{"id":"W3100210912","doi":"","title":"What went wrong and when? Instance-wise feature importance for time-series black-box models","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Black box; Computer science; Series (stratigraphy); Feature (linguistics); Time series; Artificial intelligence; Machine learning","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":[0.005091877,0.0007996834,0.001653662,0.0006148369,0.0002951906,0.001332642,0.001309623,0.001567816,0.001811002],"category_scores_gemma":[0.02298787,0.0004608764,0.0006503946,0.0005548923,0.001044527,0.003369625,0.0009894652,0.002558755,0.0002145616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006610479,"about_ca_system_score_gemma":0.0005660612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001812166,"about_ca_topic_score_gemma":0.001885493,"domain_scores_codex":[0.9990344,0.0003893645,0.00005068149,0.000283948,0.0001262912,0.0001153867],"domain_scores_gemma":[0.9896444,0.008699414,0.0005105007,0.0005163723,0.0003868097,0.0002424646],"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":[0.001013261,0.0002753958,0.01521458,0.000342357,0.0003959021,0.0004255545,0.0002839997,0.7407897,0.005269103,0.06895701,0.004038766,0.1629943],"study_design_scores_gemma":[0.000006946176,0.00001913748,0.0004481674,0.000008257595,0.00001442162,0.00002034638,0.000005796611,0.980808,0.0003388306,0.01824165,0.00008193518,0.000006425633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2010448,0.001284653,0.792915,0.002357977,0.0002195066,0.00006257739,0.0002333896,0.0005706548,0.001311438],"genre_scores_gemma":[0.9660143,0.0002881486,0.03218439,0.0001608017,0.0001299996,0.00003323443,0.0002094483,0.000057908,0.0009217828],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005091877,"threshold_uncertainty_score":0.02692872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03220889811413114,"score_gpt":0.2498583712261862,"score_spread":0.2176494731120551,"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."}}