{"id":"W4416183377","doi":"10.1109/gaclm67198.2025.11231829","title":"Cluster-Based Symbolic Compression of Time Series for Scalable Forecasting and Analysis","year":2025,"lang":"","type":"article","venue":"","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Concordia University","funders":"","keywords":"Scalability; Data compression; Time series; Pipeline (software); Representation (politics); Cluster analysis; Series (stratigraphy); Key (lock); Volume (thermodynamics); Segmentation","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"],"consensus_categories":[],"category_scores_codex":[0.0009384578,0.0003922652,0.0012587,0.0009542151,0.0006603563,0.0004523583,0.0006516566,0.0001800951,0.0002184412],"category_scores_gemma":[0.000199661,0.0003463951,0.0006307056,0.003850648,0.0002807722,0.000644331,0.0007067041,0.0001335207,0.000002991894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000381819,"about_ca_system_score_gemma":0.0001731368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001857155,"about_ca_topic_score_gemma":0.00007700351,"domain_scores_codex":[0.996905,0.0001312213,0.001149924,0.0008946154,0.0003139315,0.0006053475],"domain_scores_gemma":[0.9972556,0.0007039417,0.0005784647,0.0007685433,0.0005445706,0.0001488897],"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":[0.001275549,0.001006895,0.0550715,0.004222188,0.01043523,0.000008248143,0.002446766,0.2881384,0.007371033,0.03865723,0.004121698,0.5872452],"study_design_scores_gemma":[0.0008124572,0.0002632079,0.001050633,0.0003578882,0.001932816,0.000001667122,0.0001225938,0.9876633,0.005892368,0.0007108941,0.0008807207,0.0003114837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03408905,0.0008756706,0.9582406,0.0009905597,0.0001419857,0.0004993984,0.00004804882,0.00006352043,0.005051218],"genre_scores_gemma":[0.8497072,0.00003350511,0.1388861,0.000214059,0.0000421848,0.00002684159,0.00003548002,0.00001745048,0.01103721],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8193545,"threshold_uncertainty_score":0.9998988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01592125685822614,"score_gpt":0.2420274973132799,"score_spread":0.2261062404550537,"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."}}