{"id":"W1979991500","doi":"10.1007/s10664-012-9224-x","title":"Configuring latent Dirichlet allocation based feature location","year":2012,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"U.S. Department of Education; National Science Foundation","keywords":"Latent Dirichlet allocation; Computer science; Feature (linguistics); Source code; Heuristics; Context (archaeology); Java; Artificial intelligence; Topic model; Code (set theory); Measure (data warehouse); Data mining; Natural language processing; Information retrieval; Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005053923,0.0002736067,0.0002118883,0.0002573355,0.00009735407,0.000142456,0.000673337,0.0001727861,0.00002197549],"category_scores_gemma":[0.002307262,0.0002750617,0.00008370567,0.001130686,0.00001770855,0.0007202154,0.0001742096,0.0004503653,0.0001625018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002960885,"about_ca_system_score_gemma":0.00007692727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007759668,"about_ca_topic_score_gemma":3.133222e-7,"domain_scores_codex":[0.9979314,0.0000396586,0.0002351536,0.000390513,0.0005963015,0.0008069666],"domain_scores_gemma":[0.9977708,0.0009816218,0.00004497102,0.0006541631,0.000156033,0.0003924497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007558645,0.0002056426,0.7764213,0.0002812369,0.00005845044,0.00001751643,0.0006431837,0.2078303,0.001196544,0.0007707287,0.006344035,0.006223564],"study_design_scores_gemma":[0.0003851537,0.00004752734,0.826615,0.0001086006,0.00001040649,0.00002264896,0.000002868268,0.141282,0.005751718,0.00001408421,0.02517003,0.0005900068],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05946279,0.0007589292,0.9360986,0.0008566431,0.0007749467,0.0002041057,0.000001443571,0.001826974,0.0000155916],"genre_scores_gemma":[0.9014249,0.000003736944,0.09778346,0.0002189673,0.0003326907,0.00007093789,0.00001698243,0.00004479039,0.0001035071],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8419622,"threshold_uncertainty_score":0.9999701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0249021583454907,"score_gpt":0.2743756658225636,"score_spread":0.2494735074770729,"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."}}