{"id":"W3187853654","doi":"","title":"Temporal Dependencies in Feature Importance for Time Series Predictions.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Feature (linguistics); Computer science; Series (stratigraphy); Time series; Artificial intelligence; Machine learning; Data mining; Multivariate statistics; Task (project management); Code (set theory); Pattern recognition (psychology)","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":[0.004655926,0.001033237,0.0007011152,0.001937137,0.0003900058,0.001112624,0.001236583,0.001466828,0.002730189],"category_scores_gemma":[0.0325729,0.0003792336,0.0009619664,0.001552595,0.000721004,0.002547255,0.001109695,0.002444468,0.0004243851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009782568,"about_ca_system_score_gemma":0.0008805022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003177461,"about_ca_topic_score_gemma":0.003965088,"domain_scores_codex":[0.9985147,0.0006889192,0.0001020741,0.0003795598,0.000235401,0.00007927925],"domain_scores_gemma":[0.9817811,0.01511901,0.001355914,0.0009010441,0.0005407278,0.0003022584],"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":[0.0006885154,0.0002526653,0.04837066,0.0005283906,0.0004735128,0.0004224901,0.0004400597,0.4824164,0.003715913,0.05117118,0.01177659,0.3997436],"study_design_scores_gemma":[0.00001784171,0.00005127201,0.003587165,0.00002862398,0.00002876831,0.00007504632,0.00002295564,0.9564607,0.0007209439,0.03807045,0.0009214325,0.00001485239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05699985,0.00184434,0.9363314,0.001292595,0.0001465235,0.00008612932,0.0007747774,0.001273519,0.00125089],"genre_scores_gemma":[0.8588235,0.0006278263,0.1365955,0.0002735404,0.0003123253,0.0001333992,0.001611467,0.0001671674,0.001455322],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004655926,"threshold_uncertainty_score":0.02462322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05508152365558667,"score_gpt":0.1980822921425934,"score_spread":0.1430007684870068,"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."}}