{"id":"W2081439463","doi":"10.1145/1082983.1083150","title":"Mining student CVS repositories for performance indicators","year":2005,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Engineering Research","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Set (abstract data type); Code (set theory); Quality (philosophy); Source lines of code; Data science; Work (physics); Source code; Data mining; Software engineering; Software; Engineering; Programming language","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":[0.00500648,0.0009453151,0.001036439,0.01896901,0.0005244758,0.002585433,0.00176851,0.001033321,0.0009418507],"category_scores_gemma":[0.04621628,0.0004267551,0.0006192927,0.01737681,0.0003376569,0.001785702,0.001792868,0.00107617,0.001170955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006558885,"about_ca_system_score_gemma":0.001670002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00375235,"about_ca_topic_score_gemma":0.004313254,"domain_scores_codex":[0.9931375,0.001438285,0.0009528905,0.001344423,0.002692563,0.0004343601],"domain_scores_gemma":[0.9504998,0.01775745,0.009051275,0.005503552,0.01444816,0.002739818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002897787,0.0007390824,0.7455298,0.000500226,0.0002039601,0.0003878012,0.001846604,0.004058782,0.004185851,0.0007851735,0.008948733,0.2325242],"study_design_scores_gemma":[0.00008525312,0.001074943,0.8575356,0.0003147243,0.0003450131,0.001020385,0.003289239,0.0861463,0.01767814,0.002817359,0.029472,0.0002209851],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9574885,0.0007238535,0.0183442,0.0002707485,0.00005478963,0.0002238754,0.01894838,0.001948882,0.001996804],"genre_scores_gemma":[0.936743,0.0003155802,0.02460767,0.00003833899,0.00006888676,0.0002510979,0.03608518,0.0002083343,0.001681845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01896901,"threshold_uncertainty_score":0.0264771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01484214742963994,"score_gpt":0.2662585567185968,"score_spread":0.2514164092889568,"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."}}