{"id":"W3184473617","doi":"10.1007/s10489-021-02662-2","title":"Evaluation of interpretability methods for multivariate time series forecasting","year":2021,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Interpretability; Computer science; Machine learning; Artificial intelligence; Fidelity; Time series; Series (stratigraphy); Focus (optics); Multivariate statistics; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.00691671,0.0002122724,0.0003514184,0.00009299912,0.0001539426,0.0001123498,0.0009101576,0.0001048721,0.000180938],"category_scores_gemma":[0.003468319,0.0002184102,0.00013811,0.0007639434,0.0001433146,0.0005625859,0.000427267,0.000141366,0.00006376064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001465564,"about_ca_system_score_gemma":0.0003993004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003105247,"about_ca_topic_score_gemma":0.00001748236,"domain_scores_codex":[0.9971758,0.0004277463,0.0007374242,0.0007334011,0.0005225914,0.0004030433],"domain_scores_gemma":[0.9953986,0.001282542,0.0002789022,0.0009609234,0.001993182,0.00008584504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002405055,0.00008806144,0.000009406794,0.00004140454,0.00004066645,7.913978e-7,0.002111341,0.003377058,0.1010132,0.1516832,0.00001888571,0.7415919],"study_design_scores_gemma":[0.00002820996,0.00003523099,0.000009279839,0.00001741976,0.00002406329,0.000004660037,0.000208816,0.3858112,0.4677857,0.1457786,0.0001864062,0.0001104584],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003140321,0.0002168794,0.9889454,0.000170396,0.0003198696,0.0007292284,0.000004641659,0.0001043737,0.006368885],"genre_scores_gemma":[0.4426542,0.000005325062,0.5569745,0.00005452687,0.00002969387,0.0001885395,0.000004732246,0.00001234018,0.0000760917],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7414815,"threshold_uncertainty_score":0.8906509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1252773207783487,"score_gpt":0.4005119010539609,"score_spread":0.2752345802756122,"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."}}