Files
mcm-26-b/output/rl/review-20260911/evaluation/development/revised/results.json
T
2026-09-11 17:24:07 +08:00

263 lines
7.0 KiB
JSON

{
"source": "local_referee_only",
"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": 14.65,
"score_mode": "entropy",
"score_subsample": 800,
"mc_representatives": 7,
"lambda_move_s": 0.0105,
"wide_rings": [
1.0,
1.5,
2.0
],
"station_ring_radius_m": 1159.7,
"two_opt_enabled": true,
"two_opt_passes": 4,
"grid_cert_enabled": true,
"opportunistic_measure": true,
"opportunistic_radius_ratio": 0.65
}
},
"split": "development",
"rows": [
{
"case": "10-700",
"problem": 3,
"variant": "revised",
"valid": true,
"virtual_s": 3372.287884,
"all_cleared": true,
"measures": 124,
"failed_clears": 0,
"repeated_measures": 0,
"wall_s": 1.783104000001913,
"model_sha256": "b8b3a2bb103588348d8d7791bde9a2b0635c04778f0ac64f91c6f5c7cf87ca6e"
},
{
"case": "10-701",
"problem": 3,
"variant": "revised",
"valid": true,
"virtual_s": 3111.104271,
"all_cleared": true,
"measures": 119,
"failed_clears": 0,
"repeated_measures": 0,
"wall_s": 0.8802473000105238,
"model_sha256": "b8b3a2bb103588348d8d7791bde9a2b0635c04778f0ac64f91c6f5c7cf87ca6e"
},
{
"case": "10-702",
"problem": 3,
"variant": "revised",
"valid": true,
"virtual_s": 2987.469832,
"all_cleared": true,
"measures": 130,
"failed_clears": 0,
"repeated_measures": 0,
"wall_s": 0.9258373999909963,
"model_sha256": "b8b3a2bb103588348d8d7791bde9a2b0635c04778f0ac64f91c6f5c7cf87ca6e"
},
{
"case": "16-700",
"problem": 3,
"variant": "revised",
"valid": true,
"virtual_s": 3615.490259,
"all_cleared": true,
"measures": 106,
"failed_clears": 0,
"repeated_measures": 0,
"wall_s": 1.1374622000003,
"model_sha256": "b8b3a2bb103588348d8d7791bde9a2b0635c04778f0ac64f91c6f5c7cf87ca6e"
},
{
"case": "16-701",
"problem": 3,
"variant": "revised",
"valid": true,
"virtual_s": 3352.595571,
"all_cleared": true,
"measures": 111,
"failed_clears": 0,
"repeated_measures": 0,
"wall_s": 1.1424620999896433,
"model_sha256": "b8b3a2bb103588348d8d7791bde9a2b0635c04778f0ac64f91c6f5c7cf87ca6e"
},
{
"case": "16-702",
"problem": 3,
"variant": "revised",
"valid": true,
"virtual_s": 3148.793121,
"all_cleared": true,
"measures": 113,
"failed_clears": 0,
"repeated_measures": 0,
"wall_s": 1.0423000000009779,
"model_sha256": "b8b3a2bb103588348d8d7791bde9a2b0635c04778f0ac64f91c6f5c7cf87ca6e"
},
{
"case": "10-700",
"problem": 4,
"variant": "revised",
"valid": true,
"virtual_s": 12615.866,
"all_cleared": true,
"measures": 629,
"failed_clears": 0,
"repeated_measures": 0,
"wall_s": 0.16313280000758823,
"model_sha256": "6865d541ff9bdee81886d327345f2660d5f7d72f4b39810a58ae4b867ab37e42"
},
{
"case": "10-701",
"problem": 4,
"variant": "revised",
"valid": true,
"virtual_s": 14940.808477,
"all_cleared": true,
"measures": 665,
"failed_clears": 157,
"repeated_measures": 0,
"wall_s": 0.19661280000582337,
"model_sha256": "6865d541ff9bdee81886d327345f2660d5f7d72f4b39810a58ae4b867ab37e42"
},
{
"case": "10-702",
"problem": 4,
"variant": "revised",
"valid": true,
"virtual_s": 13408.10963,
"all_cleared": true,
"measures": 599,
"failed_clears": 17,
"repeated_measures": 0,
"wall_s": 0.17331990000093356,
"model_sha256": "6865d541ff9bdee81886d327345f2660d5f7d72f4b39810a58ae4b867ab37e42"
},
{
"case": "16-700",
"problem": 4,
"variant": "revised",
"valid": true,
"virtual_s": 9859.182322,
"all_cleared": true,
"measures": 286,
"failed_clears": 161,
"repeated_measures": 0,
"wall_s": 0.2287503999978071,
"model_sha256": "6865d541ff9bdee81886d327345f2660d5f7d72f4b39810a58ae4b867ab37e42"
},
{
"case": "16-701",
"problem": 4,
"variant": "revised",
"valid": true,
"virtual_s": 10135.152714,
"all_cleared": true,
"measures": 362,
"failed_clears": 55,
"repeated_measures": 0,
"wall_s": 0.23891419998835772,
"model_sha256": "6865d541ff9bdee81886d327345f2660d5f7d72f4b39810a58ae4b867ab37e42"
},
{
"case": "16-702",
"problem": 4,
"variant": "revised",
"valid": true,
"virtual_s": 9593.18014,
"all_cleared": true,
"measures": 335,
"failed_clears": 5,
"repeated_measures": 0,
"wall_s": 0.20746679999865592,
"model_sha256": "6865d541ff9bdee81886d327345f2660d5f7d72f4b39810a58ae4b867ab37e42"
}
],
"aggregates": {
"q3-revised": {
"runs": 6,
"valid": 6,
"mean_virtual_s": 3264.6234896666665,
"median_virtual_s": 3250.694346,
"max_virtual_s": 3615.490259,
"failed_clears": 0,
"repeated_measures": 0
},
"q4-revised": {
"runs": 6,
"valid": 6,
"mean_virtual_s": 11758.716547166667,
"median_virtual_s": 11375.509356999999,
"max_virtual_s": 14940.808477,
"failed_clears": 395,
"repeated_measures": 0
}
}
}