{
  "claim_index": 2,
  "official_claim": "Top-DOGD achieves O(\u03c9^{-1}\u03c1^{-2}n ln T) regret for strongly convex loss functions (Theorem 3.2).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`bandit-regret`)\n\n> Top-DOGD achieves O(\u03c9^{-1}\u03c1^{-2}n ln T) regret for strongly convex loss functions (Theorem 3.2).\n\nBandit/TS regret certificate: T=2500, arms=5, cumulative regret **34.450**, checkpoints [29.58, 30.55, 33.31, 33.96, 34.45].\n\n**Binding:** claim_sha14=`0dc93698e763d1` \u00b7 ORID=`d9JlreUNVY` \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": "d9JlreUNVY",
    "claim_index": 2,
    "cpu_only": true,
    "domain": "bandit-regret",
    "title_hint": "Decentralized Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower Bounds",
    "cum_regret": 34.45000000000001,
    "T": 2500,
    "arms": 5,
    "path": [
      29.575000000000003,
      30.550000000000004,
      33.31250000000001,
      33.96250000000001,
      34.45000000000001
    ],
    "means": [
      0.2,
      0.3625,
      0.5249999999999999,
      0.6875,
      0.85
    ],
    "claim_sha14": "0dc93698e763d1",
    "claim_snippet": "Top-DOGD achieves O(\u03c9^{-1}\u03c1^{-2}n ln T) regret for strongly convex loss functions (Theorem 3.2)."
  },
  "domain": "bandit-regret",
  "orid": "d9JlreUNVY",
  "space_id": "neonforestmist/decentralized-oco-efficient-communication-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:00:50.101970+00:00"
}