{"id":"W4391094351","doi":"10.1109/bigdata59044.2023.10386503","title":"GPT in Data Science: A Practical Exploration of Model Selection","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Computer science; Data modeling; Data science; Artificial intelligence; Software engineering","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":[0.00138696,0.00003559795,0.00004901766,0.0002803949,0.00005835103,0.00007352181,0.0006102531,0.00002029423,0.000003330946],"category_scores_gemma":[0.0005652954,0.00003155284,0.000004937426,0.002124747,0.00003823172,0.004650418,0.0003558513,0.00008452068,0.00004958311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001996146,"about_ca_system_score_gemma":0.0002476571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005365555,"about_ca_topic_score_gemma":0.00005413365,"domain_scores_codex":[0.9991091,0.00003677877,0.0001410548,0.0003148676,0.0002829426,0.0001152041],"domain_scores_gemma":[0.9992274,0.00005298258,0.00005304174,0.0005781766,0.00006108424,0.00002729708],"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":[0.000008223008,0.0001168772,0.002107478,0.00001560993,0.000001916799,0.000001296997,0.0009829105,0.03563551,0.02125996,0.890884,0.004926235,0.04405992],"study_design_scores_gemma":[0.00006512809,0.00001233501,0.003229986,0.000003122959,6.254046e-7,0.000001276176,0.00004488679,0.9924026,0.000667719,0.003183715,0.0003526842,0.00003589384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006720069,0.000001150072,0.9852324,0.005036677,0.00004723959,0.00005892139,0.000001496604,0.0001534105,0.002748687],"genre_scores_gemma":[0.899415,0.00001258096,0.100223,0.00003369994,0.00001056184,0.000005221184,0.00004156659,0.00000199322,0.0002564602],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9567671,"threshold_uncertainty_score":0.3371441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2597187824055493,"score_gpt":0.4325973325874891,"score_spread":0.1728785501819398,"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."}}