{"id":"W1563140451","doi":"10.17705/1jais.00201","title":"Guidelines for Empirical Evaluations of Conceptual Modeling Grammars","year":2009,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Queensland University of Technology","keywords":"Rule-based machine translation; Computer science; Grammar; L-attributed grammar; Scripting language; Empirical research; Semantics (computer science); Domain (mathematical analysis); Conceptual model; Natural language processing; Artificial intelligence; Context-free grammar; Programming language; Linguistics; Mathematics","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":[0.002678636,0.00006365808,0.0002195589,0.0001152724,0.0001115572,0.0001131831,0.0004913233,0.00007592941,2.152141e-7],"category_scores_gemma":[0.003810797,0.00004130859,0.0002260934,0.0001842802,0.000009823115,0.001290022,0.00001998149,0.00005722577,0.00000169991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001643336,"about_ca_system_score_gemma":0.0001789122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003474538,"about_ca_topic_score_gemma":7.756028e-7,"domain_scores_codex":[0.998056,0.00006221503,0.001168799,0.00003949995,0.0005571594,0.0001163579],"domain_scores_gemma":[0.9933069,0.0003257313,0.00200082,0.0001443546,0.004196473,0.00002573462],"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":[0.00007346708,0.0000715815,0.002918774,0.00008309053,0.0002270227,5.707092e-8,0.01193635,0.5689753,0.0002549641,0.3024771,0.1015123,0.01147006],"study_design_scores_gemma":[0.001122632,0.0001829549,0.0007445427,0.00007320571,0.00004522439,0.000009808404,0.00209158,0.9683367,0.0002249727,0.00754207,0.01954636,0.00007995025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008047763,0.000104795,0.9825594,0.006974435,0.001527664,0.0004278182,0.00001217166,0.0000148355,0.0003310505],"genre_scores_gemma":[0.97673,0.000008028733,0.02227763,0.0005990136,0.000197128,0.000008265213,0.00000298327,0.000001975819,0.0001749773],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9686822,"threshold_uncertainty_score":0.4562155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1545799069316244,"score_gpt":0.3942508206520433,"score_spread":0.239670913720419,"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."}}