{"id":"W4319792205","doi":"10.48550/arxiv.2302.03694","title":"Characterizing Financial Market Coverage using Artificial Intelligence","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"FinTech, Crowdfunding, Digital Finance","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université TÉLUQ","funders":"Centers for Disease Control and Prevention; Tencent; Vlaamse regering; Accenture; U.S. Department of Homeland Security","keywords":"Leverage (statistics); Financial market; Market data; Finance; Financial modeling; Financial market participants; Artificial intelligence; Computer science; Indirect finance; Business","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":[],"category_scores_codex":[0.0004408782,0.0005668083,0.0005613152,0.0007810954,0.0003472547,0.0007486019,0.001050768,0.0004388745,0.0002651079],"category_scores_gemma":[0.0004101571,0.0007462374,0.0003392222,0.001384483,0.0001855104,0.001576109,0.0028019,0.0008448884,0.001139547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003186757,"about_ca_system_score_gemma":0.0001552128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007488229,"about_ca_topic_score_gemma":0.0001826565,"domain_scores_codex":[0.9973058,0.00002167698,0.0004687383,0.001330026,0.0001670567,0.0007067763],"domain_scores_gemma":[0.998243,0.00008352379,0.0007199768,0.0006941612,0.0002235761,0.00003575101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006080031,0.0003494426,0.01508535,0.00185459,0.0001634184,0.002964651,0.00008134459,0.06501377,0.0009234964,0.9021608,0.003114962,0.007680179],"study_design_scores_gemma":[0.0002098099,0.00002054724,0.009793735,0.001169781,0.0002510552,0.000005423242,0.0001411973,0.5026717,0.000356964,0.4738986,0.009535369,0.001945805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8280187,0.00001867555,0.1525111,0.0001374568,0.003168912,0.0005500522,0.00007572819,0.0007345296,0.01478483],"genre_scores_gemma":[0.995872,0.00005327491,0.0001024615,0.0003618575,0.001405188,0.000002017549,0.00009046333,0.0001028299,0.002009929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4376579,"threshold_uncertainty_score":0.9996382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.147221799940381,"score_gpt":0.2055452278072392,"score_spread":0.05832342786685815,"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."}}