{"id":"W4410427524","doi":"10.1109/tai.2025.3570676","title":"Leveraging Long-Term Multivariate History Representation for Time Series Forecasting","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Mitacs","keywords":"Term (time); Multivariate statistics; Series (stratigraphy); Representation (politics); Computer science; Time series; Econometrics; Artificial intelligence; Machine learning; Mathematics; Political science; Geology","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":[0.0003049511,0.0001921202,0.0002312268,0.0003048567,0.0004664525,0.0001703364,0.0004562979,0.00007370883,0.0001235102],"category_scores_gemma":[0.00004241527,0.0002028271,0.0002174755,0.0005525622,0.00008495523,0.0006825366,0.00000749624,0.0001745589,0.00006114281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002270381,"about_ca_system_score_gemma":0.00009562207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008685754,"about_ca_topic_score_gemma":0.00007057038,"domain_scores_codex":[0.9983656,0.00005866895,0.0005181783,0.0005527328,0.0001785141,0.0003263427],"domain_scores_gemma":[0.9988757,0.0002899622,0.0001457462,0.0004377057,0.0001889222,0.00006197787],"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":[0.0001294679,0.0001656469,0.00001612674,0.00004347413,0.000107473,0.000008396072,0.001775294,0.06592952,0.01204379,0.008781068,0.0001146433,0.9108851],"study_design_scores_gemma":[0.00004822408,0.00009321691,0.00006012687,0.00009556576,0.00004853551,0.000006606881,0.0001049136,0.8311777,0.1635195,0.00434717,0.0002608498,0.000237641],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003710977,0.00005054696,0.9934671,0.0004039807,0.001241182,0.0003013047,0.00000466542,0.0002009441,0.0006192877],"genre_scores_gemma":[0.9576065,0.00001007627,0.03742467,0.0001632927,0.00006942201,0.00009023285,0.000004014178,0.00001641383,0.004615363],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9560425,"threshold_uncertainty_score":0.8271049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08926465082639921,"score_gpt":0.3037478091007902,"score_spread":0.214483158274391,"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."}}