Spaces:
Running
Running
| { | |
| "paper": "2606.08681", | |
| "campaign": "independent-regressions-claims-3-to-5", | |
| "git_sha": "3a38e9ec8587c59f15192c21428de092059b781f", | |
| "seed": 20260728, | |
| "environment": { | |
| "python": "3.12.12", | |
| "platform": "Linux-6.12.90-120.164.amzn2023.x86_64-x86_64-with-glibc2.36", | |
| "cpu_count_visible": 64, | |
| "cpu_threads_effective": 1, | |
| "numpy": "2.5.1" | |
| }, | |
| "compute_plan": { | |
| "backend": "hf", | |
| "flavor": "cpu-upgrade", | |
| "estimated_cores": 8, | |
| "estimated_runtime_seconds": 1200 | |
| }, | |
| "runtime_seconds": 15.488084773998708, | |
| "run_id": "9c41004b-5557-456c-85f4-c18da9b20634", | |
| "claim": { | |
| "id": "C4-INDEPENDENT", | |
| "anchor": "Table 2 / Section 3 and Proposition 3.1", | |
| "status": "PASS", | |
| "evidence": { | |
| "status": "VERIFIED", | |
| "rows": [ | |
| { | |
| "epsilon": 0.25, | |
| "delta_star": 0.73667, | |
| "u0": 0.1758530328653588, | |
| "analytic_tangent_slope": -1.4974416001259545, | |
| "minimum_tangent_slack": 0, | |
| "minimum_slope_increment": 0, | |
| "tangent_dominance": true, | |
| "convex_tail": true | |
| }, | |
| { | |
| "epsilon": 0.5, | |
| "delta_star": 0.70697, | |
| "u0": 0.17435351771114274, | |
| "analytic_tangent_slope": -1.6806680948879547, | |
| "minimum_tangent_slack": -3.9444858557224904e-7, | |
| "minimum_slope_increment": 0, | |
| "tangent_dominance": true, | |
| "convex_tail": true | |
| }, | |
| { | |
| "epsilon": 1, | |
| "delta_star": 0.649185, | |
| "u0": 0.16878926941872574, | |
| "analytic_tangent_slope": -2.078419293355624, | |
| "minimum_tangent_slack": 0, | |
| "minimum_slope_increment": 0, | |
| "tangent_dominance": true, | |
| "convex_tail": true | |
| }, | |
| { | |
| "epsilon": 2, | |
| "delta_star": 0.549133, | |
| "u0": 0.1514991228268617, | |
| "analytic_tangent_slope": -2.9760351292862377, | |
| "minimum_tangent_slack": 0, | |
| "minimum_slope_increment": 0, | |
| "tangent_dominance": true, | |
| "convex_tail": true | |
| }, | |
| { | |
| "epsilon": 4, | |
| "delta_star": 0.416972, | |
| "u0": 0.11564327912801145, | |
| "analytic_tangent_slope": -5.041609426650677, | |
| "minimum_tangent_slack": -2.461805277409468e-7, | |
| "minimum_slope_increment": -3e-323, | |
| "tangent_dominance": true, | |
| "convex_tail": true | |
| }, | |
| { | |
| "epsilon": 8, | |
| "delta_star": 0.29217, | |
| "u0": 0.07259321767686538, | |
| "analytic_tangent_slope": -9.750641183120514, | |
| "minimum_tangent_slack": -4.178951782396467e-7, | |
| "minimum_slope_increment": -7.707e-321, | |
| "tangent_dominance": true, | |
| "convex_tail": true | |
| }, | |
| { | |
| "epsilon": 16, | |
| "delta_star": 0.197615, | |
| "u0": 0.03955363315735349, | |
| "analytic_tangent_slope": -20.28597749697904, | |
| "minimum_tangent_slack": 0, | |
| "minimum_slope_increment": -1.0522549e-316, | |
| "tangent_dominance": true, | |
| "convex_tail": true | |
| } | |
| ], | |
| "negative_controls": [ | |
| { | |
| "id": "NC_C5_extend_threshold_to_delta_0.9", | |
| "mutated_row": { | |
| "epsilon": 1, | |
| "delta_star": 0.9, | |
| "u0": 0.07191646824487513, | |
| "analytic_tangent_slope": -2.892737901160772, | |
| "minimum_tangent_slack": -0.10803549340954666, | |
| "minimum_slope_increment": -0.0007810622667761002, | |
| "tangent_dominance": false, | |
| "convex_tail": false | |
| }, | |
| "rejected": true | |
| } | |
| ], | |
| "passed": true | |
| }, | |
| "limitation": "Independent current regression for previously full-credit evidence; historical judged values remain preserved and reachable." | |
| }, | |
| "all_passed": true | |
| } | |