{"id":"W4416830716","doi":"10.48550/arxiv.2509.22267","title":"Towards a more realistic evaluation of machine learning models for bearing fault diagnosis","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Spurious relationship; Task (project management); Bearing (navigation); Trustworthiness; Fault (geology); Fault detection and isolation","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001240082,0.0005116175,0.0007639115,0.0004065067,0.00008218344,0.00004123219,0.0005615276,0.0004839289,0.00004810388],"category_scores_gemma":[0.001347866,0.0005678068,0.0003224806,0.0002284672,0.00004289221,0.000128481,0.0005217313,0.0009374447,0.00000247147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004098952,"about_ca_system_score_gemma":0.0001483759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001409413,"about_ca_topic_score_gemma":0.0001552847,"domain_scores_codex":[0.9975346,0.0001302868,0.000756987,0.0006011342,0.0005956832,0.0003813011],"domain_scores_gemma":[0.9980226,0.0003676076,0.0002352369,0.0007594447,0.0005316417,0.00008348928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001154219,0.00006714808,0.05868505,0.002252313,0.0002420914,0.000001313365,0.000530529,0.9172876,0.0001472437,0.0002418425,0.001047799,0.0194855],"study_design_scores_gemma":[0.0004343465,0.00004149937,0.01183712,0.001299835,0.0005938796,6.97429e-7,0.0000227394,0.9709475,0.009883949,0.003905637,0.0005677655,0.0004650389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8734447,0.004879724,0.1076894,0.0003343594,0.0007576264,0.003579627,0.0009090433,0.001989739,0.006415757],"genre_scores_gemma":[0.9861448,0.001618211,0.006711131,0.00004220512,0.0001415148,0.004407729,0.0007446425,0.0001073256,0.00008240826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1127001,"threshold_uncertainty_score":0.9996774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08859138658566755,"score_gpt":0.358260096895953,"score_spread":0.2696687103102854,"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."}}