
+    "bl-8b58d9bc-352b-4842-a7f8-a6254b5d1e25",
+    "?Q??m?;?u?'",
+    "bl-39cec462-c80c-4970-a3aa-91fe83053bde"
+   ],
+   "n_returned": 10,
+   "latency_ms": 412.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.21428571428571427,
+   "recall@10": 0.2857142857142857,
+   "precision@5": 0.6,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q13",
+   "category": "phrase",
+   "query": "zero-knowledge encrypted backup",
+   "returned": [
+    "deda48cd-5e1a-46cb-bd43-8016afdb3a8a",
+    "8f3abb0d-77ed-4af3-9f4d-ba62cd198886",
+    "7774a16c-1027-4e3b-a21e-67f1f95a4acd",
+    "?",
+    "bl-ec84b63d-b278-4944-8d7f-4aa7a51c0315",
+    "?",
+    "mem-fb44a2fc-7405-41ff-87b3-84643ac07313",
+    "?",
+    "mem-a3c97012-5fa3-4915-a839-2c75c72005e0",
+    "?"
+   ],
+   "n_returned": 10,
+   "latency_ms": 377.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 1.0
+  },
+  {
+   "id": "q14",
+   "category": "paraphrase",
+   "query": "the elderly relative who passed while he stayed away",
+   "returned": [
+    "cb070131-dfd4-4a38-91d7-22b1bde164d2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "knw-d788a210-613b-4c49-9486-88bbc9d4716f",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-a535f205-bc4c-4058-9171-6263c496044a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-0228da71-d7f7-4f3b-b7b3-c5eede42b62a",
+    "ctx-4a41"
+   ],
+   "n_returned": 10,
+   "latency_ms": 758.8,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q15",
+   "category": "paraphrase",
+   "query": "a soldier sidelined by illness who refused to quit",
+   "returned": [
+    "b1183213-d659-4759-85d7-5b1f22427fe2",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-16efddd1-c43d-4a42-9d78-f54fb82bd277",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "7452eb8f-be01-4b55-aec1-ff0c29e790f6",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "532277bf-2959-4beb-ae0d-b018c97678ee",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "d4015bd7-c592-4ed8-8574-1f15ad37af75"
+   ],
+   "n_returned": 10,
+   "latency_ms": 741.3,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q16",
+   "category": "paraphrase",
+   "query": "choosing an uncomfortable fact over a pleasant fiction",
+   "returned": [
+    "tag-fiction",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-8d690e9d-a7e9-4062-b2f8-e2064294e463",
+    "knw-8fd9836c-cc39-49df-8d61-babda626cc88",
+    "mem-ce793303-c5a5-4586-a232-a3426edd9ec7",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "mem-443bd012-fc9a-4088-b236-de5157a1ef92",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "mem-ca4d6a34-d354-413f-bc86-126cc17ca81c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 642.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q17",
+   "category": "paraphrase",
+   "query": "a tight payload beats a bloated one",
+   "returned": [
+    "bl-680b24a9-edc3-4a9d-847a-bff0b46b568c",
+    "bl-798d135f-3987-4ccd-8de6-70ca2f358337",
+    "08f0d1e2-8d0e-42e3-9f0a-8186ae31ec7e",
+    "knw-08559f5c-2306-4220-a146-398c74f1643c",
+    "4da5dbaf-46e5-4f3e-b474-f60d9f8241d3",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "mem-434be7c8-88cb-4039-b79a-1da4ac4de783",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "bl-79ce4464-5dd6-49bd-9b0c-9803549d0665"
+   ],
+   "n_returned": 10,
+   "latency_ms": 537.2,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q18",
+   "category": "paraphrase",
+   "query": "if you are able and nobody is coming the job is yours",
+   "returned": [
+    "bl-4476e856-c567-4b49-8ff7-d7dca3e5715e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-e5cc63c0-8701-49d6-855a-e387fe087771",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "mem-75e490d1-f0a9-4b73-8cfc-8daecfaf6f38",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "a1000001-0000-0000-0000-000000000010",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "bfad516b-c306-4c4c-874a-a347c46c05c2",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 725.1,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q19",
+   "category": "paraphrase",
+   "query": "learning is the wealth creditors cannot seize",
+   "returned": [
+    "tag-learning",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "345b6420-e004-4d2e-b55c-6a729393fa99",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-92a7fdc5-9dd0-48cf-a691-506058de3838",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000010",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 562.8,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q20",
+   "category": "paraphrase",
+   "query": "reliability proven by track record not assertion",
+   "returned": [
+    "mem-cde58b77-50d3-4bac-9581-e70a4c02c015",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-8d699e2c-ac2a-4742-bb62-b6da00f4b10e",
+    "knw-f671966c-3387-4848-abca-b5deec122e00",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "mem-53d6adf0-cd08-4707-a237-daa5e65c7298",
+    "a708dd6e-fe73-4f2f-a21e-89daa0985487",
+    "knw-6b48dce2-f21c-452a-9db5-4e6aa61c87ca",
+    "bl-ef2bac68-e119-4139-b529-c7a1404ae3ac"
+   ],
+   "n_returned": 10,
+   "latency_ms": 686.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q21",
+   "category": "paraphrase",
+   "query": "boundaries that enable instead of confine",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "bl-0e8f4880-7b24-43aa-aed9-ad4d9fc73ff8",
+    "project-Source_kn-6f248a50__Add_containment_rules__convergence__location-independence__failure_modes_",
+    "bl-8848929a-a23a-46bc-a2c7-fe3a3bc1cddf",
+    "bl-205141ad-b2a0-4d93-86d0-89eb0723e1bd",
+    "bl-e93858c4-7cac-4b1a-bb62-490790d4c3f3",
+    "bl-34f51ddb-a840-459f-a248-94214f5febb6",
+    "bl-286b562a-5299-40e0-a32a-afa9cbdfe995"
+   ],
+   "n_returned": 10,
+   "latency_ms": 584.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q22",
+   "category": "paraphrase",
+   "query": "what shifts tells you where to cut a system apart",
+   "returned": [
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c",
+    "bl-4c5b385e-135a-4663-8521-96af0b491121",
+    "knw-12b4b913-7a25-4b0d-844c-504c01d6725e",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "knw-9707256e-ed44-4042-bd88-f90fa514e1cf",
+    "34356a36-0df5-4020-8dcc-5e7a423f8d4c",
+    "knw-0087493b-25cd-45b0-bf46-c078c5b49718",
+    "mem-22f5f665-3ad2-4063-88b0-915849a795f5",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 719.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q23",
+   "category": "paraphrase",
+   "query": "a mind that compounds instead of resetting each day",
+   "returned": [
+    "bl-8dd70cac-866d-4ff2-b9fe-b4b3c5f094bb",
+    "mem-b43f6ef4-2f5a-418d-b5ce-3f21520cf6b8",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-ed33e669-0790-44cb-a036-958d605c6fea",
+    "a1000001-0000-0000-0000-000000000001",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-1b58b05c-9305-4f06-a586-a08c96008027",
+    "mem-024598a9-ed2e-4eeb-b1e1-5410856ff132",
+    "ctx-4a41",
+    "mem-5708f4c9-3d61-4182-8543-2843698931e6"
+   ],
+   "n_returned": 10,
+   "latency_ms": 634.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q24",
+   "category": "paraphrase",
+   "query": "loved for the unedited self and not the polished exterior",
+   "returned": [
+    "077d064f-3489-4c05-9aca-3782f96b51db",
+    "knw-f9ce17a7-17fc-431f-8f23-695b670ec4fa",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "27e1b1a4-ad0b-49d9-812f-fedf43b8aabe",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "bl-87c93185-b2bf-40af-ae23-3c830c007abf",
+    "knw-920c891f-bb8c-48c4-9afc-018ef12dcdc4",
+    "fce2792a-53fc-4d4a-be3b-42bd6ceb1ba7",
+    "a1000001-0000-0000-0000-000000000001"
+   ],
+   "n_returned": 10,
+   "latency_ms": 674.2,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q25",
+   "category": "paraphrase",
+   "query": "cheerfulness you arrive at instead of assuming",
+   "returned": [
+    "mem-82158b02-a180-435d-84f0-0b7ce37511b4",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "e4f27651-52c5-43fd-aff3-61d31685b3cd",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "mem-5624ec9d-62ba-4aba-8a3d-6afec6c09dd4",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "mem-a16deccb-16a7-419c-a013-ff824a4daa15",
+    "a1000001-0000-0000-0000-000000000009",
+    "mem-833dbbcd-2400-4594-bb35-93b023049ac0",
+    "kn-13f60407-7b70-4db1-964f-ea1f8196efbd"
+   ],
+   "n_returned": 10,
+   "latency_ms": 571.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q26",
+   "category": "paraphrase",
+   "query": "a childhood offering no solid foundation to inherit",
+   "returned": [
+    "mem-b99efff0-00e6-40c8-9c5b-730330eef33b",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "knw-2c46cfb4-6d4e-4822-8a1a-7d743c1e4329",
+    "knw-f6ed7d00-bf7d-42ce-9e40-77cf3406e918",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "knw-23c27d3b-e0d2-43a8-a80c-0a44477ae18a",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-f230b362-b201-4402-9833-4160c89ab3d4",
+    "tag-childhood",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21"
+   ],
+   "n_returned": 10,
+   "latency_ms": 603.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.2
+  },
+  {
+   "id": "q27",
+   "category": "associative",
+   "query": "Grandma Lucas stroke February 2006 goodbye window",
+   "returned": [
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "kn-0bb4f021-56de-4947-a35b-a37209e7ba21",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "efe53612-6914-4936-8e3b-1e694eb174e5",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 656.2,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q28",
+   "category": "associative",
+   "query": "Marines hernia sepsis medical ward",
+   "returned": [
+    "bl-33ecccc2-e37f-43db-91b3-c2a86f08aaac",
+    "54608b69-78b6-4239-b60f-b8206cfecacc",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "mem-9110798f-d0cb-4446-bc2a-14f09b6a09e2",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "art-79042b8b-6192-440f-90b0-60708f7e6325",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "art-ddfcd045-2c3b-4a1e-9966-fec5ce44e1dd",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71"
+   ],
+   "n_returned": 10,
+   "latency_ms": 536.9,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.07692307692307693,
+   "recall@10": 0.3076923076923077,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q29",
+   "category": "associative",
+   "query": "Sarah Bishop Dyer trailer performance",
+   "returned": [
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-a99cefe3-5e83-4050-98d8-6c69f57c7c71",
+    "766de879-f9d0-4a07-b6df-b43ee13763d8",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "tag-trailer-park-paladins",
+    "kn-5de5a9ac-fd15-45ab-bf18-77566781cf40",
+    "project-trailer-park-paladins",
+    "kn-78db5396-3dbc-4481-bfc7-e4e1422feb1c"
+   ],
+   "n_returned": 10,
+   "latency_ms": 562.4,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.18181818181818182,
+   "recall@10": 0.45454545454545453,
+   "precision@5": 0.4,
+   "mrr@10": 0.5
+  },
+  {
+   "id": "q30",
+   "category": "associative",
+   "query": "Swarm Architecture containment lateral worker",
+   "returned": [
+    "bl-0fac287f-f4c0-4f15-bc4d-ff7f8a7af3ae",
+    "bl-9bde67c1-f0ba-4c3a-8fe5-de0deee0ce43",
+    "bl-2515d870-e35e-443b-ba20-5150bbc73fed",
+    "kn-a5b3d0ac-f6a1-49a4-aebb-b8b4cd67fe83",
+    "kn-b36902cc-0b05-44ba-9aa7-800e5dea9ca9",
+    "bl-bea7473c-c687-414c-9c0b-00c509a616c1",
+    "bl-fc6fcb0b-9e4b-40bf-8e88-dbfe4e27c31a",
+    "kn-6f248a50-355b-47bb-aec8-e0e646a9b077",
+    "kn-6061318f-046b-4935-907d-8eafdce14930",
+    "mem-ab34c2f7-3243-424b-affa-25555f6cf9cc"
+   ],
+   "n_returned": 10,
+   "latency_ms": 556.6,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q31",
+   "category": "associative",
+   "query": "hope won inside the narrative preface",
+   "returned": [
+    "kn-e0423482-cfa5-4796-8689-8495c93b66bc",
+    "knw-e94982a2-358d-4f2f-af31-8ee0fcec07c6",
+    "bl-2b00aeb0-c0fa-4a9f-8f30-4207e98b3d52",
+    "kn-58874a74-b96f-4883-9e08-45707f4bd3ee",
+    "kn-5b606390-a52d-4ca2-8e0e-eba141d13440",
+    "knw-4aebd815-4eaf-49d7-954b-03595f3d48be",
+    "knw-723551f5-1950-42a3-8b89-b6a06913cef0",
+    "tag-hope",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "kn-db9f141b-dbe3-4037-92e0-4bb9be0e5e6e"
+   ],
+   "n_returned": 10,
+   "latency_ms": 542.6,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 0.09090909090909091,
+   "recall@10": 0.18181818181818182,
+   "precision@5": 0.2,
+   "mrr@10": 0.25
+  },
+  {
+   "id": "q32",
+   "category": "associative",
+   "query": "man of the house six years old expectation",
+   "returned": [
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "knw-528dbc37-eabc-4b75-a7a5-65bf38d6018a",
+    "knw-d357b6bb-ad8a-4791-b516-426aea45fa5b",
+    "knw-473f3f24-20f6-4f39-8589-3709538eb6ac",
+    "mem-a0b7cfda-bc9e-4f40-b9a9-1722cf3f8263",
+    "knw-7902acca-604e-409b-8faf-ad85424211d0",
+    "knw-35940684-abc4-42f0-b942-818f66b1f69a",
+    "4f698ae6-c40e-464e-9798-50350991a188",
+    "719aa819-00a9-4f4b-a857-4f9fe5ad44d7",
+    "kn-6061318f-046b-4935-907d-8eafdce14930"
+   ],
+   "n_returned": 10,
+   "latency_ms": 683.5,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0
+  },
+  {
+   "id": "q33",
+   "category": "nonsense",
+   "query": "zqxjvw plimforth grebulon",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 350.4,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q34",
+   "category": "nonsense",
+   "query": "flarnbistle quommetry",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 258.4,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q35",
+   "category": "nonsense",
+   "query": "xxqzzt vurblenacht throom",
+   "returned": [],
+   "n_returned": 0,
+   "latency_ms": 348.4,
+   "error": null,
+   "clean": true,
+   "false_positives": 0
+  },
+  {
+   "id": "q36",
+   "category": "superseded",
+   "query": "is the self-improvement architecture called DARMA or DHARMA",
+   "returned": [
+    "mem-f3b37427-b7d1-4f7e-b32c-0241a20ce8da",
+    "mem-80d7416b-20e9-48a0-b176-b215527e2f56",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____architecture__",
+    "kn-b7e98d63-8b83-4911-b4d0-990602a7f575",
+    "tag-__darma____cgi____patents____self-improvement____character-preservation____autonomous____kotlin____architecture__",
+    "knw-e047bb42-dc5b-4383-9e88-e508dc03abe3",
+    "mem-c17aefb1-38b5-4ced-af50-fe524127e1a4",
+    "bl-5b17bd3b-0c41-46cb-a710-6fa4429692ff",
+    "bl-145a0985-2382-400f-a7c5-c335c5e30a72",
+    "mem-82b93b21-a865-410f-9ec1-fc54121d9bb5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 664.5,
+   "error": null,
+   "hit@5": 1.0,
+   "recall@5": 1.0,
+   "recall@10": 1.0,
+   "precision@5": 0.2,
+   "mrr@10": 0.5,
+   "outranks": true,
+   "rank_correct": 2,
+   "rank_stale": 8
+  },
+  {
+   "id": "q37",
+   "category": "superseded",
+   "query": "how many provisional patents does Will actually have",
+   "returned": [
+    "mem-6f0b2b45-90c1-4356-ac01-3daac05b09c8",
+    "12082f7e-e320-438b-bd65-083d8259748f",
+    "015644f5-8194-4af0-800d-dd4a0cd71396",
+    "13705072-4515-4124-963d-083af490494f",
+    "527ecb25-2587-47eb-8269-73be2431abd4",
+    "6de314bf-5c4c-4cfc-871f-fa2e422d45e6",
+    "a1000001-0000-0000-0000-000000000002",
+    "3cf706a1-3825-45d8-b0a9-06cae6cdf5b8",
+    "kn-eb1b9e18-3dc6-4b9b-9cc6-86e0ae6b6be8",
+    "de3b6428-b76c-4c44-90e0-bf1dd6998027"
+   ],
+   "n_returned": 10,
+   "latency_ms": 747.3,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 1.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.125,
+   "outranks": true,
+   "rank_correct": 8,
+   "rank_stale": null
+  },
+  {
+   "id": "q38",
+   "category": "superseded",
+   "query": "is MCP still the live integration layer",
+   "returned": [
+    "5fcba804-eb5b-48ec-82da-146b1c6bb50d",
+    "bl-7328cbe3-0200-43c2-88e7-0a164e15fca4",
+    "bl-c8c19362-430b-4817-9cf4-9e85e0099c64",
+    "bl-c5c6571e-118f-47c7-8cbb-3ed0ebf64a51",
+    "mem-101e81b4-8097-4749-8d8d-7bb66de34517",
+    "ctx-3a55",
+    "86228228-7adf-41fb-b4c4-9ceea87953ae",
+    "4509ed62-9fb2-48b8-9038-ac569fca9604",
+    "bl-4f7b651b-6b33-449c-8a3b-cfce12ce984b",
+    "mem-3a2cf162-d93b-4f29-86f2-5066fb7fe1f5"
+   ],
+   "n_returned": 10,
+   "latency_ms": 504.2,
+   "error": null,
+   "hit@5": 0.0,
+   "recall@5": 0.0,
+   "recall@10": 0.0,
+   "precision@5": 0.0,
+   "mrr@10": 0.0,
+   "outranks": false,
+   "rank_correct": null,
+   "rank_stale": 5
+  }
+ ]
+}

tools/retrieval-eval/wb2.py

@@ -0,0 +1,92 @@
+import json,sys,pickle,numpy as np
+sys.path.insert(0,'.')
+from legs import *
+GP='/Users/timlingo/Development/neuron-technologies/_wt-bm25lex/tools/retrieval-eval/'
+G=json.load(open(GP+'gold_set.json'))
+def wstart(s,tok):
+    i=s.find(tok)
+    while i!=-1:
+        if i==0 or not s[i-1].isalnum(): return True
+        i=s.find(tok,i+1)
+    return False
+def legs4(query, wordstart=False, unfloor=False):
+    toks=tokenize(query); lt=[t.lower() for t in toks]
+    hit_idx=[];hit_mask=[];df=[0]*len(toks)
+    for i in range(N):
+        if not OK[i]: continue
+        s=LOW[i];m=0
+        for t,tok in enumerate(lt):
+            if tok in s and (not wordstart or wstart(s,tok)): m|=(1<<t)
+        if m:
+            hit_idx.append(i);hit_mask.append(m)
+            for t in range(len(toks)):
+                if m>>t&1: df[t]+=1
+    dl_n=int(OK.sum());avgdl=float(DL[OK].sum()/max(dl_n,1))
+    idf=[math.log(1.0+((dl_n-d+0.5)/(d+0.5))) for d in df]
+    L=[]
+    for j,i in enumerate(hit_idx):
+        norm=1.0-B+B*(DL[i]/avgdl);w=0.0
+        for t in range(len(toks)):
+            if hit_mask[j]>>t&1: w+=idf[t]*(K1+1.0)/(1.0+K1*norm)
+        L.append((i,w,SAL[i]))
+    L.sort(key=lambda x:(-x[1],-x[2]))
+    if not L: return [],[],[]
+    qv=qemb(query);cos=En@qv;cos=np.where(HAVE&OK,cos,-2.0)
+    order=np.argsort(-cos)[:600]
+    Sl=[int(i) for i in order if cos[i]>(0.0 if unfloor else SEED_MIN)]
+    semseed=[int(i) for i in order[:SEED_K] if cos[i]>0.0]
+    act={};seen={};qq=[]
+    for i,_,_ in L[:ASSOC_SEEDS]:
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    for i in semseed:
+        if i in seen: continue
+        act[i]=1.0;seen[i]=2;qq.append((i,0))
+    qh=0
+    while qh<len(qq):
+        cur,h=qq[qh];qh+=1
+        if h>=DEPTH: continue
+        parent=act[cur]
+        for e,oi in ADJ_F[cur]+ADJ_T[cur]:
+            if e['rel'] not in STRUCT or EXCL[oi]: continue
+            na=parent*e['w']*DECAY*SAL[oi]
+            if na<FIRE: continue
+            if seen.get(oi) and na<=act.get(oi,0): continue
+            act[oi]=na
+            if not seen.get(oi): seen[oi]=1
+            if len(qq)<AMAX*4: qq.append((oi,h+1))
+    A=sorted([(i,float(cos[i])) for i,st in seen.items() if st==1 and OK[i] and HAVE[i] and cos[i]>0.0],key=lambda x:-x[1])[:AMAX]
+    return [i for i,_,_ in L],Sl,[i for i,_ in A]
+def merge(L,S,A,lim=10):
+    out=[];li=si=ai=0
+    while len(out)<lim and (li<len(L) or si<len(S) or ai<len(A)):
+        if li<len(L):
+            if L[li] not in out: out.append(L[li])
+            li+=1
+        if len(out)>=lim: break
+        if si<len(S):
+            if S[si] not in out: out.append(S[si])
+            si+=1
+        if len(out)>=lim: break
+        if ai<len(A):
+            if A[ai] not in out: out.append(A[ai])
+            ai+=1
+    return out
+def outcome(q,ids):
+    c=q['category']
+    if c=='nonsense': return len(ids)==0
+    if c=='superseded':
+        a,b=q['must_outrank']
+        if a not in ids: return False
+        if b not in ids: return True
+        return ids.index(a)<ids.index(b)
+    return any(x in ids[:5] for x in q['relevant'])
+def run(**kw):
+    return {q['id']:outcome(q,[NODES[i]['id'] for i in merge(*legs4(q['query'],**kw),10)]) for q in G['queries']}
+base=run()
+print("baseline",sum(base.values()),"misses",[k for k,v in base.items() if not v])
+for name,kw in [('wordstart',dict(wordstart=True)),
+                ('unfloor',dict(unfloor=True)),
+                ('wordstart+unfloor',dict(wordstart=True,unfloor=True))]:
+    r=run(**kw)
+    g=sorted(k for k in base if r[k] and not base[k]);l=sorted(k for k in base if base[k] and not r[k])
+    print("%-20s net=%+d gains=%s losses=%s"%(name,len(g)-len(l),g,l))

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

@@ -7327,6 +7327,39 @@ static int istr_contains(const char* hay, const char* needle) {
     return 0;
 }
 
+/* Word-START-anchored variant of istr_contains.
+ *
+ * WHY. The retrieval match primitive is a raw substring test, so a query token
+ * matches ANYWHERE inside a corpus word: "throom" matches "bathroom", "cat"
+ * matches "concatenate". Measured on this corpus over the 38-query gold set,
+ * that is not a rare accident — it is the bulk of some queries' candidate
+ * sets. q28's lexical leg is 36,954 records of which only 13 contain a query
+ * token at a word start (99.96% mid-word noise); six other queries carry
+ * ~20,500 mid-word-only records each; and the nonsense control q35
+ * ("xxqzzt vurblenacht throom") returns 7 records ALL of which match only
+ * mid-word, which is the entire reason that control has been dirty since main.
+ *
+ * WHAT CHANGES. A token must begin at a word boundary — the preceding
+ * character is not alphanumeric. Suffixes are still matched ("value" still
+ * hits "values", "unjailbreakable" still hits "unjailbreakables"), so this is
+ * strictly a prefix anchor, not whole-word equality; whole-word equality would
+ * break the morphological matching the phrase category depends on.
+ *
+ * PROVENANCE, stated honestly: this restores no engram claim. Will's design
+ * has no lexical leg at all (05-detailed-description l.64 takes "one or more
+ * seed node UUIDs representing the current active context" as its input), so
+ * the lexical leg is the seed-finding step that feeds the designed mechanism.
+ * Cleaner seeds serve that mechanism; they do not replace it. */
+static int istr_contains_wordstart(const char* hay, const char* needle) {
+    if (!hay || !needle || !*needle) return 0;
+    size_t nl = strlen(needle);
+    for (const char* p = hay; *p; p++) {
+        if (p != hay && isalnum((unsigned char)p[-1])) continue;
+        if (strncasecmp(p, needle, nl) == 0) return 1;
+    }
+    return 0;
+}
+
 /* ── Tokenized query matching ───────────────────────────────────────────
  * The engram query surface (search / activate / goal-bias) historically
  * matched the ENTIRE raw query string as a single case-insensitive
@@ -7379,9 +7412,9 @@ 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(n->content, toks[t]) ||
-            istr_contains(n->label,   toks[t]) ||
-            istr_contains(n->tags,    toks[t]))
+        if (istr_contains_wordstart(n->content, toks[t]) ||
+            istr_contains_wordstart(n->label,   toks[t]) ||
+            istr_contains_wordstart(n->tags,    toks[t]))
             score++;
     }
     return score;
@@ -7396,9 +7429,9 @@ 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(n->content, toks[t]) ||
-            istr_contains(n->label,   toks[t]) ||
-            istr_contains(n->tags,    toks[t]))
+        if (istr_contains_wordstart(n->content, toks[t]) ||
+            istr_contains_wordstart(n->label,   toks[t]) ||
+            istr_contains_wordstart(n->tags,    toks[t]))
             m |= (uint32_t)1u << t;
     }
     return m;
@@ -9712,7 +9745,19 @@ el_val_t engram_search_json(el_val_t query, el_val_t limit) {
                     ? engram_assoc_leg(g, hits, nhits, semseed, nsemseed,
                                        qv, qdim, assoc, ENGRAM_ASSOC_MAX)
                     : 0;
-                int64_t* order = malloc((size_t)lim * sizeof(int64_t));
+                /* Corpus-vocabulary gate. If no stored record contains ANY
+                 * query token in its content, label or tags, the query is
+                 * outside this graph's vocabulary: there are no seeds, and
+                 * 05-detailed-description l.64 makes retrieval downstream of
+                 * seeds ("the caller provides one or more seed node UUIDs
+                 * representing the current active context"). No seeds, no
+                 * retrieval — the graph declines rather than confabulating a
+                 * nearest neighbour for gibberish. The mechanism is iteration
+                 * 6's (feat/claim24-unfloored-semantic); it is required here
+                 * because word-start matching empties the lexical leg for
+                 * q35-style queries whose only "hits" were mid-word, and the
+                 * semantic leg would otherwise answer them anyway. */
+                int64_t* order = (nhits > 0) ? malloc((size_t)lim * sizeof(int64_t)) : NULL;
                 if (order) {
                     int64_t no = engram_interleave3(hits, nhits, sem, nsem,
                                                     assoc, nassoc, lim, order);