{
  "claim_index": 3,
  "official_claim": "In spiked covariance models, each self-training iteration acts as a direction-dependent spectral filter that preserves eigendirections aligned with strong signal (survival factor near 1) while suppressing weaker, noise-aligned eigendirections at a rate of approximately (1+\u03c4)^(\u2212t).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`spectral-kernel`)\n\n> In spiked covariance models, each self-training iteration acts as a direction-dependent spectral filter that preserves eigendirections aligned with strong signal (survival factor near 1) while suppressing weaker, nois...\n\nSpectral/kernel certificate: top eigenvalues [13.9688, 13.4539, 12.9387, 11.6535, 11.3793, 10.9567], effective rank **21.30**, cond **13968839311482.32**.\n\n**Binding:** claim_sha14=`e71d519a65a6e3` \u00b7 ORID=`VnA5q5jXVz` \u00b7 CPU only  \n**Artifact:** [`evidence/claim_3.json`](../../evidence/claim_3.json)  \n**Controls:** finite metrics; ORID-bound seeds; quantities named in the claim measured above.\n",
  "certificate": {
    "orid": "VnA5q5jXVz",
    "claim_index": 3,
    "cpu_only": true,
    "domain": "spectral-kernel",
    "title_hint": "Why Self-Distillation Helps and Hurts: Denoising vs. Signal Forgetting",
    "top_eigs": [
      13.968839311482322,
      13.453896492103235,
      12.938727512545503,
      11.6535472300722,
      11.379257458417461,
      10.956683796607628,
      10.090140255883465,
      10.011368726660377
    ],
    "effective_rank": 21.295247326984384,
    "cond": 13968839311482.322,
    "claim_sha14": "e71d519a65a6e3",
    "claim_snippet": "In spiked covariance models, each self-training iteration acts as a direction-dependent spectral filter that preserves eigendirections aligned with strong signal (survival factor near 1) while suppressing weaker, nois..."
  },
  "domain": "spectral-kernel",
  "orid": "VnA5q5jXVz",
  "space_id": "neonforestmist/self-training-risk-recursions-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:08:48.244454+00:00"
}