From 5dcd29000579d9dea626b47f84aa3fdc16700605 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 12:41:18 -0500 Subject: results: close Oral-A v2 causal-capture gate --- results/oral_a_v2_calibration_gate.json | 147 ++++++++++++++++++++++++++++++++ 1 file changed, 147 insertions(+) create mode 100644 results/oral_a_v2_calibration_gate.json (limited to 'results/oral_a_v2_calibration_gate.json') diff --git a/results/oral_a_v2_calibration_gate.json b/results/oral_a_v2_calibration_gate.json new file mode 100644 index 0000000..1ffc605 --- /dev/null +++ b/results/oral_a_v2_calibration_gate.json @@ -0,0 +1,147 @@ +{ + "checks": { + "all_six_records_finite": true, + "both_modes_selected": true, + "structured_all_layer_at_least_0.01": true, + "structured_early_gain_over_unit_at_least_0.01": false, + "structured_early_third_at_least_0.01": false + }, + "confirmation_test_seeds_touched": false, + "protocol": "oral_a_v2_causal_capture_v1", + "review_score_after": 5, + "review_score_before": 5, + "rows": [ + { + "calibration_mode": "channel_subspace", + "eta_A": 0.01, + "finite": true, + "metric_space": "channel_basis_moments", + "metrics": { + "all_layer_alignment": 0.05273995646520665, + "early_third_alignment": 0.007209055746595065, + "mean_calibration_mse": 0.2708950854477958, + "mean_parameter_update_rms": 0.011981565658686305, + "mean_prediction_target_cosine": 0.00018159585958168355, + "mean_target_power": 0.2708926473589623 + }, + "path": "results/oral_a_v2_calibration/channel_subspace_etaA0.01.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + }, + { + "calibration_mode": "channel_subspace", + "eta_A": 0.1, + "finite": true, + "metric_space": "channel_basis_moments", + "metrics": { + "all_layer_alignment": 0.026189661456124957, + "early_third_alignment": 0.0038381816702894866, + "mean_calibration_mse": 0.27095736647643465, + "mean_parameter_update_rms": 0.012069313096218597, + "mean_prediction_target_cosine": 0.00010544442092045836, + "mean_target_power": 0.2708926473589623 + }, + "path": "results/oral_a_v2_calibration/channel_subspace_etaA0.1.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + }, + { + "calibration_mode": "channel_subspace", + "eta_A": 1.0, + "finite": true, + "metric_space": "channel_basis_moments", + "metrics": { + "all_layer_alignment": 0.003992186883758558, + "early_third_alignment": 0.001714374249180158, + "mean_calibration_mse": 0.2717085534018111, + "mean_parameter_update_rms": 0.012732941480864037, + "mean_prediction_target_cosine": -8.862524765940711e-05, + "mean_target_power": 0.2708926473589623 + }, + "path": "results/oral_a_v2_calibration/channel_subspace_etaA1.0.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + }, + { + "calibration_mode": "unit_targets", + "eta_A": 0.01, + "finite": true, + "metric_space": "full_hidden_field", + "metrics": { + "all_layer_alignment": 0.011664319529173602, + "early_third_alignment": 0.0011051012067279469, + "mean_calibration_mse": 306.8068681861785, + "mean_parameter_update_rms": 0.0, + "mean_prediction_target_cosine": -1.0456776873674686e-06, + "mean_target_power": 306.80684325786916 + }, + "path": "results/oral_a_v2_calibration/unit_targets_etaA0.01.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + }, + { + "calibration_mode": "unit_targets", + "eta_A": 0.1, + "finite": true, + "metric_space": "full_hidden_field", + "metrics": { + "all_layer_alignment": 0.00986900356426639, + "early_third_alignment": -0.0007603219904315969, + "mean_calibration_mse": 306.80736262691147, + "mean_parameter_update_rms": 0.0, + "mean_prediction_target_cosine": -8.709214493754583e-06, + "mean_target_power": 306.80684325786916 + }, + "path": "results/oral_a_v2_calibration/unit_targets_etaA0.1.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + }, + { + "calibration_mode": "unit_targets", + "eta_A": 1.0, + "finite": true, + "metric_space": "full_hidden_field", + "metrics": { + "all_layer_alignment": 0.0031812682450675454, + "early_third_alignment": -0.0031450521055376157, + "mean_calibration_mse": 306.8130476901478, + "mean_parameter_update_rms": 0.0, + "mean_prediction_target_cosine": 1.1424882244632998e-06, + "mean_target_power": 306.80684325786916 + }, + "path": "results/oral_a_v2_calibration/unit_targets_etaA1.0.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + } + ], + "score_change_rule": "mechanics/calibration alone cannot raise score", + "selected": { + "channel_subspace": { + "calibration_mode": "channel_subspace", + "eta_A": 0.01, + "finite": true, + "metric_space": "channel_basis_moments", + "metrics": { + "all_layer_alignment": 0.05273995646520665, + "early_third_alignment": 0.007209055746595065, + "mean_calibration_mse": 0.2708950854477958, + "mean_parameter_update_rms": 0.011981565658686305, + "mean_prediction_target_cosine": 0.00018159585958168355, + "mean_target_power": 0.2708926473589623 + }, + "path": "results/oral_a_v2_calibration/channel_subspace_etaA0.01.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + }, + "unit_targets": { + "calibration_mode": "unit_targets", + "eta_A": 0.01, + "finite": true, + "metric_space": "full_hidden_field", + "metrics": { + "all_layer_alignment": 0.011664319529173602, + "early_third_alignment": 0.0011051012067279469, + "mean_calibration_mse": 306.8068681861785, + "mean_parameter_update_rms": 0.0, + "mean_prediction_target_cosine": -1.0456776873674686e-06, + "mean_target_power": 306.80684325786916 + }, + "path": "results/oral_a_v2_calibration/unit_targets_etaA0.01.json", + "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6" + } + }, + "status": "failed" +} -- cgit v1.2.3