{"id":"W6892667994","doi":"10.5281/zenodo.11124223","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":"Scientific Computing and Data Management","field":"Decision Sciences","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":[0.01975089,0.0005530355,0.0004013387,0.001470817,0.001587088,0.005332721,0.001699588,0.001689314,0.005366953],"category_scores_gemma":[0.2285163,0.0007519908,0.000628053,0.002129156,0.004247347,0.01567672,0.00315755,0.00490949,0.001161054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001339251,"about_ca_system_score_gemma":0.001769436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002496293,"about_ca_topic_score_gemma":0.002352537,"domain_scores_codex":[0.9764535,0.01349648,0.0009680394,0.001834535,0.006328746,0.0009185759],"domain_scores_gemma":[0.6164908,0.3308873,0.01556219,0.02617286,0.00777516,0.003111636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006332923,0.007259492,0.4011295,0.001890394,0.0004625799,0.004076107,0.0804576,0.02959637,0.01818505,0.1589811,0.02613088,0.2654981],"study_design_scores_gemma":[0.0006038733,0.004577193,0.1841076,0.002030866,0.0007461118,0.00991507,0.1188814,0.2413061,0.02109861,0.3263049,0.08999945,0.0004288403],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554031,0.0004085327,0.02146784,0.005584129,0.00004272952,0.0002392242,0.0007528534,0.0004817976,0.01561982],"genre_scores_gemma":[0.9897763,0.0002104518,0.007456462,0.000420578,0.00003922793,0.0001392096,0.000524082,0.0003361567,0.001097648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01975089,"threshold_uncertainty_score":0.104454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1984956063767667,"score_gpt":0.3774778309615135,"score_spread":0.1789822245847467,"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."}}