{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001431161,0.000183112,0.0001937222,0.0005569106,0.00009824716,0.0001411093,0.0003654954,0.0001206595,0.00001103759],"category_scores_gemma":[0.00001064173,0.000197906,0.0003155803,0.0009683956,0.000005163326,0.0004020731,0.000002766878,0.0002988707,0.000006578998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00012764,"about_ca_system_score_gemma":0.00007753411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009035994,"about_ca_topic_score_gemma":0.000006440157,"domain_scores_codex":[0.9988404,0.000009663312,0.0001729072,0.0004486127,0.0002009605,0.000327447],"domain_scores_gemma":[0.9990615,0.0002864779,0.00001581146,0.0005034332,0.00003741622,0.0000954171],"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":[0.000003078969,0.00002452696,5.886408e-7,0.00005923512,0.0001661653,0.00001004891,0.0007750975,0.9724391,0.00003852009,0.02254365,0.00000737808,0.003932577],"study_design_scores_gemma":[0.0001355142,0.00001812196,6.721957e-7,0.00007246695,0.0001489078,0.000001087205,0.00002021402,0.9974283,0.001078575,0.0008196505,0.00007039687,0.0002061178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001332284,0.0001683687,0.9960296,0.00007900508,0.0005858589,0.0001572572,0.00007543527,0.001565302,0.000006867933],"genre_scores_gemma":[0.5401459,0.000002392707,0.4596679,0.00003691419,0.00002428741,0.00003646128,0.000002018094,0.00001888589,0.00006530474],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5388136,"threshold_uncertainty_score":0.8070374,"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."}}