{"id":"W4396913016","doi":"10.48550/arxiv.2405.06806","title":"An Empirical Study on the Effectiveness of Large Language Models for SATD Identification and Classification","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identification (biology); Computer science; Empirical research; Natural language processing; Artificial intelligence; Statistics; Mathematics; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007593447,0.003287835,0.001437306,0.002885586,0.001000171,0.002168224,0.002074885,0.002483927,0.002948126],"category_scores_gemma":[0.02660806,0.0006600479,0.001692924,0.001972471,0.0008792321,0.005385645,0.00178367,0.003703676,0.003455076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002065774,"about_ca_system_score_gemma":0.00137831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01229151,"about_ca_topic_score_gemma":0.01891925,"domain_scores_codex":[0.9944468,0.002506084,0.0005341633,0.001533039,0.0006669415,0.0003129447],"domain_scores_gemma":[0.9774852,0.01717217,0.0008904674,0.002485585,0.001463162,0.0005033358],"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":[0.002344339,0.002283998,0.05505833,0.002216246,0.001248851,0.0006922815,0.0006711563,0.1251216,0.01057912,0.002377827,0.04949881,0.7479073],"study_design_scores_gemma":[0.0002184547,0.001060214,0.01391788,0.000284141,0.0003866308,0.0007655826,0.0005852201,0.9553763,0.01520368,0.003260355,0.008797695,0.0001437994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8470744,0.02083981,0.0870686,0.002246456,0.001168065,0.0006437675,0.009486014,0.01882828,0.01264461],"genre_scores_gemma":[0.9010392,0.001782164,0.07184645,0.0008281739,0.0002353379,0.0003136106,0.01969684,0.0006286959,0.003629527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01229151,"threshold_uncertainty_score":0.04015851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07916967803166322,"score_gpt":0.2876175790890751,"score_spread":0.2084479010574119,"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."}}