{"id":"W6910986835","doi":"10.5281/zenodo.11125279","title":"Are Large Language Models a Threat to Programming Platforms? An Exploratory Study","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Exploratory research; Scripting language; Natural language; Key (lock); Semantics (computer science)","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":[0.01416327,0.0004617771,0.0003193567,0.001405989,0.001573285,0.003871862,0.001303343,0.001459611,0.004985358],"category_scores_gemma":[0.1609611,0.000663133,0.0005014901,0.001684494,0.003919116,0.01041765,0.002857883,0.004098812,0.001176662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116774,"about_ca_system_score_gemma":0.001306367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001617491,"about_ca_topic_score_gemma":0.001642862,"domain_scores_codex":[0.9839317,0.009730983,0.0006727771,0.001198341,0.00386778,0.0005984879],"domain_scores_gemma":[0.6978332,0.25959,0.01516244,0.01887805,0.005680842,0.002855444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005039726,0.008831618,0.5093977,0.001875718,0.000349441,0.005287484,0.1365773,0.0108213,0.01785192,0.09421095,0.01916635,0.1905906],"study_design_scores_gemma":[0.0005901427,0.006926242,0.3589904,0.002479268,0.0007102605,0.01643602,0.2217763,0.08828024,0.02153711,0.1767851,0.1050843,0.00040456],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.979362,0.0002598804,0.007585129,0.002360233,0.00001723728,0.0001784494,0.0004536422,0.000153813,0.009629557],"genre_scores_gemma":[0.9946976,0.0001722534,0.003274216,0.0002919925,0.00002294144,0.000121758,0.0003716891,0.0001329499,0.0009147188],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01416327,"threshold_uncertainty_score":0.07490343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05163197300563738,"score_gpt":0.2856398672925345,"score_spread":0.2340078942868971,"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."}}