{"id":"W6967140673","doi":"10.48448/r92r-p008","title":"Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Variety (cybernetics); Benchmark (surveying); Domain (mathematical analysis); Range (aeronautics); Empirical research; Financial modeling","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":[0.003123272,0.001750264,0.0009209136,0.001181836,0.0007548227,0.002800908,0.002698315,0.002832602,0.01346387],"category_scores_gemma":[0.01523154,0.0005978465,0.00153199,0.001773392,0.0008439606,0.00628641,0.001949042,0.004088095,0.00758503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001508152,"about_ca_system_score_gemma":0.002460127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01223012,"about_ca_topic_score_gemma":0.02567304,"domain_scores_codex":[0.998486,0.000635776,0.00009206223,0.0004626862,0.0002112871,0.000112302],"domain_scores_gemma":[0.9941189,0.004195635,0.0001836128,0.000746514,0.0004904395,0.0002649876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000733916,0.0005998861,0.006234696,0.001510168,0.0004064321,0.0004288155,0.0005270242,0.2671249,0.002949483,0.02694684,0.2064863,0.4860514],"study_design_scores_gemma":[0.0001256841,0.00009707067,0.0007098195,0.00009578051,0.00006786365,0.0001596891,0.0001684978,0.9476979,0.002412128,0.02771561,0.02071291,0.00003704011],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1779006,0.01264581,0.6096253,0.01867441,0.003020196,0.0008066934,0.02255759,0.08014452,0.07462496],"genre_scores_gemma":[0.5018445,0.003157116,0.4242116,0.003931315,0.0006754401,0.0008313499,0.03541612,0.003983896,0.02594866],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01346387,"threshold_uncertainty_score":0.0450412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07553981387815964,"score_gpt":0.3538486378940655,"score_spread":0.2783088240159058,"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."}}