MyBVUgacQ9 / raw /summary.json
DineshAI's picture
Rebuild verification from full-scale runs: 4 claims VERIFIED, 2 BLOCKED (honest)
4370027 verified
Raw
History Blame Contribute Delete
23.2 kB
{
"provenance": {
"git_sha": "6c6a5a792e1c48bfbdd2758b674b855a94831de1",
"git_branch": "orx/instrument-fixes-envelope-decades-tail-sup-envel",
"git_dirty": false,
"python": "3.12.12",
"platform": "Linux-6.12.90-120.164.amzn2023.x86_64-x86_64-with-glibc2.36",
"machine": "x86_64",
"cpu_count_usable": 8,
"cpu_count_host": 64,
"cgroup_cpu_quota": 8.0,
"numpy": "2.2.6",
"scipy": "1.15.3",
"global_seed": 20260726,
"run_command": "uv run --frozen python -m repro.run_all",
"utc": "2026-07-26T21:26:34Z"
},
"calibration": {
"passed": true,
"cases": [
{
"case": "theta_1_over_k",
"expected": {
"linear": false,
"little_o_1_over_k": false,
"determined": true
},
"observed": {
"linear": false,
"little_o_1_over_k": false,
"determined": true
},
"power_alpha": 0.9999999999999998,
"c1_estimate": 1.000748755181323,
"passed": true
},
{
"case": "theta_1_over_logk",
"expected": {
"linear": false,
"little_o_1_over_k": false,
"determined": false
},
"observed": {
"linear": false,
"little_o_1_over_k": false,
"determined": false
},
"power_alpha": 0.16428897619174537,
"c1_estimate": 1.0001128872719103,
"passed": true
},
{
"case": "k_pow_-1.5",
"expected": {
"linear": false,
"little_o_1_over_k": true,
"determined": true
},
"observed": {
"linear": false,
"little_o_1_over_k": true,
"determined": true
},
"power_alpha": 1.5000000000000007,
"c1_estimate": 1.0011233429836264,
"passed": true
},
{
"case": "geometric_0.7",
"expected": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"observed": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"power_alpha": 188.84214020463898,
"c1_estimate": 1.4285696539481423,
"passed": true
},
{
"case": "geometric_0.995",
"expected": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"observed": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"power_alpha": 5.0548182276817055,
"c1_estimate": 1.0050251256281406,
"passed": true
},
{
"case": "geometric_0.04_floored",
"expected": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"observed": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"power_alpha": 7.794739784845435,
"c1_estimate": 24.999999999999986,
"passed": true
},
{
"case": "theta_1_over_k_floored",
"expected": {
"linear": false,
"little_o_1_over_k": false
},
"observed": {
"linear": false,
"little_o_1_over_k": false,
"determined": true
},
"power_alpha": 1.0000000000000027,
"c1_estimate": 1.000748755181323,
"passed": true
},
{
"case": "geometric_0.9_noisy",
"expected": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"observed": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"power_alpha": 106.25824361354564,
"c1_estimate": 1.1111229240680602,
"passed": true
},
{
"case": "k_pow_-1_noisy",
"expected": {
"linear": false,
"little_o_1_over_k": false,
"determined": true
},
"observed": {
"linear": false,
"little_o_1_over_k": false,
"determined": true
},
"power_alpha": 1.0091042001717254,
"c1_estimate": 1.0007593948030888,
"passed": true
},
{
"case": "geometric_then_plateau_autofloor",
"expected": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"observed": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"power_alpha": 5.309155599594488,
"c1_estimate": 1.1764705882352942,
"passed": true
},
{
"case": "geometric_truncated_autofloor",
"expected": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"observed": {
"linear": true,
"little_o_1_over_k": true,
"determined": true
},
"power_alpha": 2.782640719904104,
"c1_estimate": 1.075268817204301,
"passed": true
},
{
"case": "theta_1_over_k_truncated_autofloor",
"expected": {
"linear": false,
"little_o_1_over_k": false
},
"observed": {
"linear": false,
"little_o_1_over_k": false,
"determined": false
},
"power_alpha": 0.9999999999999996,
"c1_estimate": 1.0960610499494086,
"passed": true
}
]
},
"assumptions": {
"passed": true,
"instances": [
{
"instance": "toy(q=1)",
"rho_threshold": 4.0,
"assumptions_hold": true,
"n_x": 4,
"n_z": 1,
"n_c": 1,
"n_blocks": 4,
"mu_f": 1.0,
"L_f": 1.0,
"mu_phi": 1.0,
"L_phi": 1.0,
"sigma_min_Q": 1.0,
"rank_Q": 1,
"Q_full_row_rank": true,
"lam_min_QQt": 1.0,
"norm_pinvQ": 1.0,
"norm_C": 1.0,
"norm_d": 0.0,
"norm_e": 1.0,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"free",
"free",
"free",
"free"
]
},
{
"instance": "toy(q=10)",
"rho_threshold": 0.4,
"assumptions_hold": true,
"n_x": 4,
"n_z": 1,
"n_c": 1,
"n_blocks": 4,
"mu_f": 1.0,
"L_f": 1.0,
"mu_phi": 1.0,
"L_phi": 1.0,
"sigma_min_Q": 10.0,
"rank_Q": 1,
"Q_full_row_rank": true,
"lam_min_QQt": 100.0,
"norm_pinvQ": 0.1,
"norm_C": 1.0,
"norm_d": 0.0,
"norm_e": 1.0,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"free",
"free",
"free",
"free"
]
},
{
"instance": "toy(q=10,box)",
"rho_threshold": 0.4,
"assumptions_hold": true,
"n_x": 4,
"n_z": 1,
"n_c": 1,
"n_blocks": 4,
"mu_f": 1.0,
"L_f": 1.0,
"mu_phi": 1.0,
"L_phi": 1.0,
"sigma_min_Q": 10.0,
"rank_Q": 1,
"Q_full_row_rank": true,
"lam_min_QQt": 100.0,
"norm_pinvQ": 0.1,
"norm_C": 1.0,
"norm_d": 0.0,
"norm_e": 1.0,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"box[-2,2]",
"box[-2,2]",
"box[-2,2]",
"box[-2,2]"
]
},
{
"instance": "B1_convex_multiaffine",
"rho_threshold": 2.6666666666666665,
"assumptions_hold": true,
"n_x": 4,
"n_z": 1,
"n_c": 1,
"n_blocks": 4,
"mu_f": 1.0,
"L_f": 1.0,
"mu_phi": 1.0,
"L_phi": 1.0,
"sigma_min_Q": 1.5,
"rank_Q": 1,
"Q_full_row_rank": true,
"lam_min_QQt": 2.25,
"norm_pinvQ": 0.6666666666666666,
"norm_C": 1.0,
"norm_d": 0.0,
"norm_e": 1.0,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"free",
"free",
"free",
"free"
]
},
{
"instance": "B2_convex_linear",
"rho_threshold": 4.0,
"assumptions_hold": true,
"n_x": 2,
"n_z": 1,
"n_c": 1,
"n_blocks": 2,
"mu_f": 1.0,
"L_f": 1.0,
"mu_phi": 1.0,
"L_phi": 1.0,
"sigma_min_Q": 1.0,
"rank_Q": 1,
"Q_full_row_rank": true,
"lam_min_QQt": 1.0,
"norm_pinvQ": 1.0,
"norm_C": 0.0,
"norm_d": 1.4142135623730951,
"norm_e": 1.0,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"free",
"free"
]
},
{
"instance": "random(nx=80)",
"rho_threshold": 3020.344417614443,
"assumptions_hold": true,
"n_x": 80,
"n_z": 12,
"n_c": 10,
"n_blocks": 20,
"mu_f": 1.0000824856463375,
"L_f": 2.804020206917896,
"mu_phi": 1.0019132602326106,
"L_phi": 2.5745202530551725,
"sigma_min_Q": 0.09360154370751472,
"rank_Q": 10,
"Q_full_row_rank": true,
"lam_min_QQt": 0.008761248984429789,
"norm_pinvQ": 10.683584483657567,
"norm_C": 1.0000000000000009,
"norm_d": 1.209131094418871,
"norm_e": 0.39810741619577894,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free"
]
},
{
"instance": "random(nx=200)",
"rho_threshold": 2609.8792092662347,
"assumptions_hold": true,
"n_x": 200,
"n_z": 25,
"n_c": 20,
"n_blocks": 40,
"mu_f": 1.0000006854790031,
"L_f": 3.0805787395751913,
"mu_phi": 1.0000161082533408,
"L_phi": 2.6151531587157955,
"sigma_min_Q": 0.10237959866254737,
"rank_Q": 20,
"Q_full_row_rank": true,
"lam_min_QQt": 0.01048158222230427,
"norm_pinvQ": 9.767571010862172,
"norm_C": 1.0000000000000009,
"norm_d": 1.2429759838984777,
"norm_e": 0.474525725597745,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free",
"free"
]
},
{
"instance": "locomotion2D(T=20)",
"rho_threshold": 40.0,
"assumptions_hold": true,
"n_x": 80,
"n_z": 21,
"n_c": 21,
"n_blocks": 20,
"mu_f": 1.0,
"L_f": 1.0,
"mu_phi": 10.0,
"L_phi": 10.0,
"sigma_min_Q": 1.0,
"rank_Q": 21,
"Q_full_row_rank": true,
"lam_min_QQt": 1.0,
"norm_pinvQ": 1.0,
"norm_C": 0.005740481251602518,
"norm_d": 0.2985644716859745,
"norm_e": 0.0,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN2+support[0.8,1.4]mg"
]
},
{
"instance": "locomotion3D(T=20)",
"rho_threshold": 40.0,
"assumptions_hold": true,
"n_x": 240,
"n_z": 63,
"n_c": 63,
"n_blocks": 20,
"mu_f": 1.0,
"L_f": 1.0,
"mu_phi": 10.0,
"L_phi": 10.0,
"sigma_min_Q": 1.0,
"rank_Q": 63,
"Q_full_row_rank": true,
"lam_min_QQt": 1.0,
"norm_pinvQ": 1.0,
"norm_C": 2.93912640082049e-05,
"norm_d": 0.03422143116681238,
"norm_e": 0.0,
"C_zero_diagonal_blocks": true,
"C_max_diag_block_entry": 0.0,
"C_symmetric": true,
"f_strongly_convex": true,
"phi_strongly_convex": true,
"all_sets_polyhedral": true,
"set_labels": [
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg",
"friction_pyramid(mu=0.7)xN4+support[0.8,1.4]mg"
]
}
]
},
"claims": {
"claim1": {
"verdict": "VERIFIED",
"confidence": "HIGH",
"headline": "o(1/k) established in 24/30 configs and refuted in 4, limit-point characterisation in 30/30, 5 inconclusive; Assumption-2.6 control fails as the paper predicts",
"n_configs": 30,
"n_determined": 25,
"n_inconclusive": 5,
"determinacy": 0.8333333333333334,
"n_ok": 24,
"n_o1k": 24,
"n_nash": 30,
"negative_control": {
"instance": "example_2_8(xy=1, Q=0)",
"assumption_2_6_holds": false,
"rank_Q": 0,
"n_c": 1,
"other_assumptions_hold": true,
"x_final": [
-0.0,
-0.0
],
"norm_x_final": 0.0,
"w_final": -4000.0,
"final_violation": 1.0,
"iterates_go_to_origin": true,
"dual_diverges": true,
"limit_infeasible": true,
"control_failed_as_predicted": true
},
"artifacts": [
"claim1/claim1_results.csv",
"claim1/claim1_raw.json",
"claim1/claim1_negative_control.json"
],
"internal_failure": false
},
"claim2": {
"verdict": "VERIFIED",
"confidence": "MEDIUM",
"headline": "eq.(4) certificate holds in 11 determined configs -> geometric in 11, local minimum in 11; certificate conservative vs bisected onset: True; high-||C|| control not geometric: True",
"n_cert": 11,
"n_cert_linear": 11,
"n_cert_localmin": 11,
"certificate_thresholds": [
0.00010000000000000006,
0.001000000000000001,
0.0010000000000000013
],
"empirical_onsets": [
2.0720787171542208,
5.327978945865642,
3.5545223556118883
],
"certificate_conservative": true,
"control_ok": true,
"accepts_zero_C": true,
"artifacts": [
"claim2/claim2_results.csv",
"claim2/claim2_bisection.json",
"claim2/claim2_localmin.json"
],
"internal_failure": false
},
"claim3": {
"verdict": "VERIFIED",
"confidence": "MEDIUM",
"headline": "10/10 instances have ACTIVE polyhedral indicators with L not second-order differentiable at the limit; the theorem's local gap decays geometrically in 5/5 of those with a determined rate; large-||C|| control does not: True",
"n_in_regime": 10,
"n_in_regime_determined": 5,
"n_geometric": 5,
"n_localmin": 10,
"n_apriori_certificate": 5,
"control_ok": true,
"artifacts": [
"claim3/claim3_results.csv",
"claim3/claim3_local_gaps.json",
"claim3/claim3_ball_comparison.json"
],
"internal_failure": false
},
"claim4": {
"verdict": "VERIFIED",
"confidence": "MEDIUM",
"headline": "measured ||C|| ~ (Delta t)^3.000 from the assembled operator; geometric convergence for every determined dt <= t_0 ~ 1.4807s (23/23)",
"measured_exponent": 3.000000000000001,
"t0_lower": 1.480730101003345,
"t0_upper": 1.5,
"n_below": 23,
"n_below_geometric": 23,
"eq7_ok": true,
"artifacts": [
"claim4/claim4_C_scaling.json",
"claim4/claim4_dt_sweep.csv",
"claim4/claim4_t0_bisection.json"
],
"internal_failure": false
},
"claim5": {
"verdict": "BLOCKED",
"confidence": "LOW",
"headline": "q>=10 sufficiency: 64/64 geometric; empirical onset q~0.07 (below 10, so the paper's condition is sufficient not necessary); ADMM fastest to 1e-08 in 21/36 multi-affine and 58/72 linear-constraint configurations",
"sufficiency_holds": true,
"n_above_10": 64,
"n_above_10_linear": 64,
"empirical_onset_median": 0.06988884548913396,
"baseline_supported": false,
"admm_wins_multiaffine": 21,
"n_multiaffine": 36,
"admm_wins_linear": 58,
"n_linear": 72,
"admm_objective_best": 36,
"n_objective_compared": 105,
"deviation": "PADMM/IPDS-ADMM/IADMM are standard reimplementations of the named methods; the three source papers were not retrievable",
"artifacts": [
"claim5/claim5_q_sweep.csv",
"claim5/claim5_q_onset_bisection.json",
"claim5/claim5_baseline_comparison.csv"
],
"internal_failure": false
},
"claim6": {
"verdict": "BLOCKED",
"confidence": "HIGH",
"headline": "2D locomotion (Fig 5), the humanoid-jump violation curves (Fig 3) and the centroidal solves behind Fig 6 reproduce with geometric convergence in every determined run; the real-robot half of the claim cannot be run without the hardware",
"simulation_reproduced": true,
"parts": {
"fig5-centre": {
"n": 6,
"n_determined": 5,
"n_geometric": 5,
"all_feasible_start": true,
"max_final_violation": 8.624516593324095e-06
},
"fig5-right": {
"n": 10,
"n_determined": 10,
"n_geometric": 10,
"all_feasible_start": true,
"max_final_violation": 1.0935146800891987e-16
},
"fig3-jump": {
"n": 30,
"n_determined": 30,
"n_geometric": 30,
"all_feasible_start": true,
"max_final_violation": 1.4232689452650154e-15
},
"fig6-humanoid-jump": {
"n": 10,
"n_determined": 10,
"n_geometric": 10,
"all_feasible_start": true,
"max_final_violation": 1.4232689452650154e-15
},
"fig6-quadruped-bound": {
"n": 10,
"n_determined": 10,
"n_geometric": 10,
"all_feasible_start": true,
"max_final_violation": 6.847543068772414e-16
}
},
"hardware": {
"reproducible": false,
"reason": "Figure 6 reports centroidal trajectories tracked by a DDP kinematics optimiser and executed on physical humanoid and quadruped robots. No robot hardware is available to this reproduction, and the authors' hardware logs are not published, so the hardware conjunct of the claim cannot be verified or falsified.",
"what_would_unblock": "access to the two robots (or the authors' released hardware trajectory and tracking logs) plus the Crocoddyl DDP tracking configuration used in the paper"
},
"artifacts": [
"claim6/claim6_results.csv",
"claim6/claim6_fig3_violation_mean_std.json",
"claim6/claim6_violation_traces.json"
],
"internal_failure": false
}
},
"self_assessed_points": 8,
"wall_clock_s": 7222.673751690076
}