{
  "scope": "Research prototypes only; production files unchanged",
  "baseline_revision": "fbf31d74feb12538dc07207cb80722dac38dd438",
  "primary_data": "eval/labels/image6.json",
  "catalog": "stock-lopia-clean",
  "data_status": "Single development photo, previously tuned. No cross-visit generalization claim.",
  "controls": ["Freeze catalog and labels; hash inputs", "Extract evidence once, replay identical evidence across policies", "Inference receives boxes and observations, never identity ground truth", "Oracle arm alone receives true group membership", "Unknown is not a SKU: never merge unknowns merely because labels equal", "Report labels over all 109 facings and correct labels over all 64 catalog facings separately", "Keep geometry-derived rows fixed across methods", "Compare deterministic runs to chain dynamic programming", "Report group rescue, correction and damage separately", "Separate measured wall time from cached-evidence simulations", "Never call a synthetic pan a recorded walk", "Use paced video timestamps, not result-synchronous sends, for full-rate replay"],
  "hypotheses": {
    "A": "Color plus normalized appearance and local correspondences separate repeated facings better than either alone; brand siblings remain difficult.",
    "B": "Geometry-only rows plus appearance-supported run edges identify repeats without truth labels; leave-one-row-out calibration limits same-row tuning.",
    "C": "Perfect membership sharing observed strong member evidence recovers at least 5 percentage points of catalog-facing correct coverage. No oracle SKU assignment.",
    "D": "Inferred group recovery retains useful oracle gain without more than one damaged originally correct facing; measure rather than require a positive result.",
    "E": "Visual-first scheduling and selective group representative OCR reduce actual OCR calls and make first evidence available sooner; never infer speed from call counts alone.",
    "F": "Coverage-first has greater product utility than strict even with lower shown-label precision. Near-argmax is a measured stress point, not the presumed winner.",
    "G": "Independent frame pacing exposes queue churn that the existing send/result client cannot test because both wait for every result. Compare identical source frame sequences at native sample pacing and 0.5x."
  },
  "policies": {"strict":4.0,"balanced":2.0,"coverage-first":0.5,"near-argmax":0.0},
  "confirmation": "Strict production decision is strong evidence, not calibrated probability. All extra identities provisional.",
  "utility_costs_per_facing_second": {"blank":1.0,"wrong_sibling_provisional":1.5,"wrong_other_provisional":4.0,"wrong_confirmed":8.0,"correct":0.0,"flip_event":0.2},
  "utility_sensitivity": "Sweep wrong-label cost; no empirical user-cost calibration claimed",
  "required_outputs": ["raw per-facing and per-pair evidence", "boundary/group confusion counts", "policy frontier plot", "OCR arm costs", "per-frame live timelines", "latency p50/p95 and CPU", "decision A-H with limitations and implementation acceptance"]
}