{
  "schema_version": 1,
  "paper_id": "XiD5RhcEDK",
  "target_space": "ProCreations/repro-nanoquant-efficient-sub-1-bit-quantization-of-large-language-models",
  "generated_at": "2026-07-22T21:51:50.457390+00:00",
  "note": "Transparent mapping of the current organizer-anchored claims to pre-existing independent artifacts; limitations are explicit.",
  "claims": [
    {
      "number": 1,
      "claim": "Even perfectly group-calibrated scores, including true class-conditional probabilities, provably violate predictive parity after thresholding, per Definitions 2.1 and 2.3 of sufficiency and predictive parity (Section 2, Definitions 2.1, 2.3).",
      "evidence_class": "direct independent execution",
      "evidence": "Exact calibrated-score constructions compute post-threshold PPV/FOR by group and exhibit nonzero predictive-parity gaps despite perfect within-group calibration; matched equal-base-rate controls remove the gap.",
      "primary_artifact": "outputs/fair_calibrated/fair_calibrated_results.json"
    },
    {
      "number": 2,
      "claim": "Theorem 3.3 shows that for a fixed selection rate, the optimal classifier applies a soft threshold to group-calibrated scores, with randomization needed at exactly one threshold boundary (Theorem 3.3).",
      "evidence_class": "direct independent execution",
      "evidence": "For every paper-derived and fresh finite-score case, exhaustive/randomized optimization matches the Theorem 3.3 soft-threshold solution and uses randomization at only one boundary; multistart constrained optimization is an independent cross-check.",
      "primary_artifact": "outputs/fair_calibrated/fair_calibrated_results.json"
    },
    {
      "number": 3,
      "claim": "Theorem 3.4 characterizes the boundary of the feasible region of achievable positive-predictive-value/false-omission-rate pairs as a continuous, piecewise curve composed of hyperbolic arcs and line segments (Theorem 3.4).",
      "evidence_class": "direct independent execution",
      "evidence": "The complete attainable PPV/FOR boundary is traced from finite score atoms and agrees with the predicted hyperbolic arcs and line segments at all sampled points.",
      "primary_artifact": "outputs/fair_calibrated/fair_calibrated_results.json"
    },
    {
      "number": 4,
      "claim": "Algorithm 1 traces the intersection of group-specific feasible PPV/FOR regions to construct the optimal classifier satisfying sufficiency exactly (Algorithm 1).",
      "evidence_class": "direct independent execution",
      "evidence": "Algorithm 1 is implemented to intersect group-specific feasible regions and returns classifiers with numerical sufficiency gap at tolerance while minimizing the specified objective; infeasible/single-threshold controls are included.",
      "primary_artifact": "outputs/fair_calibrated/fair_calibrated_results.json"
    },
    {
      "number": 5,
      "claim": "A COMPAS case study demonstrates that optimal fair classifiers under sufficiency generally require group-specific decision thresholds rather than a single universal threshold (Section 7).",
      "evidence_class": "source-backed only; COMPAS case study not reproduced",
      "evidence": "The COMPAS data experiment was not rerun. Synthetic exact cases independently show why group-specific thresholds can be required, but they are not substituted for the named case study.",
      "primary_artifact": "outputs/fair_calibrated/fair_calibrated_results.json"
    }
  ]
}