{"id":"W2142716611","doi":"10.1145/1137983.1138013","title":"Information theoretic evaluation of change prediction models for large-scale software","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Zipf's law; Computer science; Closeness; Data mining; Probabilistic logic; Software; Entropy (arrow of time); Principle of maximum entropy; Algorithm; Mathematics; Statistics; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02582177,0.001543269,0.00149365,0.003966202,0.001032739,0.002069824,0.002124312,0.002060397,0.0008002414],"category_scores_gemma":[0.08743717,0.0007064696,0.001218612,0.002250484,0.002219484,0.00539952,0.001925393,0.00192359,0.000169835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005556827,"about_ca_system_score_gemma":0.001881363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008292457,"about_ca_topic_score_gemma":0.005516973,"domain_scores_codex":[0.992074,0.004144573,0.0004130449,0.0008713373,0.002196373,0.00030059],"domain_scores_gemma":[0.8277342,0.1552096,0.006419216,0.004537793,0.004993894,0.001105341],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003140699,0.0001304134,0.007933081,0.00007709579,0.0001721632,0.00005455312,0.00009025996,0.9683796,0.0003175851,0.006402676,0.0003807712,0.01574763],"study_design_scores_gemma":[0.000007157922,0.00004607224,0.0008642592,0.000006920462,0.00001215203,0.00001326883,0.00001125918,0.9958091,0.0002113248,0.002970838,0.00003709656,0.00001052255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4983691,0.002479243,0.4917451,0.002081998,0.00009122019,0.0002353553,0.0007523927,0.001287394,0.002958133],"genre_scores_gemma":[0.9599711,0.0003335866,0.03842519,0.0001432687,0.00007761414,0.00009303115,0.0006637091,0.00004557851,0.0002469809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9741783,"threshold_uncertainty_score":0.1365603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04478003771689125,"score_gpt":0.2831079990688019,"score_spread":0.2383279613519106,"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."}}