chore(eval): reconcile the distractor sets and refresh the sweep numbers

The Wikimedia collector truncated the whole basename at 60 characters, so 13
files lost their extension and cv2 could not read them by name - the distractor
sets were quietly scoring 13 images fewer than they held. It now truncates the
stem and keeps the extension, and the files on disk are renamed to match.

The search terms also pull in .djvu volumes whose page 1 Commons serves as a
JPEG thumbnail. Twelve book scans were in the sets; they contributed 0 false
accepts, and they are not shelves, so the collector filters them and the
manifests no longer list them.

With all 2650 crops readable the sweep is re-measured end to end: 3.09% at the
old lines, 0.30% at the shipped 4.0/4, image6 44 shown / 42 correct / 95.5%.
The accept sweep table and the verdict's far-unknown sentence now carry those
numbers instead of the pre-calibration ones.

Also: the fetched images are gitignored (manifests and results are not), the
l10/l11 shelf-tag crops that back the catalog corrections are committed, and a
stale pre-gate eval.json and a duplicate of eval/labels/image6.json are gone.

recognization/data/evaluations/2026-09-29-session/catalog-audit/enroll-2026-09-29.json

@@ -0,0 +1,76 @@
+{
+ "source": "data/packshots/source",
+ "output": "stock-lopia-clean",
+ "min_width": 120,
+ "min_height": 160,
+ "min_views": 1,
+ "duplicate_cosine": 0.98,
+ "min_name_ocr": 0.7,
+ "ocr": "vision",
+ "text_only_skus": [
+  "sku_l04",
+  "sku_l07",
+  "sku_l08",
+  "sku_l12"
+ ],
+ "text_discriminated_siblings": [
+  {
+   "sku": "sku_l09",
+   "view": "sku_l09.jpg",
+   "sibling_sku": "sku_l10",
+   "sibling_view": "sku_l10.jpg",
+   "cosine": 0.9817,
+   "name_similarity": 0.333
+  }
+ ],
+ "below_pyramid_floor": [],
+ "completeness": {
+  "live_ready": null,
+  "reason": "no --shelf-tags given; the completeness rule needs the shelf's SKU list",
+  "enrolled": 8,
+  "text_only": [
+   "sku_l04",
+   "sku_l07",
+   "sku_l08",
+   "sku_l12"
+  ]
+ },
+ "skus": {
+  "sku_l01": [
+   "sku_l01.jpg"
+  ],
+  "sku_l02": [
+   "sku_l02.jpg"
+  ],
+  "sku_l03": [
+   "sku_l03.jpg"
+  ],
+  "sku_l05": [
+   "sku_l05.jpg"
+  ],
+  "sku_l06": [
+   "sku_l06.jpg"
+  ],
+  "sku_l09": [
+   "sku_l09.jpg"
+  ],
+  "sku_l10": [
+   "sku_l10.jpg"
+  ],
+  "sku_l11": [
+   "sku_l11.jpg"
+  ]
+ },
+ "refused": [
+  {
+   "sku": "sku_l04",
+   "view": "sku_l04.jpg",
+   "reason": "name/OCR 0.00 below 0.70: 明太手屋さんが つくつ た コ"
+  },
+  {
+   "sku": "sku_l07",
+   "view": "sku_l07.jpg",
+   "reason": "name/OCR 0.57 below 0.70: ラッキー マヨネーズ 調味料（アミノ酸）不使用"
+  }
+ ]
+}

recognization/data/evaluations/2026-09-29-session/catalog-audit/eval-after-l10.json

@@ -0,0 +1,221 @@
+{
+ "image": "add/image6.jpg",
+ "stock_dir": "stock-lopia-clean",
+ "labels": "eval/labels/image6.json",
+ "provenance": {
+  "catalog_hash": "3f1653d9d962073af96121250006b9b6d86113556797bbee65de68b60e87a64d",
+  "labels_hash": "5aabf029921ced767d4e14a18e8bccb55812dd974852c56e0931a98fa10366cf",
+  "image_hash": "a08b89ba37d27c9d5a81bcd56bcd042e6baf54d2f182bbaaf47e97f14c9cd525",
+  "code_revision": "68061635d9fef3097609945bfd9ac1935791b398"
+ },
+ "facings": 111,
+ "leakage": {
+  "excluded": 0,
+  "labels": []
+ },
+ "hub_share_limit": 0.3,
+ "enrollment": {
+  "catalog_skus": [
+   "sku_l01",
+   "sku_l02",
+   "sku_l03",
+   "sku_l04",
+   "sku_l05",
+   "sku_l06",
+   "sku_l07",
+   "sku_l08",
+   "sku_l09",
+   "sku_l10",
+   "sku_l11",
+   "sku_l12"
+  ],
+  "enrolled_skus": [
+   "sku_l01",
+   "sku_l02",
+   "sku_l03",
+   "sku_l05",
+   "sku_l06",
+   "sku_l09",
+   "sku_l10",
+   "sku_l11"
+  ],
+  "unenrolled_skus": {
+   "sku_l07": 6,
+   "sku_l04": 1,
+   "sku_l08": 1
+  },
+  "facings_without_enrollment": 8,
+  "scored_facings": 109
+ },
+ "results": {
+  "full": [
+   {
+    "lane": "local",
+    "accept": 2.0,
+    "margin": 0.15,
+    "in_catalog": 61,
+    "out_catalog": 48,
+    "enrolled": 53,
+    "correct": 48,
+    "wrong": 9,
+    "rejected": 52,
+    "catalog_ceiling": 0.8689,
+    "identity_ceiling": 0.9245,
+    "decision_ceiling": 0.8113,
+    "end_to_end_coverage": 0.7869,
+    "false_accepts": 9,
+    "unknown_false_accepts": 8,
+    "unenrolled_false_accepts": 0,
+    "false_accept_rate": 0.1667,
+    "near_unknown_false_accept_rate": 0.0,
+    "precision": 0.8421,
+    "max_sku_share": 0.2281,
+    "hub_sku": "sku_l09",
+    "hub_alarm": false,
+    "histogram": {
+     "sku_l09": 13,
+     "sku_l11": 10,
+     "sku_l10": 9,
+     "sku_l01": 5,
+     "sku_l03": 5,
+     "sku_l07": 5,
+     "sku_l06": 4,
+     "sku_l02": 3,
+     "sku_l05": 3
+    },
+    "per_sku": {
+     "sku_l01": {
+      "correct": 5,
+      "total": 5
+     },
+     "sku_l02": {
+      "correct": 2,
+      "total": 4
+     },
+     "sku_l03": {
+      "correct": 4,
+      "total": 4
+     },
+     "sku_l04": {
+      "correct": 0,
+      "total": 1
+     },
+     "sku_l05": {
+      "correct": 3,
+      "total": 3
+     },
+     "sku_l06": {
+      "correct": 4,
+      "total": 4
+     },
+     "sku_l07": {
+      "correct": 5,
+      "total": 6
+     },
+     "sku_l08": {
+      "correct": 0,
+      "total": 1
+     },
+     "sku_l09": {
+      "correct": 11,
+      "total": 13
+     },
+     "sku_l10": {
+      "correct": 9,
+      "total": 11
+     },
+     "sku_l11": {
+      "correct": 5,
+      "total": 9
+     }
+    },
+    "ms_per_crop": 26.7
+   }
+  ],
+  "live": [
+   {
+    "lane": "local",
+    "accept": 2.0,
+    "margin": 0.15,
+    "in_catalog": 61,
+    "out_catalog": 48,
+    "enrolled": 53,
+    "correct": 41,
+    "wrong": 4,
+    "rejected": 64,
+    "catalog_ceiling": 0.8689,
+    "identity_ceiling": 0.8491,
+    "decision_ceiling": 0.6604,
+    "end_to_end_coverage": 0.6721,
+    "false_accepts": 4,
+    "unknown_false_accepts": 3,
+    "unenrolled_false_accepts": 0,
+    "false_accept_rate": 0.0625,
+    "near_unknown_false_accept_rate": 0.0,
+    "precision": 0.9111,
+    "max_sku_share": 0.2,
+    "hub_sku": "sku_l09",
+    "hub_alarm": false,
+    "histogram": {
+     "sku_l09": 9,
+     "sku_l10": 9,
+     "sku_l11": 7,
+     "sku_l07": 6,
+     "sku_l01": 4,
+     "sku_l03": 3,
+     "sku_l05": 3,
+     "sku_l06": 2,
+     "sku_l02": 1,
+     "sku_l04": 1
+    },
+    "per_sku": {
+     "sku_l01": {
+      "correct": 4,
+      "total": 5
+     },
+     "sku_l02": {
+      "correct": 1,
+      "total": 4
+     },
+     "sku_l03": {
+      "correct": 3,
+      "total": 4
+     },
+     "sku_l04": {
+      "correct": 1,
+      "total": 1
+     },
+     "sku_l05": {
+      "correct": 3,
+      "total": 3
+     },
+     "sku_l06": {
+      "correct": 2,
+      "total": 4
+     },
+     "sku_l07": {
+      "correct": 5,
+      "total": 6
+     },
+     "sku_l08": {
+      "correct": 0,
+      "total": 1
+     },
+     "sku_l09": {
+      "correct": 9,
+      "total": 13
+     },
+     "sku_l10": {
+      "correct": 9,
+      "total": 11
+     },
+     "sku_l11": {
+      "correct": 4,
+      "total": 9
+     }
+    },
+    "ms_per_crop": 20.9
+   }
+  ]
+ }
+}

recognization/data/evaluations/2026-09-29-session/scratch/fa_detail.py

@@ -0,0 +1,27 @@
+"""Which facings are falsely accepted, and as what."""
+import sys, cv2
+sys.path.insert(0, "code")
+from eval_identity import LocalLaneAdapter, load_labels, at_live_resolution, leaked, UNKNOWN, crop_of
+from identity_lanes import DecisionPolicy
+
+payload = load_labels("eval/labels/image6.json")
+image = cv2.imread("add/image6.jpg")
+facings = [f for f in payload["facings"] if f["label"] != "exclude"]
+facings = [f for f in facings if leaked(image, f["box"], "stock-lopia-clean") is None]
+enrolled = {"sku_l01","sku_l02","sku_l03","sku_l05","sku_l06","sku_l09","sku_l10","sku_l11"}
+
+for live in (False, True):
+    picture = at_live_resolution(image) if live else image
+    scaled = facings if not live else [
+        {**f, "box": [int(round(v * picture.shape[1] / image.shape[1])) for v in f["box"]]}
+        for f in facings]
+    lane = LocalLaneAdapter("stock-lopia-clean")
+    print(f"=== {'live' if live else 'full'} ===")
+    for f in scaled:
+        crop = crop_of(picture, f["box"])
+        if crop.size == 0: continue
+        ranked = lane.rank(crop)
+        d = lane.decide(crop, ranked, accept=2.0, margin=0.0, scale="local")
+        ans = d.get("best_sku") if d.get("identity_level") == "accepted" else None
+        if ans and ans != f["label"]:
+            print(f"  #{f['index']:>3} truth={f['label']:<9} answered={ans:<9} enrolled={f['label'] in enrolled}")

recognization/data/evaluations/2026-09-29-session/scratch/fa_text.py

@@ -0,0 +1,54 @@
+"""What the falsely-accepted crops actually read, and what the text lane scores.
+
+The advisory says crops 82-97 are Kewpie Mayonnaise 450g - a product the
+catalog does not hold - and that no catalog row can therefore win the text
+ranking, so the veto at DecisionPolicy.decide never fires. This prints the
+reads and the scores that claim depends on.
+"""
+import csv
+import sys
+
+import cv2
+import numpy as np
+
+sys.path.insert(0, "code")
+from identity_lanes import TextLane, carries_identity  # noqa: E402
+from ocr import build_ocr_engine  # noqa: E402
+
+INDICES = [73, 82, 83, 84, 86, 94, 95, 96, 97]
+
+rows = []
+with open("stock-lopia-clean/stock.csv", encoding="utf-8") as handle:
+    for record in csv.reader(handle):
+        if len(record) >= 2 and record[0].startswith("sku_"):
+            rows.append({"sku_id": record[0], "product_name": record[1]})
+
+engine = build_ocr_engine("vision")
+lane = TextLane.from_catalog(rows, "stock-lopia-clean", ocr_engine=engine)
+
+labels = {f["index"]: f for f in __import__("json").load(open("eval/labels/image6.json"))["facings"]}
+image = cv2.imread("add/image6.jpg")
+
+tiles = []
+for index in INDICES:
+    facing = labels[index]
+    x1, y1, x2, y2 = facing["box"]
+    crop = image[y1:y2, x1:x2]
+    read = lane.read(crop)
+    scores = lane.scores_from_text(read)
+    top = sorted(scores.items(), key=lambda kv: -kv[1])[:3]
+    print(f"#{index:>3} truth={facing['label']:<9} carries={carries_identity(read)}")
+    print(f"      read: {read[:110]}")
+    print(f"      text top: {[(s, round(v, 3)) for s, v in top]}")
+
+    height, width = crop.shape[:2]
+    scale = 260.0 / max(1, height)
+    resized = cv2.resize(crop, (max(1, int(width * scale)), 260), interpolation=cv2.INTER_CUBIC)
+    canvas = np.full((300, 220, 3), 255, np.uint8)
+    canvas[30:290, : min(resized.shape[1], 220)] = resized[:, :220]
+    cv2.putText(canvas, str(index), (6, 22), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
+    tiles.append(canvas)
+
+grid = np.vstack([np.hstack(tiles[:5]), np.hstack(tiles[5:])])
+cv2.imwrite("data/evaluations/2026-09-29-session/scratch/fa_tiles.jpg", grid)
+print("tile:", grid.shape)

recognization/data/evaluations/2026-09-29-session/scratch/size_gate.py

@@ -0,0 +1,71 @@
+"""Mass-only size contradiction, with full reads.
+
+The first pass counted every quantity token, including percentages, so a crop
+reading "カロリー 50% カット" looked like a 50 g package. Only mass units can
+contradict a package size, so this restricts to g/kg and prints the whole read
+for every accepted facing that carries one.
+"""
+import csv
+import json
+import re
+import sys
+
+import cv2
+
+sys.path.insert(0, "code")
+from eval_identity import LocalLaneAdapter, at_live_resolution, crop_of, leaked  # noqa: E402
+from identity_lanes import TextLane, normalize_text  # noqa: E402
+from ocr import build_ocr_engine  # noqa: E402
+
+MASS = re.compile(r"(\d+(?:\.\d+)?)\s*(KG|G)", re.IGNORECASE)
+# Package sizes this product class actually comes in. Below it are OCR fragments
+# of a longer number ("20" from 200); above it are concatenations ("5210").
+PLAUSIBLE = (100.0, 2000.0)
+
+
+def masses(text: str):
+    return {float(number) for number, _unit in MASS.findall(normalize_text(text))}
+
+
+rows = []
+with open("stock-lopia-clean/stock.csv", encoding="utf-8") as handle:
+    for record in csv.reader(handle):
+        if len(record) >= 2 and record[0].startswith("sku_"):
+            rows.append({"sku_id": record[0], "product_name": record[1]})
+names = {row["sku_id"]: row["product_name"] for row in rows}
+
+engine = build_ocr_engine("vision")
+text_lane = TextLane.from_catalog(rows, "stock-lopia-clean", ocr_engine=engine)
+local_lane = LocalLaneAdapter("stock-lopia-clean")
+
+payload = json.load(open("eval/labels/image6.json"))
+image = cv2.imread("add/image6.jpg")
+facings = [f for f in payload["facings"] if f["label"] != "exclude"]
+facings = [f for f in facings if leaked(image, f["box"], "stock-lopia-clean") is None]
+
+for live in (False, True):
+    picture = at_live_resolution(image) if live else image
+    scaled = facings if not live else [
+        {**f, "box": [int(round(v * picture.shape[1] / image.shape[1])) for v in f["box"]]}
+        for f in facings]
+    print(f"=== {'live' if live else 'full'} ===")
+    for facing in scaled:
+        crop = crop_of(picture, facing["box"])
+        if crop.size == 0:
+            continue
+        ranked = local_lane.rank(crop)
+        decision = local_lane.decide(crop, ranked, accept=2.0, margin=0.0, scale="local")
+        if decision.get("identity_level") != "accepted":
+            continue
+        answer = decision.get("best_sku")
+        read = text_lane.read(crop)
+        read_masses = masses(read)
+        name_masses = masses(names.get(answer, ""))
+        if not read_masses or not name_masses:
+            continue
+        plausible = {m for m in read_masses if PLAUSIBLE[0] <= m <= PLAUSIBLE[1]}
+        veto = bool(plausible) and not (read_masses & name_masses)
+        correct = "correct" if answer == facing["label"] else "WRONG"
+        print(f"  #{facing['index']:>3} {'VETO' if veto else 'keep'} {correct:<7} "
+              f"answer={answer:<9} read_m={sorted(read_masses)} name_m={sorted(name_masses)}")
+        print(f"        read: {read[:120]}")