{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007448369,0.001462571,0.001541317,0.006488992,0.001093479,0.003913186,0.003922268,0.002662333,0.002090036],"category_scores_gemma":[0.03396232,0.0005730442,0.001493182,0.003576797,0.0009067095,0.005133431,0.004116514,0.001595661,0.001144772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001750658,"about_ca_system_score_gemma":0.003247377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01203316,"about_ca_topic_score_gemma":0.01703802,"domain_scores_codex":[0.9874547,0.00355964,0.001005283,0.002195885,0.005008563,0.0007759054],"domain_scores_gemma":[0.9501736,0.03019155,0.003184498,0.005910204,0.008757506,0.001782693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004026343,0.002161572,0.06412498,0.001633694,0.001251703,0.0003524164,0.002986884,0.02542202,0.0171096,0.004810701,0.00710224,0.8690179],"study_design_scores_gemma":[0.0005666863,0.002001439,0.07050119,0.0003804103,0.001582506,0.001439484,0.007488814,0.8500167,0.03207904,0.01833792,0.01528139,0.0003244746],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4443914,0.003222867,0.5265602,0.001026253,0.0002315893,0.0008413243,0.001475939,0.01160157,0.01064884],"genre_scores_gemma":[0.7101226,0.001060975,0.2823523,0.000294062,0.00004007178,0.0001405832,0.002499016,0.000574208,0.002916242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01203316,"threshold_uncertainty_score":0.03939122,"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."}}