{"id":"W2107796781","doi":"10.1109/icpc.2011.44","title":"Scalable Automatic Concept Mining from Execution Traces","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; TRACE (psycholinguistics); Program comprehension; Identification (biology); Scalability; Artifact (error); Flexibility (engineering); Process (computing); Latent Dirichlet allocation; Code (set theory); Software maintenance; Artificial intelligence; Precision and recall; Machine learning; Software; Programming language; Software system; Topic model","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":[0.001889988,0.001711546,0.001617361,0.006580539,0.00120121,0.001879949,0.003287211,0.001116413,0.001660157],"category_scores_gemma":[0.01201248,0.000655333,0.001546093,0.00503112,0.0005889175,0.003603481,0.001900262,0.001658774,0.00127963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001037566,"about_ca_system_score_gemma":0.003067583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006069842,"about_ca_topic_score_gemma":0.01097523,"domain_scores_codex":[0.9975151,0.0004408526,0.00020283,0.0007788097,0.0008586787,0.0002037698],"domain_scores_gemma":[0.9920043,0.004841559,0.0005551936,0.000875568,0.001466863,0.0002564244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004639186,0.0005799135,0.008645467,0.0007248321,0.0001604487,0.0005004056,0.0007766408,0.04870632,0.02173032,0.007057442,0.0128392,0.8978152],"study_design_scores_gemma":[0.00005219523,0.00007731529,0.002268675,0.00005065318,0.00004998167,0.0002767128,0.0003575186,0.9553468,0.01249736,0.02279425,0.006188926,0.0000395144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05269597,0.0006816806,0.9292442,0.0003484792,0.00006175653,0.0005080591,0.002922761,0.0123635,0.001173478],"genre_scores_gemma":[0.192114,0.0004216196,0.793626,0.00007823194,0.00005552377,0.000745763,0.01095584,0.0004747558,0.00152833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006580539,"threshold_uncertainty_score":0.01206905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03493957784317039,"score_gpt":0.2511520532854926,"score_spread":0.2162124754423222,"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."}}