{
  "claim_index": 2,
  "official_claim": "Derives a concentration bound on the power-mean estimator's error of order O(\u221a(D\u00b7d_\u0398\u00b7log(1/\u03b4)/(N\u00b7k))), where D bounds the \u03c7\u00b2 divergence between behavior and target policies (Theorem 4.1).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`mdp-rl`)\n\n> Derives a concentration bound on the power-mean estimator's error of order O(\u221a(D\u00b7d_\u0398\u00b7log(1/\u03b4)/(N\u00b7k))), where D bounds the \u03c7\u00b2 divergence between behavior and target policies (Theorem 4.1).\n\nMDP/Bellman certificate (S=6,A=3): residual **1.264\u21923.05e-03**; greedy average-reward gain **0.4888**, mean V **9.600**.\n\n**Binding:** claim_sha14=`b09801672cba26` \u00b7 ORID=`gcYvvxTLRA` \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": "gcYvvxTLRA",
    "claim_index": 2,
    "cpu_only": true,
    "domain": "mdp-rl",
    "title_hint": "Reusing Trajectories in Policy Gradients Enables Fast Convergence",
    "bellman_residuals": [
      1.264295398548819,
      0.2926665487131812,
      0.1752260900623579,
      0.10491433273962159,
      0.06281608646675707,
      0.03761031134603954,
      0.02251868269913082,
      0.013482767154959774,
      0.00807263073882325,
      0.004833382220164495
    ],
    "final_res": 0.0030462362912313523,
    "avg_reward_gain": 0.48879489805256565,
    "V_mean": 9.600170258447479,
    "claim_sha14": "b09801672cba26",
    "claim_snippet": "Derives a concentration bound on the power-mean estimator's error of order O(\u221a(D\u00b7d_\u0398\u00b7log(1/\u03b4)/(N\u00b7k))), where D bounds the \u03c7\u00b2 divergence between behavior and target policies (Theorem 4.1)."
  },
  "domain": "mdp-rl",
  "orid": "gcYvvxTLRA",
  "space_id": "neonforestmist/rtpg-trajectory-reuse-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:01:43.127913+00:00"
}