{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03934402,0.002088325,0.001409798,0.002006634,0.0007988788,0.00416501,0.002906645,0.003776615,0.001293213],"category_scores_gemma":[0.1126853,0.0006194285,0.001168993,0.001356001,0.002064692,0.00467675,0.004713208,0.004495264,0.0006451372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00252688,"about_ca_system_score_gemma":0.001954844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003459105,"about_ca_topic_score_gemma":0.003001238,"domain_scores_codex":[0.9713687,0.01868405,0.001603851,0.002121332,0.00561429,0.0006077831],"domain_scores_gemma":[0.9422836,0.03529284,0.003735715,0.01094305,0.006726538,0.001018358],"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":[0.0009639239,0.0006311688,0.01776414,0.0009387739,0.0005918932,0.0001920218,0.0003000652,0.8367122,0.009619982,0.01412226,0.008403443,0.1097601],"study_design_scores_gemma":[0.00005343241,0.0005040242,0.002136587,0.0001337732,0.00004494824,0.00009565173,0.0001003365,0.975251,0.006837812,0.01285176,0.001961657,0.00002898334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2366417,0.004457607,0.7420541,0.004888255,0.0005819865,0.0005382439,0.002234157,0.003709845,0.004894102],"genre_scores_gemma":[0.7777826,0.0007501355,0.2147157,0.0008709425,0.000180224,0.0003757211,0.00424575,0.0003203948,0.0007585557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03934402,"threshold_uncertainty_score":0.2080735,"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."}}