{"id":"W1979786964","doi":"10.1109/scam.2010.22","title":"Estimating the Optimal Number of Latent Concepts in Source Code Analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Latent Dirichlet allocation; Computer science; Source code; Latent variable; Code (set theory); Topic model; Latent semantic analysis; Software; Natural language processing; Data mining; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005187155,0.00005823143,0.0001150312,0.0000866495,0.00002484113,0.00005160476,0.0007473991,0.00003207857,0.0001155681],"category_scores_gemma":[0.0003895032,0.00003924102,0.00005399049,0.0009784998,0.00005360713,0.0001000347,0.0002342197,0.0002282714,0.00003057214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001030441,"about_ca_system_score_gemma":0.00002842889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002178015,"about_ca_topic_score_gemma":0.00007105423,"domain_scores_codex":[0.9992105,0.00002557895,0.0001537061,0.0001662495,0.0002596559,0.0001843169],"domain_scores_gemma":[0.9987645,0.0006409088,0.00003059272,0.0004690392,0.00005534029,0.00003964804],"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":[0.000001050589,0.0000269066,0.5907651,0.000005843792,0.00005705412,0.000004168096,0.00100239,0.3989994,0.0007806881,0.002516335,0.0000794575,0.005761585],"study_design_scores_gemma":[0.00006960471,0.000004339331,0.1413604,0.000002483266,0.000005163328,0.000003371222,0.000006549883,0.8576788,0.000749619,0.00003419769,0.00004075533,0.00004479093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5223206,0.000002189586,0.4773012,0.0001232647,0.00005126545,0.00003134533,2.309413e-7,0.00004451695,0.0001253306],"genre_scores_gemma":[0.7629559,1.118321e-7,0.2367997,0.00001561308,0.00001273043,0.000003719945,2.79516e-7,0.000003045879,0.0002088376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4586794,"threshold_uncertainty_score":0.1600202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01564829991397315,"score_gpt":0.3161577286747401,"score_spread":0.3005094287607669,"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."}}