{"id":"W4398243240","doi":"10.1016/j.datak.2024.102324","title":"Large language models: Expectations for semantics-driven systems engineering","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Systems Engineering Methodologies and Applications","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Foundation for Research and Technology-Hellas","keywords":"Computer science; Semantics (computer science); Programming language; Modeling language; Operational semantics; Software engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004098205,0.000385805,0.0003829757,0.0003537515,0.00007352676,0.0002559702,0.0007206149,0.0001619376,0.000006477763],"category_scores_gemma":[0.0001547356,0.000415589,0.0001065855,0.0005345274,0.000008893289,0.0005203139,0.0001833762,0.0002910799,0.00008553124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372366,"about_ca_system_score_gemma":0.00002796899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005601803,"about_ca_topic_score_gemma":0.000005327635,"domain_scores_codex":[0.9982722,0.00001356922,0.0004527238,0.000506429,0.0001365392,0.0006185767],"domain_scores_gemma":[0.998179,0.0006235449,0.00001889892,0.001009238,0.0000502418,0.0001190665],"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":[0.000001153699,0.0000232616,0.000001577138,0.003244034,0.0002876915,0.00001178882,0.002337536,0.9287157,0.01315459,0.03902806,0.01069683,0.002497804],"study_design_scores_gemma":[0.0001503399,0.000008722698,0.000004919401,0.0003693012,0.0000633251,0.00002273978,0.0006447636,0.9120185,0.0003976456,0.00001547718,0.08588193,0.0004222933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003072546,0.03158188,0.9555716,0.00002027833,0.003156071,0.0006151502,0.001527993,0.004161814,0.0002926968],"genre_scores_gemma":[0.9027181,0.0002779238,0.09121478,0.000002833004,0.002037492,0.001167703,0.001811362,0.0004403841,0.0003294623],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8996455,"threshold_uncertainty_score":0.9998296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07354628162855453,"score_gpt":0.3157645917063224,"score_spread":0.2422183100777679,"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."}}