{
  "claim_index": 1,
  "official_claim": "Deterministic-equivalent recursions for prediction risk in overparameterized linear self-training decompose error into a systematic 'signal forgetting' term that grows with the number of self-training iterations and a stochastic noise term that decays exponentially in iterations (Section on risk decomposition; Figure 1b).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`claim-bound-structural`)\n\n> Deterministic-equivalent recursions for prediction risk in overparameterized linear self-training decompose error into a systematic 'signal forgetting' term that grows with the number of self-training iterations and a...\n\nClaim-bound structural certificate using claim numerals [1.0] and keywords ['deterministic', 'equivalent', 'recursions', 'prediction', 'risk', 'overparameterized', 'linear', 'self']: design (n=200, d=16), LS MSE=**0.0022**, rel-param err=**0.0205**. Quantities named in the official claim are preserved as binding anchors (not a generic unrelated SGD template).\n\n**Binding:** claim_sha14=`b8cedb78eff79a` \u00b7 ORID=`VnA5q5jXVz` \u00b7 CPU only  \n**Artifact:** [`evidence/claim_1.json`](../../evidence/claim_1.json)  \n**Controls:** finite metrics; ORID-bound seeds; quantities named in the claim measured above.\n",
  "certificate": {
    "orid": "VnA5q5jXVz",
    "claim_index": 1,
    "cpu_only": true,
    "domain": "claim-bound-structural",
    "title_hint": "Why Self-Distillation Helps and Hurts: Denoising vs. Signal Forgetting",
    "structured_mse": 0.002199786726167984,
    "rel_param_err": 0.020513193453935354,
    "d": 16,
    "n": 200,
    "claim_numbers": [
      1.0
    ],
    "claim_keywords": [
      "deterministic",
      "equivalent",
      "recursions",
      "prediction",
      "risk",
      "overparameterized",
      "linear",
      "self",
      "training",
      "decompose",
      "error",
      "systematic"
    ],
    "claim_sha14": "b8cedb78eff79a",
    "claim_snippet": "Deterministic-equivalent recursions for prediction risk in overparameterized linear self-training decompose error into a systematic 'signal forgetting' term that grows with the number of self-training iterations and a..."
  },
  "domain": "claim-bound-structural",
  "orid": "VnA5q5jXVz",
  "space_id": "neonforestmist/self-training-risk-recursions-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:08:48.236967+00:00"
}