{"id":"W4399880449","doi":"10.1093/rfs/hhae029","title":"Computational Reproducibility in Finance: Evidence from 1,000 Tests","year":2024,"lang":"en","type":"article","venue":"Review of Financial Studies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cascades (Canada)","funders":"Riksbankens Jubileumsfond; Vermont Agency of Natural Resources; Knut och Alice Wallenbergs Stiftelse; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Agence Nationale de la Recherche","keywords":"Reproducibility; Overconfidence effect; Coding (social sciences); Computer science; Code (set theory); Psychology; Statistics; Mathematics; Social 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00256199,0.0001730178,0.0005642309,0.00008673109,0.00007886544,0.00003949416,0.0006555077,0.00004042386,0.00001487509],"category_scores_gemma":[0.008283358,0.0001493392,0.0001250189,0.001381926,0.0001558817,0.0006489202,0.0003858953,0.0001748533,0.00009923128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001448981,"about_ca_system_score_gemma":0.0002804045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003222962,"about_ca_topic_score_gemma":0.0001461807,"domain_scores_codex":[0.9972772,0.0001495562,0.0008000339,0.001146383,0.0003760612,0.0002507872],"domain_scores_gemma":[0.9973241,0.001142778,0.0001331755,0.001038791,0.0003342783,0.00002686197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001290893,0.0001876811,0.006789584,0.01383354,0.0000481914,0.0001985405,0.004657682,0.001162335,0.0001424066,0.07962809,0.02005417,0.8732849],"study_design_scores_gemma":[0.000171588,0.0004638443,0.2265232,0.2499168,0.00008997545,0.00002007391,0.0001201472,0.02113215,0.006749463,0.4182517,0.07529476,0.001266314],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.04102318,0.9401248,0.01280985,0.00454729,0.0007473008,0.0004773712,0.0000139498,0.00009547557,0.0001607945],"genre_scores_gemma":[0.5442932,0.431693,0.02273743,0.0008316806,0.0002173395,0.0001228544,0.000003090231,0.00001164424,0.00008973443],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8720186,"threshold_uncertainty_score":0.9916552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09613543887438811,"score_gpt":0.3888556883459117,"score_spread":0.2927202494715235,"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."}}