{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001199057,0.00006075657,0.00006854397,0.0001537063,0.0000426578,0.00004285387,0.0002379487,0.00004922833,0.00001266704],"category_scores_gemma":[0.0002208163,0.00005552554,0.00003565681,0.0002405637,0.00001013507,0.001591593,0.0000598151,0.00003848426,0.000006856404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006664515,"about_ca_system_score_gemma":0.00004663625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002796473,"about_ca_topic_score_gemma":0.000005636111,"domain_scores_codex":[0.9989315,0.00002687947,0.0001858052,0.00009330095,0.0005913957,0.0001711303],"domain_scores_gemma":[0.9989381,0.0001764079,0.00004745263,0.0002684924,0.0005456037,0.00002393134],"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":[0.00002801,0.0002285764,0.009722488,0.0004186523,0.00002694762,1.259745e-7,0.006175392,0.2971261,0.0001662393,0.5219797,0.005255372,0.1588723],"study_design_scores_gemma":[0.0004199353,0.00003990006,0.01188602,0.00001173841,0.000006131138,7.894374e-7,0.00001985436,0.9522579,0.0008413885,0.0343164,0.0001487052,0.00005118412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01981444,0.00004288698,0.9786528,0.00007306389,0.0001516936,0.0006487233,0.00002248505,0.0002542188,0.0003396531],"genre_scores_gemma":[0.9298657,0.00000223389,0.06965974,0.00002218174,0.00005770224,0.000307166,0.00005218365,0.00000495531,0.00002811021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9100513,"threshold_uncertainty_score":0.2264266,"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."}}