{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06565242,0.001305487,0.001073326,0.005567258,0.001739536,0.004704553,0.002079249,0.002403054,0.001445792],"category_scores_gemma":[0.290467,0.0008706403,0.002117711,0.005007278,0.001917913,0.008308609,0.002567565,0.00308201,0.0008606378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003557428,"about_ca_system_score_gemma":0.002334279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01134998,"about_ca_topic_score_gemma":0.009017676,"domain_scores_codex":[0.9537335,0.03392285,0.002828246,0.004969852,0.003818524,0.0007270401],"domain_scores_gemma":[0.5126472,0.4353379,0.01252461,0.0223922,0.01532875,0.001769467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003171966,0.002004937,0.3827031,0.002010694,0.001502095,0.0005427321,0.02620576,0.2291575,0.007769848,0.03771655,0.00948177,0.297733],"study_design_scores_gemma":[0.0002283042,0.0007392296,0.03805954,0.0001767973,0.0001279171,0.0002990914,0.002206283,0.929365,0.003622951,0.01981326,0.00521182,0.0001496826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6585702,0.0007987529,0.3265579,0.001489364,0.0002086703,0.001592354,0.002895928,0.001784194,0.006102738],"genre_scores_gemma":[0.872568,0.0001798446,0.1221233,0.00015102,0.00006084927,0.001228878,0.002935785,0.0002555271,0.0004969222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06565242,"threshold_uncertainty_score":0.3472073,"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."}}