Moltex v2 — 20261020 / 043024_429946c6

14 datasets · 6 designs · 0 scored records

Training status: completed_with_weak_training · 140 trained prediction records · 9 folds with epoch losses

PNG results, losses & training diagnosis · CAD / scan / label / model-input visualizer

— = no valid score. Diagnostic and training-fit outputs are separate from unseen-design evaluation.

Average scores

Individual and detailed scores

Individual scores · Detailed predictions/targets · Data and code provenance

Explanations

{'evaluation_protocols': {'leave_one_design_out': 'All records sharing a design-file SHA256 are held out together. Fit and preprocessing statistics use training records only.', 'per_design': "Fit each design's reviewed records and evaluate those same records. This is training fit only.", 'train_all': 'Experimental fit on eligible automatic scan-projected weak labels. Predictions are training-fit diagnostics, not independently reviewed accuracy.', 'diagnostic': 'Untrained actual-input forward passes. No accuracy is calculated.'}, 'data_selection': 'CAT/Excel/CSV/PLY complete matches from live moltex-data rules; CSV is mandatory, including OK records.', 'targets': 'Automatic scan_projected_weak CAD-node targets from CSV pixels, measured height rasters and proper rigid scan-to-CAD fits. Unannotated covered nodes outside defect buffers are assumed negative.', 'scores': 'Independently reviewed accuracy is unavailable for weak supervision. Real optimizer epoch losses and checkpoints are saved; weak-label predictions never enter reviewed score averages.', 'averaging': 'Macro means are per dataset, not per node. Unscored records never enter the average.', 'uncertainty': 'GP posterior standard deviations are available when fitted. Other models have no calibrated uncertainty claim.', 'deformation': 'Physics GNN deformation/type heads are not supervised by this node-risk contract and are not scored.', 'limitations': 'Raster calibration and registration are inferred and unreviewed. CSV source conflicts and poor-overlap cases are recorded. Datasets with failed projection gates are excluded from weak training. All source records are NG; unannotated regions are not reviewed healthy.', 'statuses': {'untrained_diagnostic': 126, 'completed': 140, 'requires_training_labels': 14}, 'failures': [{'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'AC28_DT_RR_FRT_UPR_LH_07d0fbeba5ef', 'dataset_id': 'AC28_DT_FRT_UPR_LHD_20260909_15_15__NG_a22f7d301de4', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'AC28_DT_RR_UPR_STD_6f8b270d95b5', 'dataset_id': 'AC28_DT_RR_UPR_STD_1_20260827_18_01__NG_7194c0e36c7b', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'AC28_DT_RR_UPR_STD_6f8b270d95b5', 'dataset_id': 'AC28_DT_RR_UPR_STD_20260827_16__NG_008adde420f0', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'AC28_DT_RR_UPR_STD_6f8b270d95b5', 'dataset_id': 'AC28_DT_RR_UPR_STD_20260828_09_21__NG_f4c68f38e467', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'AC28_DT_RR_UPR_STD_6f8b270d95b5', 'dataset_id': 'AC28_DT_RR_UPR_STD_2_20260827_18_01__NG_8df93616f7ea', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'LT2_DT_FRT_AREST_IMG-261014_35afb132841b', 'dataset_id': 'LT2_DT_FRT_AREST2_20260914_15_10__NG_243895937535', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'ME1a_DT_FRT_UPR_LHD_94719179587d', 'dataset_id': 'ME1a_DT_FRT_UPR_LHD_20260608_14_06__NG_ffc4fce5d996', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'MX5a_PE_DT_RR_ARMREST_LRH_261014_3e74cd458a06', 'dataset_id': 'MX5a_PE_DT_RR_AREST_1_20260626_13_08__NG_fe0e1b9b8b53', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'MX5a_PE_DT_RR_ARMREST_LRH_261014_3e74cd458a06', 'dataset_id': 'MX5a_PE_DT_RR_AREST_2_20260626_13_08__NG_41ec5d7a218e', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'NX5___RR_DT_UPR_2_CUR_TPO___261014_d11283a03a71', 'dataset_id': 'NX5_DT_RR_UPR-2_CUR_1_20260916_10_40__NG_1f98f526a60c', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'NX5___RR_DT_UPR_2_CUR_TPO___261014_d11283a03a71', 'dataset_id': 'NX5_DT_RR_UPR-2_CUR_1_20260916_10_53__NG_b3a8f50d89ae', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'NX5___RR_DT_UPR_2_CUR_TPO___261014_d11283a03a71', 'dataset_id': 'NX5_DT_RR_UPR-2_CUR_1_20260916_11_40__NG_1b598f48d4e1', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'NX5___RR_DT_UPR_2_CUR_TPO___261014_d11283a03a71', 'dataset_id': 'NX5_DT_RR_UPR-2_CUR_2_20260916_10_40__NG_4debd31ebf8a', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}, {'model_id': 'gaussian_process', 'protocol': 'diagnostic', 'design_id': 'NX5___RR_DT_UPR_2_CUR_TPO___261014_d11283a03a71', 'dataset_id': 'NX5_DT_RR_UPR-2_CUR_2_20260916_10_53__NG_a9e70207f7eb', 'status': 'requires_training_labels', 'reason': 'GP requires a fitted training posterior; no random/synthetic prior score emitted'}]}