{"id":"W4399768519","doi":"10.1109/tse.2024.3411928","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Japan Society for the Promotion of Science; JST-Mirai Program; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Programming language; Modeling language; Software engineering; Data science; Natural language processing; Software","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":[0.003891363,0.001733886,0.00135704,0.002961291,0.001212621,0.003592158,0.00380015,0.001417999,0.008856321],"category_scores_gemma":[0.009881441,0.001535087,0.004943143,0.001538028,0.001806457,0.005446689,0.004421318,0.004096373,0.003635189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001965801,"about_ca_system_score_gemma":0.002833168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009895517,"about_ca_topic_score_gemma":0.01329402,"domain_scores_codex":[0.9972616,0.001153142,0.0002281109,0.0004404108,0.0007125275,0.0002041157],"domain_scores_gemma":[0.9973089,0.001543475,0.000245752,0.0004270994,0.0003565541,0.0001182711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001220202,0.00007548814,0.001037729,0.0003822736,0.0003087228,0.0004086324,0.0005345108,0.1461991,0.002520851,0.7089982,0.01622294,0.1231895],"study_design_scores_gemma":[0.00001576463,0.00002007473,0.00008824165,0.00004928518,0.00003949091,0.00006975132,0.000040445,0.7366745,0.0007987951,0.2436395,0.01853928,0.00002474315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003983026,0.0001382833,0.9952748,0.0001397854,0.00001954533,0.00004092865,0.0002359904,0.003024475,0.000727897],"genre_scores_gemma":[0.06763932,0.0006280428,0.9226523,0.000391123,0.0001677233,0.0006191774,0.001983736,0.002387315,0.003531179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009895517,"threshold_uncertainty_score":0.02962738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01307462191319534,"score_gpt":0.2445529802957176,"score_spread":0.2314783583825223,"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."}}