{"id":"W4225878264","doi":"10.1109/tse.2022.3162985","title":"Static Profiling of Alloy Models","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Correctness; Modeling language; Natural language processing; Profiling (computer programming); Matching (statistics); Programming language; Software; Artificial intelligence; Data science; Software engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.002538957,0.0007842832,0.0007539708,0.003408615,0.001150823,0.003000672,0.001359093,0.0008866062,0.005747028],"category_scores_gemma":[0.01830907,0.0008848462,0.001260566,0.002954527,0.0007066035,0.003601286,0.001572848,0.0008747418,0.002338997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002101516,"about_ca_system_score_gemma":0.001970128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008989217,"about_ca_topic_score_gemma":0.01474364,"domain_scores_codex":[0.9956151,0.001114544,0.0003516233,0.0005931279,0.002076279,0.0002492395],"domain_scores_gemma":[0.9903839,0.004204154,0.000620357,0.002312136,0.002358592,0.0001210098],"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":[0.001094688,0.0004304979,0.06636906,0.001387088,0.0002715959,0.001656146,0.01168054,0.200815,0.05666681,0.215776,0.03167013,0.4121824],"study_design_scores_gemma":[0.00004141475,0.0001726033,0.01008015,0.0001727694,0.0001497355,0.0006078563,0.001485417,0.7923206,0.04956751,0.03566539,0.1096313,0.0001052736],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4088794,0.001206875,0.5074705,0.0008902476,0.0001885393,0.0004715578,0.008408655,0.02209258,0.05039166],"genre_scores_gemma":[0.7159907,0.0007045236,0.244222,0.0002393348,0.0000578839,0.0004220706,0.01848922,0.005217573,0.01465666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008989217,"threshold_uncertainty_score":0.01922572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02111579023518419,"score_gpt":0.2370040407203812,"score_spread":0.215888250485197,"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."}}