{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000519226,0.0003848211,0.000338459,0.0004980954,0.0002228112,0.0003012597,0.002397174,0.0001620611,0.000006992582],"category_scores_gemma":[0.1061117,0.0004050402,0.0001340171,0.000863373,0.00003676182,0.0008567843,0.0007541013,0.0003151658,0.00003366992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002230771,"about_ca_system_score_gemma":0.0001027575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005027294,"about_ca_topic_score_gemma":8.881108e-7,"domain_scores_codex":[0.997345,0.00001591994,0.0004451578,0.0006821162,0.0006569296,0.0008548374],"domain_scores_gemma":[0.9429664,0.05503149,0.0001004278,0.001485425,0.0001555733,0.0002606793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009044846,0.00007698787,0.9291496,0.0002344923,0.00008251302,0.0000121519,0.002033692,0.01400489,0.0009996785,0.0004195424,0.0007755187,0.05220185],"study_design_scores_gemma":[0.001117823,0.0004481323,0.8909318,0.0003379111,0.0000341763,0.00008065289,0.00002766467,0.008176492,0.0588141,0.00001015175,0.03852018,0.001500962],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7913684,0.0005802825,0.2041574,0.0002628759,0.00100716,0.0003733143,0.000006602428,0.002242272,0.000001709815],"genre_scores_gemma":[0.6786581,0.0000143295,0.3204703,0.00004550055,0.0004747669,0.0001889093,0.000008460156,0.00005801728,0.00008169382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1163128,"threshold_uncertainty_score":0.9998401,"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."}}