{"id":"W4394849144","doi":"10.1007/s10270-023-01147-9","title":"Empirically evaluating modeling language ontologies: the Peira framework","year":2024,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina; University of Toronto; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Modeling language; Software engineering; Programming language; Natural language processing; Data science; Knowledge management; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001875138,0.0003247866,0.0003962787,0.0001438892,0.0004445185,0.001367459,0.00173875,0.0002300316,0.000006168994],"category_scores_gemma":[0.001405919,0.0002103294,0.0002073072,0.0005443225,0.00004152368,0.0005748421,0.0005088036,0.0006351247,0.00009804267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001330767,"about_ca_system_score_gemma":0.0002748237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007906404,"about_ca_topic_score_gemma":0.00002694078,"domain_scores_codex":[0.9968198,0.0002604834,0.0006691783,0.0008321289,0.0007591476,0.0006592599],"domain_scores_gemma":[0.9972566,0.001179619,0.00008482474,0.001217628,0.0001739852,0.00008733896],"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":[0.000004174809,0.0000128724,0.0001975867,0.0002320043,0.00006705546,0.00008078889,0.01164369,0.9416457,0.00005566726,0.01822233,0.0001768351,0.02766129],"study_design_scores_gemma":[0.00006580927,0.00004270108,0.000003473025,0.0008220421,0.0000284384,0.00007309001,0.003988853,0.9839346,0.000005076,0.01065794,0.00009449248,0.0002834314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0784579,0.02499038,0.8903334,0.0007980338,0.002533827,0.0003530944,0.000003327144,0.002318005,0.000212015],"genre_scores_gemma":[0.8889918,0.00004391205,0.1100448,0.0002588518,0.0004314894,0.00008423752,0.000002836419,0.00003341867,0.0001086169],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8105339,"threshold_uncertainty_score":0.9996692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08206135092399472,"score_gpt":0.3575813258738234,"score_spread":0.2755199749498287,"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."}}