{"id":"W4401880391","doi":"10.1109/compsac61105.2024.00027","title":"Detecting LLM-Generated Text in Computing Education: Comparative Study for ChatGPT Cases","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Multimedia","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":[0.006944716,0.0007346979,0.0006438384,0.006103431,0.001061901,0.001877997,0.001168476,0.001674233,0.001563075],"category_scores_gemma":[0.1009746,0.0003417364,0.0006207272,0.002270834,0.001643032,0.002813329,0.002220546,0.001585378,0.001388294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009985466,"about_ca_system_score_gemma":0.0009086052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002521603,"about_ca_topic_score_gemma":0.004692416,"domain_scores_codex":[0.9875587,0.005139193,0.001221896,0.002250332,0.0032906,0.0005392969],"domain_scores_gemma":[0.8194816,0.1406597,0.01150655,0.01154876,0.01331882,0.003484556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003217903,0.002739111,0.561359,0.004389908,0.0005772355,0.01045429,0.02156713,0.01162176,0.02673045,0.002223013,0.02884183,0.3262783],"study_design_scores_gemma":[0.0003381934,0.003130158,0.5863318,0.001218478,0.0006116756,0.01724507,0.02146271,0.2522394,0.07052694,0.005554121,0.04081738,0.0005239674],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865791,0.0006828983,0.006152116,0.0003933137,0.0001395871,0.0002460446,0.001798491,0.001964656,0.002043729],"genre_scores_gemma":[0.9819493,0.0002370338,0.01051192,0.0002196067,0.00009193985,0.0001401831,0.004933472,0.0003198893,0.001596746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006944716,"threshold_uncertainty_score":0.03672761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3591134839477853,"score_gpt":0.5346117290447288,"score_spread":0.1754982450969435,"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."}}