{"id":"W4400581939","doi":"10.1145/3660812","title":"A Weak Supervision-Based Approach to Improve Chatbots for Code Repositories","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"AI in Service Interactions","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Concordia University","funders":"","keywords":"Computer science; Code (set theory); Programming language; World Wide Web; Software engineering; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0002235629,0.0002090869,0.00019193,0.0001795071,0.0000955068,0.0002981234,0.002911173,0.0000802656,0.000001075729],"category_scores_gemma":[0.002317334,0.0001430607,0.0001696149,0.0006765597,0.00001547616,0.0004143357,0.0007398153,0.0002151183,0.000008988703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056308,"about_ca_system_score_gemma":0.00005511556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009265966,"about_ca_topic_score_gemma":3.062464e-7,"domain_scores_codex":[0.9986077,0.00000195899,0.0002686829,0.000501881,0.0003416293,0.0002781348],"domain_scores_gemma":[0.9983687,0.0004115278,0.00006063113,0.0007575969,0.0003101099,0.00009147619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003555853,0.001326893,0.003428357,0.01408343,0.0008384454,0.000005535843,0.01600509,0.06184602,0.3237393,0.3485483,0.1958315,0.03399159],"study_design_scores_gemma":[0.0003966716,0.0005574832,0.0008163707,0.001326261,0.00006029087,0.00003283143,0.000151944,0.6580577,0.2404377,0.002388555,0.09502115,0.0007529667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02249483,0.0001565129,0.9627584,0.006914918,0.004505749,0.001128374,0.00005352517,0.001701496,0.000286251],"genre_scores_gemma":[0.3720495,0.000001396956,0.6262173,0.0003403587,0.0003422853,0.0004560883,0.000001743696,0.0000610083,0.0005303696],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5962117,"threshold_uncertainty_score":0.5833845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01275772109649029,"score_gpt":0.2427344071208827,"score_spread":0.2299766860243924,"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."}}