{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00237663,0.0003336124,0.0003138194,0.0004383324,0.0001531856,0.0003357174,0.002346367,0.0001561023,0.00001096867],"category_scores_gemma":[0.0166826,0.0002742603,0.0001385492,0.001288173,0.00005999302,0.0005159121,0.002427064,0.000583661,0.00001076702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003396593,"about_ca_system_score_gemma":0.0000790669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008301429,"about_ca_topic_score_gemma":0.000001712784,"domain_scores_codex":[0.9973919,0.00002928687,0.0003767174,0.0007191793,0.0009884275,0.0004944491],"domain_scores_gemma":[0.9970219,0.00147976,0.0000910207,0.0008599635,0.0003730807,0.0001742669],"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":[0.00008696741,0.0002242327,0.1148592,0.005965244,0.0008011685,0.00002305057,0.004897834,0.01447015,0.19129,0.01069668,0.09615499,0.5605305],"study_design_scores_gemma":[0.0006662304,0.0002160255,0.1859627,0.001856717,0.0001296256,0.0001886333,0.00002036611,0.5986962,0.1950799,0.001505308,0.01477106,0.0009072429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.729858,0.002880026,0.2573054,0.002791657,0.002856607,0.000805959,0.00001231323,0.003440643,0.00004931101],"genre_scores_gemma":[0.565814,0.00001919927,0.4334661,0.00007239023,0.0001291885,0.0001457988,0.000001721287,0.0000988727,0.000252832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.584226,"threshold_uncertainty_score":0.999971,"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."}}