{"id":"W2530824252","doi":"10.1109/tse.2016.2616306","title":"A Framework for Evaluating the Results of the SZZ Approach for Identifying Bug-Introducing Changes","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Queen's University; McGill University","funders":"","keywords":"Implementation; Computer science; Task (project management); Software bug; Software implementation; Software; Software engineering; Programming language; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001441578,0.0002297775,0.0002275267,0.0001885293,0.0003369165,0.00009435783,0.001222989,0.0001173016,0.000001877041],"category_scores_gemma":[0.003179797,0.0001349181,0.0002312431,0.0006488833,0.00004602055,0.0002091146,0.00001728454,0.0003036507,0.000001710136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001420957,"about_ca_system_score_gemma":0.00007065957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007571528,"about_ca_topic_score_gemma":0.000001958965,"domain_scores_codex":[0.9980446,0.00004793562,0.0003426918,0.0005311647,0.0005154744,0.0005181143],"domain_scores_gemma":[0.9908863,0.007581329,0.0001083719,0.001141037,0.0002146227,0.00006831199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001299326,0.0001070776,0.00005448702,0.000560566,0.0002122748,4.915971e-7,0.002018432,0.8617895,0.02196313,0.00173405,0.0002008449,0.1112292],"study_design_scores_gemma":[0.002674009,0.000662271,0.001126571,0.001496519,0.0001064674,0.00002780169,0.00009754912,0.66554,0.3257503,0.0009617663,0.0007490365,0.0008076596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004667803,0.00008287316,0.9914617,0.0006650207,0.001563589,0.001043131,0.00006781726,0.0004469844,0.000001077703],"genre_scores_gemma":[0.5061271,0.000006554711,0.4929065,0.00002240727,0.000148785,0.0006392096,5.70036e-7,0.00004280135,0.0001061465],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5014592,"threshold_uncertainty_score":0.55018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07051700283867052,"score_gpt":0.3266203963305439,"score_spread":0.2561033934918734,"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."}}