{"id":"W4400582900","doi":"10.1145/3643774","title":"AI-Assisted Code Authoring at Scale: Fine-Tuning, Deploying, and Mixed Methods Evaluation","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Code (set theory); Scale (ratio); Programming language; Geography; Cartography","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":[0.02933411,0.001918782,0.0007821088,0.001645065,0.0009150905,0.002164564,0.003863279,0.002145552,0.002949158],"category_scores_gemma":[0.1036975,0.0008998648,0.001222399,0.001085485,0.001917675,0.002918343,0.003911733,0.003461362,0.00139948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001635361,"about_ca_system_score_gemma":0.002205478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007079716,"about_ca_topic_score_gemma":0.008663188,"domain_scores_codex":[0.985292,0.009986321,0.0009595599,0.001471517,0.00184859,0.0004419814],"domain_scores_gemma":[0.8608415,0.113594,0.002022776,0.01395802,0.007760521,0.001823297],"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":[0.004555324,0.005040111,0.0458971,0.003934852,0.001111779,0.0006486617,0.007724445,0.2429437,0.02244703,0.01624433,0.0344701,0.6149826],"study_design_scores_gemma":[0.001243272,0.001438909,0.006654484,0.000372305,0.0002223843,0.0001537621,0.001214042,0.9453399,0.0132947,0.01354026,0.01639692,0.0001290181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5437647,0.003271266,0.3832335,0.0024563,0.0007062853,0.003122563,0.002345388,0.04594987,0.01515006],"genre_scores_gemma":[0.5328169,0.0003961342,0.4541804,0.0007545791,0.000083789,0.002540886,0.003033073,0.003882476,0.002311745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02933411,"threshold_uncertainty_score":0.1551355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03305225606870409,"score_gpt":0.3336914157279161,"score_spread":0.300639159659212,"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."}}