{"id":"W6980579731","doi":"","title":"Classifying Code as Human Authored or GPT-4 Generated","year":2024,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"French Language Learning Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Classifier (UML); Coding (social sciences); Stylometry; Code (set theory); Genetic programming; Source code; Raising (metalworking); Generative grammar; Computer programming","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":[0.002254846,0.0006163706,0.000343671,0.003463252,0.0005198744,0.001803563,0.0007857737,0.00111691,0.001981764],"category_scores_gemma":[0.02790817,0.0001939539,0.0005046952,0.002083612,0.0008628194,0.001966649,0.001285764,0.001135849,0.002436682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009846775,"about_ca_system_score_gemma":0.0009008513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001865054,"about_ca_topic_score_gemma":0.004690441,"domain_scores_codex":[0.9966912,0.0007781683,0.0002525064,0.0007369735,0.00136331,0.0001778499],"domain_scores_gemma":[0.9794697,0.009820047,0.002337566,0.004219582,0.003665358,0.0004877928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007353406,0.0005824334,0.150325,0.001324894,0.0001493788,0.0006867482,0.003071075,0.015763,0.02070119,0.01502937,0.0760581,0.7155734],"study_design_scores_gemma":[0.0001810916,0.0008610887,0.1267515,0.0006516727,0.0001051347,0.002619365,0.004333997,0.4667365,0.1019517,0.03124037,0.2643091,0.0002584794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.844649,0.0009349575,0.1083708,0.001355366,0.0005257477,0.0004597644,0.01061009,0.01425461,0.01883961],"genre_scores_gemma":[0.805244,0.0004932486,0.1450741,0.0006404926,0.0001055515,0.0004715495,0.03109673,0.001722475,0.01515189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003463252,"threshold_uncertainty_score":0.01192492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03924541561172725,"score_gpt":0.3219158172764362,"score_spread":0.282670401664709,"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."}}