{"id":"W4389524264","doi":"10.18653/v1/2023.findings-emnlp.26","title":"CR-COPEC: Causal Rationale of Corporate Performance Changes to learn from Financial Reports","year":2023,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Colorado Power Electronics Center, University of Colorado Boulder","keywords":"Computer science; Causal analysis; Adaptation (eye); Sentence; Accounting; Scale (ratio); Affect (linguistics); Business; Artificial intelligence; Risk analysis (engineering); Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002211157,0.001321244,0.0004138109,0.005642382,0.000723386,0.001331217,0.001485111,0.002013962,0.003887657],"category_scores_gemma":[0.01631662,0.0002839183,0.001362339,0.002593926,0.0005564136,0.002196342,0.001074161,0.001938336,0.001800534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139846,"about_ca_system_score_gemma":0.001875057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008844637,"about_ca_topic_score_gemma":0.01911662,"domain_scores_codex":[0.9982871,0.0004666419,0.0001981774,0.0005080837,0.0004258145,0.0001141987],"domain_scores_gemma":[0.9889898,0.006768486,0.001244269,0.001402079,0.001279999,0.0003152555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001090714,0.00128746,0.1028392,0.005197127,0.0008272319,0.003373228,0.001497225,0.03064013,0.02344534,0.01710422,0.4050533,0.4076449],"study_design_scores_gemma":[0.0005431038,0.0007279019,0.146509,0.001297195,0.0007697963,0.003297338,0.002081118,0.3405373,0.03033923,0.03841373,0.4350651,0.0004192524],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.225906,0.01050065,0.1292661,0.005525744,0.00180387,0.001846554,0.5889916,0.01702964,0.01912989],"genre_scores_gemma":[0.2648195,0.001602119,0.1400052,0.001043553,0.0005414373,0.001182438,0.5865396,0.0003801202,0.003886007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008844637,"threshold_uncertainty_score":0.01758635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.241610827591023,"score_gpt":0.3914695962124666,"score_spread":0.1498587686214437,"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."}}