{"id":"W4413143033","doi":"10.1016/j.ijforecast.2025.07.003","title":"Optimal text-based time-series indices","year":2025,"lang":"en","type":"article","venue":"International Journal of Forecasting","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec-Société et Culture","keywords":"Series (stratigraphy); Time series; Econometrics; Computer science; Economics; Machine learning; 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":[0.00075653,0.00007758541,0.0002008318,0.0003755869,0.00004790618,0.0001091985,0.0003500086,0.00004545289,0.0004459587],"category_scores_gemma":[0.0004929916,0.00008131673,0.0001308512,0.0001140851,0.00003672419,0.0002709157,0.0000492196,0.0001483939,0.00001283981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009695443,"about_ca_system_score_gemma":0.00005547389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001900101,"about_ca_topic_score_gemma":0.000004699225,"domain_scores_codex":[0.9990467,0.00001024245,0.0006579824,0.0001089087,0.00006739137,0.0001087697],"domain_scores_gemma":[0.9989388,0.0001182446,0.0006511395,0.00007086006,0.0001877807,0.00003319909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006028983,0.000261628,0.8693997,0.00005635597,0.0006840028,0.00009641129,0.0002806522,0.006283169,0.0001055506,0.08513293,0.002606581,0.03449015],"study_design_scores_gemma":[0.001521985,0.0001560338,0.04238569,0.0002833742,0.00001679917,0.00006844255,0.00006636322,0.8510491,0.0002377191,0.04124064,0.06271254,0.0002613061],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8816383,0.0007610996,0.04981503,0.002552277,0.001893787,0.00006570755,0.00008680816,0.00001374526,0.06317325],"genre_scores_gemma":[0.9885781,0.00001160741,0.009770479,0.0001397431,0.000162851,0.000001115547,0.000005163547,0.000006309164,0.001324676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.844766,"threshold_uncertainty_score":0.4882935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02245109836544681,"score_gpt":0.2435335135979772,"score_spread":0.2210824152325304,"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."}}