{"id":"W4384026505","doi":"10.1109/msr59073.2023.00067","title":"DACOS—A Manually Annotated Dataset of Code Smells","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Code smell; Code (set theory); Context (archaeology); Information retrieval; Benchmarking; Artificial intelligence; Focus (optics); Machine learning; Natural language processing; World Wide Web; Software","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":[0.0004088181,0.00006598404,0.00009381361,0.0001745608,0.00002150273,0.00004321215,0.001071384,0.00002812426,0.0000551537],"category_scores_gemma":[0.0002359528,0.00005901552,0.00001868458,0.001061814,0.00002461639,0.0002039415,0.0005250932,0.0000808589,0.0007602224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000121423,"about_ca_system_score_gemma":0.0000417987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003504795,"about_ca_topic_score_gemma":0.000004478105,"domain_scores_codex":[0.9990149,0.00002216994,0.0001551177,0.000224702,0.0003324225,0.0002506505],"domain_scores_gemma":[0.9986991,0.0004634208,0.00002069139,0.0006883653,0.00005777044,0.00007061267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005187909,0.0000558711,0.004099471,0.00007170103,0.00003877102,0.0001412904,0.000297751,0.003401524,0.00827322,0.006740547,0.9615545,0.01532013],"study_design_scores_gemma":[0.001105547,0.0003011582,0.1673115,0.00006112234,0.000006851654,0.00002893713,0.00005441007,0.5607122,0.09150506,0.001712888,0.1765126,0.00068769],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2050083,0.00004820662,0.7880519,0.00128177,0.0005638907,0.0003463413,0.001169304,0.002497518,0.00103278],"genre_scores_gemma":[0.8741934,0.00005921831,0.1167034,0.0003465886,0.00007821888,0.00003326122,0.001519972,0.00004612586,0.007019895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7850419,"threshold_uncertainty_score":0.9771375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03287142682747221,"score_gpt":0.3131079492889892,"score_spread":0.280236522461517,"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."}}