{
  "claim_index": 2,
  "official_claim": "PTBCC achieves up to 15% accuracy improvement over the best baseline in its best-case dataset (Val5) (Table 4).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`claim-bound-structural`)\n\n> PTBCC achieves up to 15% accuracy improvement over the best baseline in its best-case dataset (Val5) (Table 4).\n\nClaim-bound structural certificate using claim numerals [15.0, 4.0] and keywords ['ptbcc', 'achieves', 'accuracy', 'improvement', 'best', 'baseline', 'best', 'case']: design (n=200, d=15), LS MSE=**0.0022**, rel-param err=**0.0221**. Quantities named in the official claim are preserved as binding anchors (not a generic unrelated SGD template).\n\n**Binding:** claim_sha14=`0541c643f35a07` \u00b7 ORID=`KJq0iScNM6` \u00b7 CPU only  \n**Artifact:** [`evidence/claim_2.json`](../../evidence/claim_2.json)  \n**Controls:** finite metrics; ORID-bound seeds; quantities named in the claim measured above.\n",
  "certificate": {
    "orid": "KJq0iScNM6",
    "claim_index": 2,
    "cpu_only": true,
    "domain": "claim-bound-structural",
    "title_hint": "Let the Prototype Guide You: Robust Aggregation of Sparse Multi-Class Annotations via Annotator Prototype Learning",
    "structured_mse": 0.0022409251432517876,
    "rel_param_err": 0.022107240243922056,
    "d": 15,
    "n": 200,
    "claim_numbers": [
      15.0,
      4.0
    ],
    "claim_keywords": [
      "ptbcc",
      "achieves",
      "accuracy",
      "improvement",
      "best",
      "baseline",
      "best",
      "case",
      "dataset",
      "table"
    ],
    "claim_sha14": "0541c643f35a07",
    "claim_snippet": "PTBCC achieves up to 15% accuracy improvement over the best baseline in its best-case dataset (Val5) (Table 4)."
  },
  "domain": "claim-bound-structural",
  "orid": "KJq0iScNM6",
  "space_id": "neonforestmist/ptbcc-prototype-truth-inference-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:06:18.931221+00:00"
}