Make the catalog hash honest, share the text helpers, drop the duplicate labels

`catalog_hash` hashed the CSV and the view *names*, so replacing
`sku_l09.jpg` with a different product's packshot left the hash unchanged and
a report could claim the same catalog while every l09 decision in it had
moved. It hashes each view's bytes now.

`identity_lanes` carried its own `normalize_text` and `bigrams`, near-copies
of the ones in `rebuild_catalog` that had already drifted (the lane's table
folded ユ to itself, the catalog's did not). The lane imports the catalog's
now, so one read scores the same either way.

`evidence/image6_v2.json` was byte-identical to `eval/labels/image6.json`; the
evidence scripts and the decision document point at the canonical file and the
copy is gone. `score_crop`'s docstring now states the contract its callers
already depend on: the dict's insertion order is the lane's ranking, and
re-sorting by value names a different SKU than the lane chose.

Tests: the lane is shared by the classify pool, so a concurrent-ranking test
pins that one BFMatcher does not cross crops under eight threads.

recognization/docs/research/2026-09-28-recognition-architecture/evidence/README.md

@@ -3,16 +3,16 @@
 Read-only against product code: every script imports from `code/` and writes
 only into this folder. Run from `recognization/` with `.venv/bin/python`.
 
-`image6_v2.json` is the corrected image6 label set (26 of 111 v1 labels
+`eval/labels/image6.json` is the corrected image6 label set (26 of 111 v1 labels
 changed; every row carries `v1_label`, `source`, and a `note` where changed).
 `image6-v1-labels-overlay.jpg` shows the v1 labels on the shelf; green = catalog
 label, red = unknown. `sheet.py` regenerates per-SKU contact sheets.
 
 | Step | Command (prefix `E=docs/research/2026-09-28-recognition-architecture/evidence`) | Produces |
 |---|---|---|
-| Original matcher, both catalogs, full/live/live-with-unscaled-boxes | `.venv/bin/python $E/diag.py --stock stock-lopia-clean --labels $E/image6_v2.json [--live] [--bug] --out $E/run_stock-lopia-clean_<full\|live\|livebug>.pkl` (repeat with `--stock stock-lopia`) | `run_*.pkl` |
+| Original matcher, both catalogs, full/live/live-with-unscaled-boxes | `.venv/bin/python $E/diag.py --stock stock-lopia-clean --labels $E/../../../eval/labels/image6.json [--live] [--bug] --out $E/run_stock-lopia-clean_<full\|live\|livebug>.pkl` (repeat with `--stock stock-lopia`) | `run_*.pkl` |
 | Score them under v1 or v2 labels | `.venv/bin/python $E/analyze.py <labels.json> $E/run_*.pkl` | identity top-1, argmax, current gate |
-| Matcher variants | `.venv/bin/python $E/variants.py --stock stock-lopia-clean --labels $E/image6_v2.json [--live] --scales 200,400 --root --geom affine --out $E/v_ms_root_aff_<full\|live>.pkl` (also `--tmpl-h 250/400`, no flags = raw) | `v_*.pkl` |
+| Matcher variants | `.venv/bin/python $E/variants.py --stock stock-lopia-clean --labels $E/../../../eval/labels/image6.json [--live] --scales 200,400 --root --geom affine --out $E/v_ms_root_aff_<full\|live>.pkl` (also `--tmpl-h 250/400`, no flags = raw) | `v_*.pkl` |
 | Variant ranking + open-set frontier | `.venv/bin/python $E/an2.py $E $(basename -a $E/v_*.pkl)` (`LABELS=image6_v2_lfo.json` for the leave-facing-out runs) | correct at 100/95/90 % precision |
 | Leave-facing-out catalog | `.venv/bin/python $E/lfo_setup.py`, then `variants.py --stock $E/cat_<pack\|full> --labels $E/image6_v2_lfo.json --scales 200,400 --root --geom affine [--live] --out $E/lfo_cat_<pack\|full>_<full\|live>.pkl` | `lfo_*.pkl` |
 | Unrelated-shelf distractors | `YOLO_OFFLINE=1 .venv/bin/python $E/distract.py stock-lopia-clean $E/cat_full` | `distract.pkl` |
@@ -44,7 +44,7 @@ with no arguments raise `IndexError`; neither validates its own usage.
 v1 labels are no longer a file on disk — `eval/labels/image6.json` is the v2
 set. To score a run under v1, rebuild it from the `v1_label` field:
 
-    .venv/bin/python -c "import json;d=json.load(open('$E/image6_v2.json'));\
+    .venv/bin/python -c "import json;d=json.load(open('$E/../../../eval/labels/image6.json'));\
     [f.update(label=f.pop('v1_label')) for f in d['facings']];\
     json.dump(d,open('/tmp/image6_v1.json','w'),ensure_ascii=False)"
 

recognization/docs/research/2026-09-28-recognition-architecture/evidence/an2.py

@@ -1,5 +1,5 @@
 import pickle, json, sys, numpy as np, collections
-import os; S = sys.argv[1]; L = {f['index']: f['label'] for f in json.load(open(f'{S}/' + os.environ.get('LABELS','image6_v2.json')))['facings']}
+import os; S = sys.argv[1]; L = {f['index']: f['label'] for f in json.load(open(f'{S}/' + os.environ.get('LABELS','../../../../eval/labels/image6.json')))['facings']}
 RANK = {
  'inl': lambda e: e['inliers'],
  'inl*col': lambda e: e['inliers'] * (0.25 + e['color']),

recognization/docs/research/2026-09-28-recognition-architecture/evidence/dino_scale.py

@@ -16,7 +16,7 @@ for p in sorted(glob.glob('add/*')):
         if min(c.shape[:2])>=40: dis.append((f'd{j}_{os.path.basename(p)}',c))
 random.shuffle(dis)
 D=[(k,g.embed(c)) for k,c in dis]
-L=json.load(open(f'{S}/image6_v2.json')); E={k for k,_ in refs}
+L=json.load(open(f'{S}/../../../../eval/labels/image6.json')); E={k for k,_ in refs}
 Q=[(fc['label'],g.embed(c)) for fc,c in crops('add/image6.jpg',L,True) if fc['label'] in E]
 t=time.perf_counter(); _=g.embed(Q and dis[0][1]); print('embed ms',round((time.perf_counter()-t)*1000,1))
 for N in [0,50,200,len(D)]:

recognization/docs/research/2026-09-28-recognition-architecture/evidence/fuse_eval.py

@@ -2,7 +2,7 @@ import sys,os,json,pickle,csv,numpy as np
 S=os.path.dirname(os.path.abspath(__file__)); sys.path.insert(0,S)
 from ocr_fuse import norm,sim  # noqa (module runs OCR of packshots on import; cheap)
 sig=pickle.load(open(f'{S}/sig.pkl','rb')); O=pickle.load(open(f'{S}/ocr.pkl','rb'))
-L={f['index']:f['label'] for f in json.load(open(f'{S}/image6_v2.json'))['facings']}
+L={f['index']:f['label'] for f in json.load(open(f'{S}/../../../../eval/labels/image6.json'))['facings']}
 def conf(ev):
     r=sorted(ev.items(),key=lambda kv:-kv[1]['inliers']*(0.25+kv[1]['color']))
     (k1,e1),(k2,e2)=r[0],r[1]; i1,i2=e1['inliers'],e2['inliers']

recognization/docs/research/2026-09-28-recognition-architecture/evidence/lfo_setup.py

@@ -4,7 +4,7 @@ image6_v2_lfo.json with those reference facings excluded from scoring.
 Same-photo references make this an optimistic proxy, not a held-out result."""
 import json, cv2, os, shutil, collections
 E = os.path.dirname(os.path.abspath(__file__))
-L = json.load(open(f'{E}/image6_v2.json')); im = cv2.imread('add/image6.jpg')
+L = json.load(open(f'{E}/../../../../eval/labels/image6.json')); im = cv2.imread('add/image6.jpg')
 by = collections.defaultdict(list)
 for f in L['facings']:
     if f['label'] not in ('unknown', 'exclude'): by[f['label']].append(f)

recognization/docs/research/2026-09-28-recognition-architecture/evidence/ocr_exp.py

@@ -3,7 +3,7 @@ sys.path.insert(0,'code'); sys.path.insert(0,os.path.dirname(__file__))
 from ocr import VisionOcr
 from diag import crops
 S=os.path.dirname(__file__)
-L=json.load(open(f'{S}/image6_v2.json'))
+L=json.load(open(f'{S}/../../../../eval/labels/image6.json'))
 # distinguishing tokens per SKU (any hit counts); includes siblings for near-unknowns
 KEY={'sku_l01':['エッグケア','卵を使って'],'sku_l02':['アマニ'],'sku_l03':['からし','Spicy'],'sku_l04':['めんたい'],
 'sku_l05':['ゼロ','ノンコレ'],'sku_l06':['フィッテ','内臓脂肪'],'sku_l07':['ラッキー'],'sku_l08':['PERI','ペリ'],

recognization/docs/research/2026-09-28-recognition-architecture/evidence/scale.py

@@ -27,7 +27,7 @@ for p in sorted(glob.glob('add/*')):
         x1,y1,x2,y2=[int(v) for v in b['box']]; c=im[max(0,y1):y2,max(0,x1):x2]
         if min(c.shape[:2])>=40: dis.append((f'd_{os.path.basename(p)}_{j}',c))
 random.shuffle(dis); print('distractor refs available',len(dis))
-L=json.load(open(f'{S}/image6_v2.json')); Q=[(fc,c) for fc,c in crops('add/image6.jpg',L,True) if fc['label']!='exclude' and min(c.shape[:2])>=8]
+L=json.load(open(f'{S}/../../../../eval/labels/image6.json')); Q=[(fc,c) for fc,c in crops('add/image6.jpg',L,True) if fc['label']!='exclude' and min(c.shape[:2])>=8]
 Qf=[(fc['label'],)+feat(c,None) for fc,c in Q]
 bf=cv2.BFMatcher(cv2.NORM_L2)
 def verify(kq,dq,r):