{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008253757,0.0002659631,0.0004632718,0.0004275831,0.0009415326,0.000116921,0.0006609153,0.0006850684,0.003260821],"category_scores_gemma":[0.0002111227,0.0002874197,0.0002099993,0.0006510702,0.0002787074,0.0002058732,0.00007144378,0.0006634386,0.0003111385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002763475,"about_ca_system_score_gemma":0.0005614042,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2814336,"about_ca_topic_score_gemma":0.6702462,"domain_scores_codex":[0.9976147,0.0006270172,0.0001623893,0.0005422428,0.0006043797,0.000449213],"domain_scores_gemma":[0.9988992,0.0001061254,0.0002763317,0.0003004514,0.0002304471,0.000187452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000120335,0.00004541025,0.00009459534,0.0003668808,0.0002096405,0.0005066309,0.9526895,0.00002816726,0.02029913,0.005331037,0.0101857,0.01012295],"study_design_scores_gemma":[0.0004498702,0.000169932,0.0007751585,0.0005268045,0.0004213048,0.000002220113,0.915783,0.0001715978,0.001917179,0.001009988,0.07812969,0.000643176],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.9673584,0.0004644336,0.00001891966,0.001233302,0.001158984,0.0003241647,0.0000210516,0.0003660265,0.02905478],"genre_scores_gemma":[0.02919339,0.0001077179,0.005097616,0.00001953029,0.0001990169,7.11124e-7,0.0004400764,0.00004871083,0.9648932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9381649,"threshold_uncertainty_score":0.9999578,"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."}}