Files
mcm-26-b/output/q3/bayes-ablation/benchmark.json
T

712 lines
21 KiB
JSON

{
"source": "local_simulator_only",
"seeds": "0,1,2,3,4,5",
"counts": "10,16",
"config": {
"field": {
"omega_radius_m": 1800.0,
"channel_min": 1,
"channel_max": 20,
"source_count_min": 10,
"source_count_max": 16,
"r_eff_min_m": 1000.0,
"r_eff_max_m": 1500.0,
"near_radius_m": 5.0,
"clear_radius_m": 20.0,
"bearing_error_half_deg": 1.0,
"bearing_decimals": 2,
"coord_abs_limit_m": 2000000.0,
"directional_half_angle_deg": 90.0,
"max_virtual_duration_s": 360000.0,
"max_real_duration_s": 1200.0,
"test_window_s": 1500.0
},
"cost": {
"speed_mps": 5.0,
"measure_s": 5.0,
"switch_s": 1.0,
"clear_success_s": 5.0,
"clear_fail_s": 3.0
},
"session": {
"arena_id": "default",
"base_url": "http://127.0.0.1:2026",
"robot_id_max_bytes": 64,
"request_id_max_bytes": 128,
"request_body_max_bytes": 65536,
"connect_timeout_s": 5.0,
"read_timeout_s": 15.0,
"max_attempts": 3,
"retry_backoff_s": 0.25,
"reserve_exit_s": 60.0,
"real_rtt_p95_s": 1.0,
"self_test_real_budget_s": 1800.0
},
"search": {
"grid_step_m": 700.0,
"grid_half_cells": 3,
"fallback_clear_grid_m": 20.0,
"bearing_rounding_margin_deg": 0.005,
"polygon_sides": 192,
"witness_spacing_m": 60.0,
"candidate_rings": [
0.0,
0.4,
0.75,
1.0
],
"candidate_angles": 12,
"clear_margin_m": 0.5,
"max_localize_steps": 8,
"max_anomalies_per_channel": 3,
"max_blocked_probes": 4,
"fallback_max_cells": 400,
"persistent_search": false,
"virtual_reserve_s": 10000.0
},
"bayes": {
"particle_spacing_m": 25.0,
"score_mode": "radius",
"score_subsample": 800,
"mc_representatives": 6,
"lambda_move_s": 0.1,
"wide_rings": [
1.0,
1.5,
2.0
],
"station_ring_radius_m": 1200.0,
"inner_mass_weight": 0.5,
"resolve_bonus": 10.0,
"station_move_penalty_s": 40.0,
"two_opt_enabled": true,
"two_opt_passes": 3,
"grid_cert_enabled": true
}
},
"aggregates": {
"seven_batch": {
"runs": 14,
"all_cleared_runs": 14,
"valid_runs": 14,
"mean_virtual_s": 5352.7325,
"median_virtual_s": 5434.1494999999995,
"max_virtual_s": 6755.138,
"mean_measures": 102.35714285714286,
"mean_distance_m": 23412.95,
"mean_skipped_measures": 0,
"mean_compute_wall_s": 1.3252562797861174,
"mean_paired_time_reduction": 0.0,
"min_paired_time_reduction": 0.0,
"max_paired_time_reduction": 0.0,
"failed_clears": 0
},
"bayes": {
"runs": 14,
"all_cleared_runs": 14,
"valid_runs": 14,
"mean_virtual_s": 4277.573428571429,
"median_virtual_s": 4351.9775,
"max_virtual_s": 5030.248,
"mean_measures": 109.57142857142857,
"mean_distance_m": 17820.37857142857,
"mean_skipped_measures": 0,
"mean_compute_wall_s": 0.963306818642325,
"mean_paired_time_reduction": 0.19524497250092424,
"min_paired_time_reduction": 0.013843669501892086,
"max_paired_time_reduction": 0.28148289237721946,
"failed_clears": 0
}
},
"runs": [
{
"case": "random-10-seed0",
"variant": "seven_batch",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4267.838,
"accounted_virtual_time_s": 4267.838,
"measures": 108,
"clears": 10,
"failed_clears": 0,
"distance_m": 17879.2,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.0046135419979692,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "62615b6a00bd5b2516acf1b3744d968389e41754880e4497c885951de612c1e5"
},
{
"case": "random-10-seed0",
"variant": "bayes",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 3498.5,
"accounted_virtual_time_s": 3498.5,
"measures": 111,
"clears": 10,
"failed_clears": 0,
"distance_m": 13937.5,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 0.4990922920042067,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "7e4fe8b32d06f2f71e286806486bef546c6c32e8c8abf1879f68c7520ea66321"
},
{
"case": "random-10-seed1",
"variant": "seven_batch",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 5227.394,
"accounted_virtual_time_s": 5227.394,
"measures": 112,
"clears": 10,
"failed_clears": 0,
"distance_m": 22577.0,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.0347122500024852,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "b0c0acdc57299d65d7462dcb63861df0985dcad240ab3ac71b110f10541c9ab7"
},
{
"case": "random-10-seed1",
"variant": "bayes",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 3998.736,
"accounted_virtual_time_s": 3998.736,
"measures": 117,
"clears": 10,
"failed_clears": 0,
"distance_m": 16278.7,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 0.7109259589997237,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "0fbcbc7ddd69a189c1b9ac2903be3440f61faf7d44b19ab12428b0415e4ffba7"
},
{
"case": "random-10-seed2",
"variant": "seven_batch",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4919.386,
"accounted_virtual_time_s": 4919.386,
"measures": 102,
"clears": 10,
"failed_clears": 0,
"distance_m": 21341.9,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.2283702499989886,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "167cbe69eac057ebbf9738179537aa03fbfa12205660222380c72ac9928cf47f"
},
{
"case": "random-10-seed2",
"variant": "bayes",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 3534.663,
"accounted_virtual_time_s": 3534.663,
"measures": 111,
"clears": 10,
"failed_clears": 0,
"distance_m": 14153.3,
"skipped_measures": 0,
"no_shrink_measures": 3,
"compute_wall_s": 0.8635688340000343,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "c3cebf19d4cc6749e3c582265c27b231acca6084407a6a8d0e4b62f88fe8c9e5"
},
{
"case": "random-10-seed3",
"variant": "seven_batch",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4770.216,
"accounted_virtual_time_s": 4770.216,
"measures": 116,
"clears": 10,
"failed_clears": 0,
"distance_m": 20161.1,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.0459828330058372,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "cb3b60ac2e62aa569c47726d94f9b05e990222aa4ec813f0448ecbef6975a6b8"
},
{
"case": "random-10-seed3",
"variant": "bayes",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4184.416,
"accounted_virtual_time_s": 4184.416,
"measures": 117,
"clears": 10,
"failed_clears": 0,
"distance_m": 17217.1,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 0.6219143329944927,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "fb722cb2cdcad85ca96aecd650dfe9ae65de384614887a56fac2d2c7df1cfb26"
},
{
"case": "random-10-seed4",
"variant": "seven_batch",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4530.077,
"accounted_virtual_time_s": 4530.077,
"measures": 103,
"clears": 10,
"failed_clears": 0,
"distance_m": 19350.4,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.0621211670004413,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "10576ed2e9b8c65b48817601901150659d29076344fa46b4eb0dd6683d88f23b"
},
{
"case": "random-10-seed4",
"variant": "bayes",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 3845.753,
"accounted_virtual_time_s": 3845.753,
"measures": 114,
"clears": 10,
"failed_clears": 0,
"distance_m": 15598.8,
"skipped_measures": 0,
"no_shrink_measures": 1,
"compute_wall_s": 0.6638023749983404,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "ca4960dd0badcfa8a8a45d552b2a6f94e1f2d93225ac3fbf3369a15f77979836"
},
{
"case": "random-10-seed5",
"variant": "seven_batch",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4239.276,
"accounted_virtual_time_s": 4239.276,
"measures": 100,
"clears": 10,
"failed_clears": 0,
"distance_m": 17986.4,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.172969125000236,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "3383fcd82dd713a596dfff85ae1e57c51f0a662e4503eba4618fec07691ab058"
},
{
"case": "random-10-seed5",
"variant": "bayes",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 3531.895,
"accounted_virtual_time_s": 3531.895,
"measures": 102,
"clears": 10,
"failed_clears": 0,
"distance_m": 14384.5,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 0.925086832998204,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "46aafab321e71bc469b2404aa7d2e844f6d68e24b5e80f8a46cbf6ea3259ec51"
},
{
"case": "boundary-10",
"variant": "seven_batch",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4550.961,
"accounted_virtual_time_s": 4550.961,
"measures": 126,
"clears": 10,
"failed_clears": 0,
"distance_m": 18739.8,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 0.6578390000067884,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "c0f6ca5adb38b624deeb5e71467a8760612311d88b73d1c12c625e9607aa9106"
},
{
"case": "boundary-10",
"variant": "bayes",
"source_count": 10,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4487.959,
"accounted_virtual_time_s": 4487.959,
"measures": 131,
"clears": 10,
"failed_clears": 0,
"distance_m": 18299.8,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 0.24124591700092424,
"anomalies": [],
"stop_reason": "all_resolved",
"actions_sha256": "a4cba3dd9f284f79df6c2a721e440b2535d917e5156e3fa46d643955f6d4812a"
},
{
"case": "random-16-seed0",
"variant": "seven_batch",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 6323.059,
"accounted_virtual_time_s": 6323.059,
"measures": 82,
"clears": 16,
"failed_clears": 0,
"distance_m": 28820.3,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.879373541996756,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "65412262a8ed1bc48ed14a5dd47977196bbd5d3f4c10935f97b9e53a9aba7479"
},
{
"case": "random-16-seed0",
"variant": "bayes",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4823.59,
"accounted_virtual_time_s": 4823.59,
"measures": 105,
"clears": 16,
"failed_clears": 0,
"distance_m": 20608.0,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 2.0598397080029827,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "f38c62bba9fbe931f4e754fd29c6ea5ea7aaaaed71e3c1c5d348cbf5b825f020"
},
{
"case": "random-16-seed1",
"variant": "seven_batch",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 6366.238,
"accounted_virtual_time_s": 6366.238,
"measures": 83,
"clears": 16,
"failed_clears": 0,
"distance_m": 29006.2,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.9473919169977307,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "07b6bea6e0d7697e27ecc9bbb9c380a5e3f19612f0e71fb4f9fc34694474e5fb"
},
{
"case": "random-16-seed1",
"variant": "bayes",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4921.289,
"accounted_virtual_time_s": 4921.289,
"measures": 101,
"clears": 16,
"failed_clears": 0,
"distance_m": 21246.4,
"skipped_measures": 0,
"no_shrink_measures": 1,
"compute_wall_s": 1.7206028750006226,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "4a9bddf562912d045fbf311ac09ebe0fb2ede09f8a9e41bd57c804d9d40b2d7d"
},
{
"case": "random-16-seed2",
"variant": "seven_batch",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 5701.126,
"accounted_virtual_time_s": 5701.126,
"measures": 114,
"clears": 16,
"failed_clears": 0,
"distance_m": 24740.6,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.5009183329966618,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "458ab8d6f8a0ef318536956fece2ba2444fd45101fdb614f8f82c3c243b0d0d2"
},
{
"case": "random-16-seed2",
"variant": "bayes",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4283.604,
"accounted_virtual_time_s": 4283.604,
"measures": 102,
"clears": 16,
"failed_clears": 0,
"distance_m": 17978.0,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 0.9308353329979582,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "d1ded4fbefc0464ad01f5523af46a954311d2664829ae9e60c59c2a4361acb8d"
},
{
"case": "random-16-seed3",
"variant": "seven_batch",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 5698.724,
"accounted_virtual_time_s": 5698.724,
"measures": 89,
"clears": 16,
"failed_clears": 0,
"distance_m": 25483.6,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.7740798750019167,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "eff755e0adab4e080e59e6023f647520efb699234c101bcfdde306a81682e973"
},
{
"case": "random-16-seed3",
"variant": "bayes",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4420.351,
"accounted_virtual_time_s": 4420.351,
"measures": 96,
"clears": 16,
"failed_clears": 0,
"distance_m": 18861.8,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.6113453750003828,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "5c8e92247c0a23208e5da352a73adad4a2c232ed6ebec12440c0f5aa5b66c55e"
},
{
"case": "random-16-seed4",
"variant": "seven_batch",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 5640.905,
"accounted_virtual_time_s": 5640.905,
"measures": 94,
"clears": 16,
"failed_clears": 0,
"distance_m": 25024.5,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.6842128749995027,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "0c4ade3708cf77b9d591ec7c628e6950929736049f97219490c235fca88739b7"
},
{
"case": "random-16-seed4",
"variant": "bayes",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4652.97,
"accounted_virtual_time_s": 4652.97,
"measures": 97,
"clears": 16,
"failed_clears": 0,
"distance_m": 19999.9,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.2331414589934866,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "b60f2a9165c886d421badf9f5e798896e91fe55724a960b0a1c2082fe5776d8a"
},
{
"case": "random-16-seed5",
"variant": "seven_batch",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 5947.917,
"accounted_virtual_time_s": 5947.917,
"measures": 87,
"clears": 16,
"failed_clears": 0,
"distance_m": 26774.6,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.5554147079965333,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "747224e1954d84af9be835c6b5c0e7914a4205afb5d8031090b0463b6fa2ad9e"
},
{
"case": "random-16-seed5",
"variant": "bayes",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 4672.054,
"accounted_virtual_time_s": 4672.054,
"measures": 106,
"clears": 16,
"failed_clears": 0,
"distance_m": 19840.3,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.0522228339978028,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "bf8a6ef07fe4389a8ec847ec5d84830b85e107b03763681d77c91f1144e05835"
},
{
"case": "boundary-16",
"variant": "seven_batch",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 6755.138,
"accounted_virtual_time_s": 6755.138,
"measures": 117,
"clears": 16,
"failed_clears": 0,
"distance_m": 29895.7,
"skipped_measures": 0,
"no_shrink_measures": 0,
"compute_wall_s": 1.005588500003796,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "8957ee07bc9b5c00bb801e99dd8cd7148bab3d1fa86bbda096c446749b837e50"
},
{
"case": "boundary-16",
"variant": "bayes",
"source_count": 16,
"all_cleared": true,
"completed": true,
"correct_absence": true,
"normal_exit": true,
"virtual_time_s": 5030.248,
"accounted_virtual_time_s": 5030.248,
"measures": 124,
"clears": 16,
"failed_clears": 0,
"distance_m": 21081.2,
"skipped_measures": 0,
"no_shrink_measures": 1,
"compute_wall_s": 0.35267133400338935,
"anomalies": [],
"stop_reason": "sixteen_cleared",
"actions_sha256": "e36705a9f164eb24604cbee2cdf0e3cf92d9e47c99bd5db9a9729e1c943cca04"
}
],
"limitations": "自建模拟器合成数据;persistent 关闭以对齐找全口径。"
}