{"id":"W4403036283","doi":"10.1007/s10664-024-10548-3","title":"An empirical study on the effectiveness of large language models for SATD identification and classification","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identification (biology); Computer science; Empirical research; Natural language processing; Artificial intelligence; Data science; Statistics; Mathematics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01518937,0.001101307,0.0008159489,0.002231496,0.00113818,0.002463971,0.002008674,0.001848089,0.003371127],"category_scores_gemma":[0.1144367,0.0004722135,0.0009694789,0.002179855,0.001260876,0.006340297,0.00175773,0.002659673,0.001638713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001493981,"about_ca_system_score_gemma":0.001367756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006278827,"about_ca_topic_score_gemma":0.006135588,"domain_scores_codex":[0.9847825,0.01171242,0.0007426565,0.001436787,0.001056684,0.0002690011],"domain_scores_gemma":[0.6920501,0.2898922,0.002998816,0.01015454,0.003845199,0.001059111],"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":[0.006034986,0.006900226,0.2963994,0.001102752,0.0009099252,0.0005962156,0.003751296,0.09666128,0.007128435,0.01138305,0.01751547,0.5516169],"study_design_scores_gemma":[0.0003434352,0.001133909,0.03934,0.0001439339,0.0003854061,0.0007106051,0.002456486,0.9291992,0.007151946,0.01430247,0.00473508,0.00009753853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9421707,0.001339316,0.04735081,0.001391003,0.00009131552,0.0002017292,0.00180969,0.001201038,0.004444287],"genre_scores_gemma":[0.9724717,0.000230633,0.02308217,0.0001975293,0.00004232367,0.00008557105,0.002833847,0.0001258862,0.0009304887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01518937,"threshold_uncertainty_score":0.08033001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02754798223888654,"score_gpt":0.3451586090035,"score_spread":0.3176106267646134,"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."}}