{
  "claim_index": 2,
  "official_claim": "Test risk as a function of self-training iteration count follows a U-shaped curve, with an optimal early-stopping iteration set by the tradeoff between decaying stochastic error and accumulating systematic (signal-forgetting) error, occurring strictly under spectral anisotropy of the feature covariance (Figure 1b).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`spectral-kernel`)\n\n> Test risk as a function of self-training iteration count follows a U-shaped curve, with an optimal early-stopping iteration set by the tradeoff between decaying stochastic error and accumulating systematic (signal-for...\n\nSpectral/kernel certificate: top eigenvalues [15.0032, 14.0089, 13.1491, 12.4839, 11.5703, 10.6453], effective rank **21.01**, cond **15003232426016.86**.\n\n**Binding:** claim_sha14=`eb943c113445cd` \u00b7 ORID=`VnA5q5jXVz` \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": "VnA5q5jXVz",
    "claim_index": 2,
    "cpu_only": true,
    "domain": "spectral-kernel",
    "title_hint": "Why Self-Distillation Helps and Hurts: Denoising vs. Signal Forgetting",
    "top_eigs": [
      15.003232426016856,
      14.008931071443808,
      13.149105305497434,
      12.483933193067873,
      11.570344072589528,
      10.64526817564365,
      10.298216614063472,
      9.995750883348013
    ],
    "effective_rank": 21.014922953562643,
    "cond": 15003232426016.855,
    "claim_sha14": "eb943c113445cd",
    "claim_snippet": "Test risk as a function of self-training iteration count follows a U-shaped curve, with an optimal early-stopping iteration set by the tradeoff between decaying stochastic error and accumulating systematic (signal-for..."
  },
  "domain": "spectral-kernel",
  "orid": "VnA5q5jXVz",
  "space_id": "neonforestmist/self-training-risk-recursions-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:08:48.240906+00:00"
}