{"id":"W6966544521","doi":"10.48448/h67n-3175","title":"TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Event (particle physics); Time series; Context (archaeology); Series (stratigraphy); Language model; Encoder; Data modeling","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00104838,0.0006003263,0.0005962219,0.001314635,0.0004132123,0.0002029937,0.000915122,0.00020466,0.001604205],"category_scores_gemma":[0.0002877626,0.0005107166,0.00004410319,0.001400514,0.0006402607,0.0004112748,0.0007865322,0.0004359414,0.002262654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002619753,"about_ca_system_score_gemma":0.0009551598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002547035,"about_ca_topic_score_gemma":0.0006124795,"domain_scores_codex":[0.9959627,0.0001067001,0.000349446,0.001263069,0.001324537,0.0009934884],"domain_scores_gemma":[0.9983605,0.00003770759,0.0003252868,0.0006822952,0.0001789118,0.0004152724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004771889,0.000724052,0.003262957,0.0003970466,0.0005596529,0.0001495086,0.006106265,0.008604699,0.008062406,0.004075251,0.9617582,0.00582275],"study_design_scores_gemma":[0.006354612,0.001379464,0.000526459,0.004264947,0.0005174989,0.00007076097,0.003278516,0.4981842,0.0008041787,0.0004277373,0.4809257,0.003265924],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.005569004,0.0009238514,0.01781543,0.0003466286,0.000307703,0.003036967,0.003336196,0.002240759,0.9664235],"genre_scores_gemma":[0.0165239,0.00002734123,0.009240438,0.0003891366,0.00009192531,0.00004863636,0.0002568996,0.000512267,0.9729095],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4895795,"threshold_uncertainty_score":0.9997345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01032774339058176,"score_gpt":0.2876978458658168,"score_spread":0.2773701024752351,"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."}}