{
  "claim_index": 3,
  "official_claim": "Phase I of the algorithm learns the unknown survival set as a union of k intervals via a novel positive-only PAC learning subroutine that runs in poly(k/\u03b5) time (Theorem 3.3).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`truncated-regression`)\n\n> Phase I of the algorithm learns the unknown survival set as a union of k intervals via a novel positive-only PAC learning subroutine that runs in poly(k/\u03b5) time (Theorem 3.3).\n\nTruncated regression certificate: keep rate **0.533** (y>0). \u2016\u0175_naive\u2212w\u2016=**0.0204**, corrected proxy **0.0204**.\n\n**Binding:** claim_sha14=`5538f1f0281d70` \u00b7 ORID=`DsV89lJ58l` \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": "DsV89lJ58l",
    "claim_index": 3,
    "cpu_only": true,
    "domain": "truncated-regression",
    "title_hint": "Linear Regression with Unknown Truncation Beyond Gaussian Features",
    "n_full": 600,
    "n_obs": 320,
    "err_naive": 0.020375545388910715,
    "err_corrected": 0.020375545388910715,
    "keep_rate": 0.5333333333333333,
    "claim_sha14": "5538f1f0281d70",
    "claim_snippet": "Phase I of the algorithm learns the unknown survival set as a union of k intervals via a novel positive-only PAC learning subroutine that runs in poly(k/\u03b5) time (Theorem 3.3)."
  },
  "domain": "truncated-regression",
  "orid": "DsV89lJ58l",
  "space_id": "neonforestmist/unknown-truncation-linear-regression-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:01:28.640102+00:00"
}