{"id":"W7082246454","doi":"10.1016/j.compositesb.2025.113038","title":"Early fatigue failure detection in composites using autoencoder-based anomaly detection","year":2025,"lang":"en","type":"article","venue":"Composites Part B Engineering","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Composite number; Electrical conductor; Anomaly detection; Catastrophic failure; Fracture (geology); Fatigue testing; Structural health monitoring","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004545162,0.0006029379,0.0003760241,0.0004288745,0.0001270768,0.0001962917,0.0004244618,0.0004321404,0.0003330256],"category_scores_gemma":[0.0009241953,0.0002168862,0.0003912299,0.0001908159,0.0002334221,0.0004166154,0.0003015895,0.0005527744,0.0001815655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002483016,"about_ca_system_score_gemma":0.0002781887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002085602,"about_ca_topic_score_gemma":0.003725765,"domain_scores_codex":[0.9998657,0.00002016919,0.000006879479,0.00005075264,0.00003471124,0.00002178148],"domain_scores_gemma":[0.9996107,0.0001873403,0.00005123558,0.0000333631,0.0001050424,0.0000122692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003852759,0.0002649511,0.006479125,0.0001284296,0.00009188463,0.0002369393,0.0002309598,0.3476567,0.2154535,0.0008993953,0.0009657259,0.4272071],"study_design_scores_gemma":[0.000002838362,0.00005363043,0.002014295,0.00000449769,0.000007703528,0.00004514848,0.00001177369,0.9795275,0.01779708,0.0002393161,0.0002889551,0.000007324963],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3547221,0.0003905334,0.6418518,0.0001187422,0.00005443565,0.00004114908,0.0001021194,0.001575796,0.001143345],"genre_scores_gemma":[0.8469761,0.0001858902,0.1508881,0.00006602379,0.00002069709,0.00004892757,0.000241051,0.000054211,0.001518974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002085602,"threshold_uncertainty_score":0.004146993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01273120032350131,"score_gpt":0.2166600113361646,"score_spread":0.2039288110126633,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}