{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4365891,0.002793324,0.002873465,0.02290737,0.008610808,0.02078047,0.01026934,0.008615552,0.02150228],"category_scores_gemma":[0.7413957,0.003754843,0.004878021,0.02280976,0.01133797,0.02409592,0.0104465,0.009776298,0.007697457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01669392,"about_ca_system_score_gemma":0.02507542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009407789,"about_ca_topic_score_gemma":0.01887373,"domain_scores_codex":[0.4201492,0.401126,0.09964733,0.008129772,0.06730063,0.003647093],"domain_scores_gemma":[0.1440117,0.4926223,0.0300249,0.08377294,0.2461757,0.003392589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008993158,0.003496503,0.01603776,0.01164986,0.0004376289,0.0007842099,0.05438872,0.004854383,0.002734618,0.3866656,0.1304335,0.3876179],"study_design_scores_gemma":[0.001986516,0.001230955,0.02158314,0.04210814,0.0005778739,0.0006656281,0.04797979,0.0112131,0.006662363,0.3079674,0.5573763,0.0006487898],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03493594,0.008302816,0.5683708,0.02663065,0.001915806,0.1391589,0.008953518,0.002394368,0.2093372],"genre_scores_gemma":[0.04755111,0.002007363,0.7591991,0.002927329,0.0001389707,0.1799427,0.003495156,0.0006823589,0.004055913],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4365891,"threshold_uncertainty_score":0.694786,"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."}}