{"id":"W1972886276","doi":"10.1109/scam.2010.13","title":"Validating the Use of Topic Models for Software Evolution","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Software evolution; Source code; Software maintenance; Software; Metric (unit); Software development; Task (project management); Code (set theory); Software system; Topic model; Software engineering; Data science; Software construction; Artificial intelligence; Programming language; Engineering; Systems engineering","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":[0.0002381784,0.00004427973,0.00005192096,0.0000396583,0.00005700596,0.00006743106,0.0005078639,0.00003208977,0.000005535725],"category_scores_gemma":[0.001286191,0.00002973163,0.0000349576,0.0001487819,0.00002062865,0.0003968246,0.0001421342,0.0001014927,0.000002332216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001310402,"about_ca_system_score_gemma":0.00003938476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000632181,"about_ca_topic_score_gemma":0.00001109121,"domain_scores_codex":[0.999457,0.00001078812,0.00009564154,0.0001263298,0.0001653609,0.0001448973],"domain_scores_gemma":[0.9979774,0.001383619,0.00002168571,0.0004637186,0.0001274434,0.00002614412],"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":[0.000004871973,0.00005920916,0.01651382,0.0000932394,0.00002896053,8.994912e-7,0.0008012433,0.08945259,0.01219462,0.7833685,0.004215722,0.09326635],"study_design_scores_gemma":[0.0001028511,0.00002572783,0.00445634,0.000006057443,0.000001542133,0.00000263696,0.000003842646,0.9763682,0.005115125,0.01276815,0.001083948,0.00006552775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07057364,0.000006243395,0.9286987,0.000195752,0.0002182786,0.0001507528,0.000001153962,0.0001394249,0.00001609948],"genre_scores_gemma":[0.5705047,2.321622e-7,0.4291923,0.00001859584,0.00002771638,0.00001812829,3.847135e-7,0.000003502706,0.0002344752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8869157,"threshold_uncertainty_score":0.1539783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0754765022626967,"score_gpt":0.2840153090276294,"score_spread":0.2085388067649327,"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."}}