{"id":"W4409737878","doi":"10.1016/j.aei.2025.103361","title":"Prognostics of complex machinery with sparse multilabel multimodal run-to-failure data: A graph neural network approach","year":2025,"lang":"en","type":"article","venue":"Advanced Engineering Informatics","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hydro-Québec","funders":"Région Occitanie Pyrénées-Méditerranée; Ecole Nationale d'Ingénieurs de Tunis","keywords":"Prognostics; Artificial neural network; Computer science; Artificial intelligence; Graph; Machine learning; Data mining; Pattern recognition (psychology); Theoretical computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001962278,0.0004658638,0.0005585873,0.0003394013,0.00005672771,0.00004745787,0.0008151319,0.0001253062,0.00000289688],"category_scores_gemma":[0.0001236628,0.0004374266,0.00005840661,0.001017615,0.00004604279,0.0005701943,0.0003021725,0.0004707114,0.000003082796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000594324,"about_ca_system_score_gemma":0.00002277825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008746061,"about_ca_topic_score_gemma":0.00001326229,"domain_scores_codex":[0.9981253,0.00001016096,0.00079875,0.0002025981,0.0002867983,0.0005764554],"domain_scores_gemma":[0.9984031,0.0001797924,0.0001045656,0.001067299,0.0001025693,0.0001426348],"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":[0.00001818542,0.00005108638,0.001153653,0.00112856,0.0001169591,0.000002142798,0.0002247503,0.9870089,0.0004472516,0.0006402521,0.002641553,0.006566751],"study_design_scores_gemma":[0.0006523464,0.00006572397,0.002433431,0.0003357552,0.00006035946,0.000009803312,0.00004794561,0.9869289,0.0007764568,0.00001751593,0.008235606,0.0004361482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06461406,0.0001578029,0.9306964,0.00002690808,0.0002342305,0.00115565,0.0001855273,0.001674955,0.001254481],"genre_scores_gemma":[0.4328893,0.00003069377,0.5665634,0.0000662255,0.00003313951,0.0001032041,0.0002554322,0.0000521398,0.000006431799],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3682752,"threshold_uncertainty_score":0.9998078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01117978992688429,"score_gpt":0.2509937024499,"score_spread":0.2398139125230157,"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."}}