{"id":"W2011861933","doi":"10.1109/csmr.2012.78","title":"A Comparative Study of the Performance of IR Models on Duplicate Bug Detection","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Heuristics; Weighting; Set (abstract data type); Data mining; Entropy (arrow of time); Machine learning; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03087508,0.002709652,0.002765834,0.005375857,0.0008882153,0.002862885,0.001915832,0.002486948,0.0009902701],"category_scores_gemma":[0.06101016,0.0008819447,0.001869593,0.003601614,0.0008572576,0.006446046,0.001492444,0.001744169,0.001569397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001770201,"about_ca_system_score_gemma":0.001253077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00777032,"about_ca_topic_score_gemma":0.005413928,"domain_scores_codex":[0.9861134,0.008077946,0.001420318,0.001731004,0.002053999,0.0006033386],"domain_scores_gemma":[0.9074804,0.07665119,0.002326146,0.005543365,0.007043684,0.0009551008],"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":[0.005651993,0.001956562,0.03641427,0.002419941,0.002673619,0.0002969908,0.001243964,0.301668,0.01046036,0.002189328,0.01305995,0.6219651],"study_design_scores_gemma":[0.0001213335,0.001984687,0.009084955,0.00009949127,0.0005038677,0.0002689305,0.0004192192,0.975878,0.008132055,0.001526584,0.001828219,0.0001527583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8403862,0.01666874,0.1135588,0.001902359,0.0006633191,0.0005405686,0.001629085,0.01482065,0.009830367],"genre_scores_gemma":[0.9287305,0.002737602,0.06207899,0.0002001863,0.0002369521,0.000205777,0.002603828,0.0005143182,0.002691932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03087508,"threshold_uncertainty_score":0.163285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05731752959737332,"score_gpt":0.2968354962486602,"score_spread":0.2395179666512869,"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."}}