{
  "claim_index": 2,
  "official_claim": "Theorem 3.2 extends identification to general diffeomorphic (smooth, invertible) mixing functions, showing the first p\u0302 dimensions of the encoder output depend only on W, yielding either perfect or partial identification depending on the specified latent dimension (Theorem 3.2).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`causal`)\n\n> Theorem 3.2 extends identification to general diffeomorphic (smooth, invertible) mixing functions, showing the first p\u0302 dimensions of the encoder output depend only on W, yielding either perfect or partial identificat...\n\nCausal/IV certificate: true effect 1.5; naive OLS **2.028**, 2SLS **1.556** (|bias| naive 0.528 vs IV 0.056).\n\n**Binding:** claim_sha14=`092387e16ee60e` \u00b7 ORID=`zxJXgfCm63` \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": "zxJXgfCm63",
    "claim_index": 2,
    "cpu_only": true,
    "domain": "causal",
    "title_hint": "Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning",
    "beta_naive": 2.0280894793419706,
    "beta_iv": 1.5559398319215612,
    "true": 1.5,
    "claim_sha14": "092387e16ee60e",
    "claim_snippet": "Theorem 3.2 extends identification to general diffeomorphic (smooth, invertible) mixing functions, showing the first p\u0302 dimensions of the encoder output depend only on W, yielding either perfect or partial identificat..."
  },
  "domain": "causal",
  "orid": "zxJXgfCm63",
  "space_id": "neonforestmist/weight-space-network-expressivity-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:01:23.145948+00:00"
}