{"id":"W4386806325","doi":"10.1007/978-3-031-43430-3_15","title":"Multivariate Time-Series Anomaly Detection with Temporal Self-supervision and Graphs: Application to Vehicle Failure Prediction","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Autoencoder; Anomaly detection; Artificial intelligence; Data mining; Key (lock); Graph; Adjacency list; Heuristic; Time series; Task (project management); Machine learning; Pattern recognition (psychology); Deep learning; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005748426,0.0005758887,0.0007712212,0.0006899165,0.0002056179,0.0004779493,0.0006577721,0.0004806267,0.0007869386],"category_scores_gemma":[0.002114681,0.000276998,0.0005969498,0.001253417,0.0002897931,0.0006621734,0.0004701335,0.001030753,0.0001911553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003440747,"about_ca_system_score_gemma":0.000305491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004233642,"about_ca_topic_score_gemma":0.004455326,"domain_scores_codex":[0.9998024,0.00005071029,0.00001244302,0.0000598529,0.00005939686,0.00001534838],"domain_scores_gemma":[0.9989958,0.0006365801,0.000100493,0.00008283655,0.0001476465,0.00003653782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001756047,0.0001808727,0.002462953,0.0001025544,0.00008862808,0.0001332685,0.00007478694,0.481069,0.00815287,0.008756384,0.004944749,0.4938583],"study_design_scores_gemma":[0.000001345492,0.000009835062,0.000304036,9.163558e-7,0.000003721764,0.00001454553,0.00000259139,0.9967576,0.0003536263,0.002391198,0.0001583428,0.000002347692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03730896,0.0005231017,0.9596979,0.0001629219,0.00008946015,0.00001760314,0.0001506628,0.001306057,0.0007433827],"genre_scores_gemma":[0.7100321,0.0007341231,0.2855573,0.00006278189,0.0001759784,0.00004060033,0.0004273667,0.0002270021,0.002742711],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004233642,"threshold_uncertainty_score":0.008417964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006529374539151251,"score_gpt":0.2113251535062311,"score_spread":0.2047957789670799,"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."}}