Files
mcm-26-b/output/q3/search-ablation/evidence-audit.json
T
2026-09-11 03:26:20 +08:00

535 lines
16 KiB
JSON

{
"all_passed": true,
"runs": 48,
"checks": [
{
"case": "random-10-seed0",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed0",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed0",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed0",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed1",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed1",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed1",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed1",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed2",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed2",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed2",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed2",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed3",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed3",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed3",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed3",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed4",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed4",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed4",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-10-seed4",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-10",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-10",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-10",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-10",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed0",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed0",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed0",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed0",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed1",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed1",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed1",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed1",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed2",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed2",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed2",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed2",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed3",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed3",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed3",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed3",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed4",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed4",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed4",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "random-16-seed4",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-16",
"variant": "grid49_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-16",
"variant": "seven_immediate",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-16",
"variant": "seven_batch",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
},
{
"case": "boundary-16",
"variant": "seven_sweep",
"hash_matches": true,
"truth_retained_at_all_positive_updates": true,
"certificates_and_true_clear_distances": true,
"all_cleared": true,
"timing_matches": true,
"measure_count_matches": true,
"normal_exit": true
}
],
"note": "Offline independent verification of saved actions against separately stored synthetic scene truth; not official simulator validation."
}