Spaces:
Running
Running
Dinesh Jinjala
Full-scale reproduction: all 6 claims VERIFIED (claims 1,2,3,5,6 upgraded from toy baseline; claim 4 exact audit preserved). Adds per-claim pages, real 2016 election data analysis, simulation RMSE+coverage, Delta-method asymptotic validity, von Neumann minimax LP. Historical toy baseline preserved at pages/historical-toy-baseline.
08e9f95 | { | |
| "paper": "GJblFvJcMb", | |
| "claim": 5, | |
| "arxiv": "2504.19043", | |
| "source_scope": "Section 3.2 (average case) and Section 3.4 (adversarial case)", | |
| "design": { | |
| "K": [ | |
| 5, | |
| 10, | |
| 20 | |
| ], | |
| "n": [ | |
| 500, | |
| 1500, | |
| 3500, | |
| 10000 | |
| ], | |
| "n_reps": 50, | |
| "coef": "N(0,1)", | |
| "interactions_scaled_to_main_R2": 0.7, | |
| "noise_var": 0.1, | |
| "binary_factors": true, | |
| "true_pi": "Proposition 1 closed-form" | |
| }, | |
| "average_case": [ | |
| { | |
| "K": 5, | |
| "sweep": [ | |
| { | |
| "K": 5, | |
| "n": 500, | |
| "rmse_mean": 0.006461795519609526, | |
| "rmse_median": 0.006441473842272505, | |
| "bias2_median": 1.925756012859587e-07, | |
| "var_median": 4.0604308635783115e-05, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.9480000000000001, | |
| "rmse_Q": 0.041286964330342096, | |
| "lam": 1.6711055759427953 | |
| }, | |
| { | |
| "K": 5, | |
| "n": 1500, | |
| "rmse_mean": 0.0038379940433335633, | |
| "rmse_median": 0.004034878929122873, | |
| "bias2_median": 4.397210394640941e-08, | |
| "var_median": 1.528652881425369e-05, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.968, | |
| "rmse_Q": 0.02456763127249781, | |
| "lam": 1.6711055759427953 | |
| }, | |
| { | |
| "K": 5, | |
| "n": 3500, | |
| "rmse_mean": 0.0023278446035150196, | |
| "rmse_median": 0.0023115791005000963, | |
| "bias2_median": 6.485479860845058e-08, | |
| "var_median": 5.278543139260377e-06, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.952, | |
| "rmse_Q": 0.01693910751191979, | |
| "lam": 1.6711055759427953 | |
| }, | |
| { | |
| "K": 5, | |
| "n": 10000, | |
| "rmse_mean": 0.00155414240696854, | |
| "rmse_median": 0.0015758935848253172, | |
| "bias2_median": 1.870114581873225e-08, | |
| "var_median": 2.3437304364133936e-06, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.924, | |
| "rmse_Q": 0.010912603985334978, | |
| "lam": 1.6711055759427953 | |
| } | |
| ], | |
| "rmse_decreases": true, | |
| "variance_dominates_at_maxn": true, | |
| "coverage_pi_at_maxn": 0.924 | |
| }, | |
| { | |
| "K": 10, | |
| "sweep": [ | |
| { | |
| "K": 10, | |
| "n": 500, | |
| "rmse_mean": 0.007013917440829284, | |
| "rmse_median": 0.006713439826552316, | |
| "bias2_median": 1.245846044718415e-06, | |
| "var_median": 4.321492669620198e-05, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.938, | |
| "rmse_Q": 0.05363010429052456, | |
| "lam": 1.8314563277706923 | |
| }, | |
| { | |
| "K": 10, | |
| "n": 1500, | |
| "rmse_mean": 0.003702385909396305, | |
| "rmse_median": 0.0037700867847607856, | |
| "bias2_median": 2.1797935534346663e-07, | |
| "var_median": 1.3950627130498467e-05, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.942, | |
| "rmse_Q": 0.026396623410346952, | |
| "lam": 1.8314563277706923 | |
| }, | |
| { | |
| "K": 10, | |
| "n": 3500, | |
| "rmse_mean": 0.0023275051131198612, | |
| "rmse_median": 0.0023395399053992524, | |
| "bias2_median": 3.448669052052663e-08, | |
| "var_median": 5.359381818842434e-06, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.958, | |
| "rmse_Q": 0.013969799106910681, | |
| "lam": 1.8314563277706923 | |
| }, | |
| { | |
| "K": 10, | |
| "n": 10000, | |
| "rmse_mean": 0.0013963923026081933, | |
| "rmse_median": 0.0013937218914509518, | |
| "bias2_median": 8.603114480100907e-08, | |
| "var_median": 1.745040906126524e-06, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.954, | |
| "rmse_Q": 0.011576389545590102, | |
| "lam": 1.8314563277706923 | |
| } | |
| ], | |
| "rmse_decreases": true, | |
| "variance_dominates_at_maxn": true, | |
| "coverage_pi_at_maxn": 0.954 | |
| }, | |
| { | |
| "K": 20, | |
| "sweep": [ | |
| { | |
| "K": 20, | |
| "n": 500, | |
| "rmse_mean": 0.011829390895454027, | |
| "rmse_median": 0.011972736240263761, | |
| "bias2_median": 9.107464676598005e-07, | |
| "var_median": 0.00014098233892214615, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.9460000000000001, | |
| "rmse_Q": 0.21505665313075278, | |
| "lam": 2.0007786273454538 | |
| }, | |
| { | |
| "K": 20, | |
| "n": 1500, | |
| "rmse_mean": 0.005311505346276954, | |
| "rmse_median": 0.005259090601133226, | |
| "bias2_median": 3.770463942592464e-07, | |
| "var_median": 2.737060116436915e-05, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.9440000000000002, | |
| "rmse_Q": 0.10284634701539644, | |
| "lam": 2.0007786273454538 | |
| }, | |
| { | |
| "K": 20, | |
| "n": 3500, | |
| "rmse_mean": 0.003423300986658493, | |
| "rmse_median": 0.003327497302306002, | |
| "bias2_median": 9.342114747453597e-08, | |
| "var_median": 1.0773183248827142e-05, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.9480000000000002, | |
| "rmse_Q": 0.0700078953986648, | |
| "lam": 2.0007786273454538 | |
| }, | |
| { | |
| "K": 20, | |
| "n": 10000, | |
| "rmse_mean": 0.0019198522807017907, | |
| "rmse_median": 0.0019239108847675613, | |
| "bias2_median": 7.217569374034592e-09, | |
| "var_median": 3.699654089227817e-06, | |
| "variance_dominates": true, | |
| "coverage_pi": 0.9530000000000001, | |
| "rmse_Q": 0.03621903868478622, | |
| "lam": 2.0007786273454538 | |
| } | |
| ], | |
| "rmse_decreases": true, | |
| "variance_dominates_at_maxn": true, | |
| "coverage_pi_at_maxn": 0.9530000000000001 | |
| } | |
| ], | |
| "adversarial": { | |
| "sweep": [ | |
| { | |
| "n": 1000, | |
| "p_R": 0.5, | |
| "value_true": 0.4776537203230401, | |
| "value_hat_mean": 0.4701726775365815, | |
| "coverage_value": 1.0, | |
| "coverage_strategy": null, | |
| "piA_true_support": 2 | |
| }, | |
| { | |
| "n": 5000, | |
| "p_R": 0.5, | |
| "value_true": 0.536778094188713, | |
| "value_hat_mean": 0.5345057696807607, | |
| "coverage_value": 0.96, | |
| "coverage_strategy": null, | |
| "piA_true_support": 2 | |
| }, | |
| { | |
| "n": 10000, | |
| "p_R": 0.5, | |
| "value_true": 0.5659109787090211, | |
| "value_hat_mean": 0.5653511755528775, | |
| "coverage_value": 0.98, | |
| "coverage_strategy": null, | |
| "piA_true_support": 3 | |
| } | |
| ], | |
| "coverage_pattern_n5000_approaches_nominal": true, | |
| "note": "single gender factor, two-party zero-sum game (paper's tractability choice)" | |
| }, | |
| "claim5_passed": true | |
| } |