{ "bench_report": { "bench_version": 1, "track": "deformation_registration", "model": "coordinate_warp", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_config": { "lr": 0.01, "epochs": 8 }, "sweep": { "0.001": [ 0.27781713008880615, 0.3285594880580902, 0.29619064927101135, 0.34113916754722595, 0.34860163927078247, 0.3542182743549347, 0.31516358256340027, 0.28730571269989014 ], "0.003": [ 0.2060280293226242, 0.23130172491073608, 0.2125881314277649, 0.24440883100032806, 0.2516593039035797, 0.2537933588027954, 0.2329125702381134, 0.2088773399591446 ], "0.01": [ 0.1190430298447609, 0.13602468371391296, 0.14200977981090546, 0.1490132212638855, 0.14526495337486267, 0.18109995126724243, 0.1357964277267456, 0.14082112908363342 ] }, "full": { "per_seed": [ 0.1190430298447609, 0.13602468371391296, 0.14200977981090546, 0.1490132212638855, 0.14526495337486267, 0.18109995126724243, 0.1357964277267456, 0.14082112908363342 ] } }, "idea": { "best_config": { "lr": 0.01, "epochs": 8 }, "sweep": { "0.001": [ 0.27786731719970703, 0.3285939395427704, 0.29622170329093933, 0.34119054675102234, 0.3486487567424774, 0.35429301857948303, 0.31522244215011597, 0.2873333990573883 ], "0.003": [ 0.2074858844280243, 0.2321665734052658, 0.21403560042381287, 0.24621228873729706, 0.2530094385147095, 0.25567081570625305, 0.23396754264831543, 0.21000193059444427 ], "0.01": [ 0.1227923184633255, 0.14947034418582916, 0.13802805542945862, 0.15367528796195984, 0.1728336662054062, 0.18583709001541138, 0.14342737197875977, 0.14185279607772827 ] }, "per_seed": [ 0.1227923184633255, 0.14947034418582916, 0.13802805542945862, 0.15367528796195984, 0.1728336662054062, 0.18583709001541138, 0.14342737197875977, 0.14185279607772827 ] }, "comparison": { "delta_mean": 0.007355469278991222, "idea_wins": 1, "n_pairs": 8, "per_seed_diffs": [ 0.0037492886185646057, 0.013445660471916199, -0.003981724381446838, 0.004662066698074341, 0.027568712830543518, 0.004737138748168945, 0.00763094425201416, 0.0010316669940948486 ], "p_value": 0.0321, "mde": 0.008003765508655707, "mde_rel_pct": 5.572327803121244, "verdict": "idea worse (significant)", "system_worked": false }, "custom_track": { "name": "deformation_registration", "file": "custom_deformation_track.py", "domain": "geometry" }, "mechanism_signature": { "prediction": "lifted U/Cof(U)/det penalty improves conditioning and minimum determinant under large deformation", "observed_baseline_mean_condition": 9.625483721494675, "observed_idea_mean_condition": 3.6457439363002777, "observed_baseline_min_det": -0.031383185618324205, "observed_idea_min_det": 0.1291193552315235, "observed_baseline_fold_fraction": 0.05500000016763806, "observed_idea_fold_fraction": 0.0, "confirmed": true } }, "math_check": { "cofactor_max_abs": 7.152557373046875e-07, "det_max_abs": 4.76837158203125e-07, "rotation_det_max_abs": 2.384185791015625e-07 }, "all_sweeps": { "baseline": { "0.001": [ { "metric": 0.27781713008880615, "fold_fraction": 0.0, "mean_condition": 1.1320418119430542, "min_det": 0.920944094657898 }, { "metric": 0.3285594880580902, "fold_fraction": 0.0, "mean_condition": 1.1260122060775757, "min_det": 0.8810373544692993 }, { "metric": 0.29619064927101135, "fold_fraction": 0.0, "mean_condition": 1.1461265087127686, "min_det": 0.9009076952934265 }, { "metric": 0.34113916754722595, "fold_fraction": 0.0, "mean_condition": 1.1431663036346436, "min_det": 0.8950434923171997 }, { "metric": 0.34860163927078247, "fold_fraction": 0.0, "mean_condition": 1.1379283666610718, "min_det": 0.9005656242370605 }, { "metric": 0.3542182743549347, "fold_fraction": 0.0, "mean_condition": 1.1388452053070068, "min_det": 0.9023783802986145 }, { "metric": 0.31516358256340027, "fold_fraction": 0.0, "mean_condition": 1.1190083026885986, "min_det": 0.9096402525901794 }, { "metric": 0.28730571269989014, "fold_fraction": 0.0, "mean_condition": 1.1269221305847168, "min_det": 0.9133870601654053 } ], "0.003": [ { "metric": 0.2060280293226242, "fold_fraction": 0.0, "mean_condition": 1.6335077285766602, "min_det": 0.493784099817276 }, { "metric": 0.23130172491073608, "fold_fraction": 0.0, "mean_condition": 1.7948778867721558, "min_det": 0.41981199383735657 }, { "metric": 0.2125881314277649, "fold_fraction": 0.0, "mean_condition": 1.8645418882369995, "min_det": 0.43604058027267456 }, { "metric": 0.24440883100032806, "fold_fraction": 0.0, "mean_condition": 1.7859004735946655, "min_det": 0.42782339453697205 }, { "metric": 0.2516593039035797, "fold_fraction": 0.0, "mean_condition": 1.7938549518585205, "min_det": 0.43748193979263306 }, { "metric": 0.2537933588027954, "fold_fraction": 0.0, "mean_condition": 1.668728232383728, "min_det": 0.4448341429233551 }, { "metric": 0.2329125702381134, "fold_fraction": 0.0, "mean_condition": 1.5834689140319824, "min_det": 0.4970932900905609 }, { "metric": 0.2088773399591446, "fold_fraction": 0.0, "mean_condition": 1.6454168558120728, "min_det": 0.4864053726196289 } ], "0.01": [ { "metric": 0.1190430298447609, "fold_fraction": 0.0, "mean_condition": 4.642986297607422, "min_det": 0.08073875308036804 }, { "metric": 0.13602468371391296, "fold_fraction": 0.3449999988079071, "mean_condition": 29.603721618652344, "min_det": -0.3928036689758301 }, { "metric": 0.14200977981090546, "fold_fraction": 0.0, "mean_condition": 8.519186019897461, "min_det": 0.016476234421133995 }, { "metric": 0.1490132212638855, "fold_fraction": 0.0, "mean_condition": 4.453977584838867, "min_det": 0.09282688796520233 }, { "metric": 0.14526495337486267, "fold_fraction": 0.07500000298023224, "mean_condition": 13.297748565673828, "min_det": -0.09539034217596054 }, { "metric": 0.18109995126724243, "fold_fraction": 0.014999999664723873, "mean_condition": 5.3841352462768555, "min_det": -0.06205438822507858 }, { "metric": 0.1357964277267456, "fold_fraction": 0.0, "mean_condition": 3.7512576580047607, "min_det": 0.11113739013671875 }, { "metric": 0.14082112908363342, "fold_fraction": 0.004999999888241291, "mean_condition": 7.350856781005859, "min_det": -0.001996351173147559 } ] }, "idea": { "0.001": [ { "metric": 0.27786731719970703, "fold_fraction": 0.0, "mean_condition": 1.1346538066864014, "min_det": 0.9233546257019043 }, { "metric": 0.3285939395427704, "fold_fraction": 0.0, "mean_condition": 1.1273115873336792, "min_det": 0.882387638092041 }, { "metric": 0.29622170329093933, "fold_fraction": 0.0, "mean_condition": 1.1481126546859741, "min_det": 0.9028756022453308 }, { "metric": 0.34119054675102234, "fold_fraction": 0.0, "mean_condition": 1.145908236503601, "min_det": 0.8978317975997925 }, { "metric": 0.3486487567424774, "fold_fraction": 0.0, "mean_condition": 1.1401883363723755, "min_det": 0.9029046297073364 }, { "metric": 0.35429301857948303, "fold_fraction": 0.0, "mean_condition": 1.141953945159912, "min_det": 0.9053830504417419 }, { "metric": 0.31522244215011597, "fold_fraction": 0.0, "mean_condition": 1.1214745044708252, "min_det": 0.9123570322990417 }, { "metric": 0.2873333990573883, "fold_fraction": 0.0, "mean_condition": 1.1289077997207642, "min_det": 0.9152964949607849 } ], "0.003": [ { "metric": 0.2074858844280243, "fold_fraction": 0.0, "mean_condition": 1.7175836563110352, "min_det": 0.5274192094802856 }, { "metric": 0.2321665734052658, "fold_fraction": 0.0, "mean_condition": 1.833182692527771, "min_det": 0.4331795573234558 }, { "metric": 0.21403560042381287, "fold_fraction": 0.0, "mean_condition": 1.9415920972824097, "min_det": 0.4649915099143982 }, { "metric": 0.24621228873729706, "fold_fraction": 0.0, "mean_condition": 1.8535460233688354, "min_det": 0.4599893093109131 }, { "metric": 0.2530094385147095, "fold_fraction": 0.0, "mean_condition": 1.8582817316055298, "min_det": 0.46327176690101624 }, { "metric": 0.25567081570625305, "fold_fraction": 0.0, "mean_condition": 1.7491744756698608, "min_det": 0.47469472885131836 }, { "metric": 0.23396754264831543, "fold_fraction": 0.0, "mean_condition": 1.6311602592468262, "min_det": 0.5201746225357056 }, { "metric": 0.21000193059444427, "fold_fraction": 0.0, "mean_condition": 1.720042109489441, "min_det": 0.512793242931366 } ], "0.01": [ { "metric": 0.1227923184633255, "fold_fraction": 0.0, "mean_condition": 3.6080846786499023, "min_det": 0.14010927081108093 }, { "metric": 0.14947034418582916, "fold_fraction": 0.0, "mean_condition": 4.363121032714844, "min_det": 0.06148712337017059 }, { "metric": 0.13802805542945862, "fold_fraction": 0.0, "mean_condition": 4.669856071472168, "min_det": 0.09186847507953644 }, { "metric": 0.15367528796195984, "fold_fraction": 0.0, "mean_condition": 3.651010751724243, "min_det": 0.1293972134590149 }, { "metric": 0.1728336662054062, "fold_fraction": 0.0, "mean_condition": 3.4115381240844727, "min_det": 0.15038658678531647 }, { "metric": 0.18583709001541138, "fold_fraction": 0.0, "mean_condition": 2.81828236579895, "min_det": 0.14253130555152893 }, { "metric": 0.14342737197875977, "fold_fraction": 0.0, "mean_condition": 3.250553846359253, "min_det": 0.1717192828655243 }, { "metric": 0.14185279607772827, "fold_fraction": 0.0, "mean_condition": 3.3935046195983887, "min_det": 0.14545558393001556 } ] } }, "device": "cpu" }