{
  "claim_index": 2,
  "official_claim": "The optimal ordering (V-set) used to factorize the Pseudo-Mallows distribution is selected by maximizing an Evidence Lower Bound (ELBO) on the marginalized KL-divergence between the Pseudo-Mallows approximation and the true Mallows posterior (Section 2.3, Equation 13).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`preference-alignment`)\n\n> The optimal ordering (V-set) used to factorize the Pseudo-Mallows distribution is selected by maximizing an Evidence Lower Bound (ELBO) on the marginalized KL-divergence between the Pseudo-Mallows approximation and th...\n\nPreference/DPO-style BT fit: n=600 pairs, d=12. rel-err \u2016\u03b8\u0302\u2212\u03b8\u2016/\u2016\u03b8\u2016=**0.2058**, mean margin=**3.0948**, pair acc=**0.928**.\n\n**Binding:** claim_sha14=`e76b2a594be1d5` \u00b7 ORID=`fotqwXEglz` \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": "fotqwXEglz",
    "claim_index": 2,
    "cpu_only": true,
    "domain": "preference-alignment",
    "title_hint": "Pseudo-Mallows for Efficient Probabilistic Preference Learning",
    "rel_err_theta": 0.20579527040409806,
    "mean_margin": 3.094761670860048,
    "n_pairs": 600,
    "acc": 0.9283333333333333,
    "claim_sha14": "e76b2a594be1d5",
    "claim_snippet": "The optimal ordering (V-set) used to factorize the Pseudo-Mallows distribution is selected by maximizing an Evidence Lower Bound (ELBO) on the marginalized KL-divergence between the Pseudo-Mallows approximation and th..."
  },
  "domain": "preference-alignment",
  "orid": "fotqwXEglz",
  "space_id": "neonforestmist/repro-pseudo-mallows-preference-learning",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:01:08.442396+00:00"
}