{"id":"W4400406365","doi":"10.1007/s11334-024-00566-1","title":"Detecting mistakes in a domain model: a comparison of three approaches","year":2024,"lang":"en","type":"article","venue":"Innovations in Systems and Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0007210699,0.0001364743,0.0002532597,0.0009627758,0.000026477,0.0001607302,0.00028018,0.00008502754,3.605589e-7],"category_scores_gemma":[0.0005674384,0.0001421901,0.00002231156,0.002206885,0.00001768704,0.0002978857,0.00006410623,0.0003313424,6.266122e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000108059,"about_ca_system_score_gemma":0.00006024168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007908601,"about_ca_topic_score_gemma":0.00002962546,"domain_scores_codex":[0.9987041,0.00001385023,0.0005041556,0.0002969656,0.0002262704,0.0002546054],"domain_scores_gemma":[0.9989263,0.0006891922,0.00003266127,0.0002741685,0.00004755631,0.00003014978],"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":[0.000001081814,0.00002415056,0.07121599,0.0008511447,0.00001622468,0.00001614986,0.003558883,0.8759024,0.0004412173,0.04036427,0.00001090485,0.007597554],"study_design_scores_gemma":[0.0001062725,0.00001397833,0.007371854,0.0005045388,8.664769e-7,0.00001191952,0.0001355431,0.9913634,0.00009391716,0.0001548162,0.0001037107,0.0001391835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3423195,0.001751954,0.655351,0.00002187357,0.0001619582,0.0001394931,0.000002044441,0.0002401465,0.0000120219],"genre_scores_gemma":[0.9072102,0.00000139937,0.09264877,0.000001115665,0.00002280301,0.00008848174,0.000001302784,0.00001882838,0.000007098993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5648907,"threshold_uncertainty_score":0.5798342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06713351668033267,"score_gpt":0.2820279381096866,"score_spread":0.2148944214293539,"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."}}