{"id":"W4319335604","doi":"10.1016/j.eswa.2023.119619","title":"SAITS: Self-attention-based imputation for time series","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":442,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ciena (Canada); Concordia University","funders":"Beijing Jiaotong University; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Imputation (statistics); Missing data; Artificial intelligence; Data mining; Multivariate statistics; Series (stratigraphy); Time series; Machine learning; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002109239,0.0001242478,0.0001656213,0.0001392437,0.0004227601,0.0002354066,0.0003410108,0.00004283637,0.000004945926],"category_scores_gemma":[0.000008339087,0.000102345,0.00006914049,0.001051524,0.0000215953,0.0003304098,0.00003644879,0.00003322751,0.0002562001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004594839,"about_ca_system_score_gemma":0.00007160474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003555897,"about_ca_topic_score_gemma":0.000004792928,"domain_scores_codex":[0.9989272,0.00002471871,0.0002612376,0.000360976,0.0001942299,0.0002316471],"domain_scores_gemma":[0.9990027,0.0001046665,0.0001546753,0.0004569466,0.0002096299,0.00007138597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001045578,0.0007390373,0.002216819,0.0008953372,0.00104655,0.00001346656,0.007652969,0.1240219,0.02466408,0.6534738,0.1148536,0.07031789],"study_design_scores_gemma":[0.0003014312,0.00009295084,0.0003184782,0.00003378971,0.00001535672,0.000008589775,0.0002979409,0.8613606,0.0001947672,0.0002157137,0.1369331,0.0002272721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004754992,0.0001104601,0.9957479,0.001195924,0.00006338669,0.000941996,0.00001625577,0.000953818,0.0004947116],"genre_scores_gemma":[0.5453821,0.00002328208,0.4222449,0.0003559467,0.0009124274,0.02097931,0.000759392,0.0001121744,0.009230397],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7373388,"threshold_uncertainty_score":0.4173508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009208493889557967,"score_gpt":0.2370432656503537,"score_spread":0.2278347717607958,"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."}}