{"id":"W4400484351","doi":"10.1145/3663529.3663804","title":"ATheNA-S: A Testing Tool for Simulink Models Driven by Software Requirements and Domain Expertise","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Software engineering; Software testing; Domain (mathematical analysis); Software; Programming language","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":[0.0003389932,0.0001764197,0.000154189,0.00008454425,0.0001612897,0.0004487777,0.0004190954,0.00006975388,0.000002040913],"category_scores_gemma":[0.0005251357,0.0001487504,0.00004937128,0.0002441075,0.00003902696,0.0006424625,0.0002798385,0.00008521922,0.000004482299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000528897,"about_ca_system_score_gemma":0.00005316807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003344747,"about_ca_topic_score_gemma":6.586599e-7,"domain_scores_codex":[0.9986624,0.00002531934,0.0002375012,0.0005660678,0.0001933391,0.0003153763],"domain_scores_gemma":[0.9984145,0.001013362,0.00002612859,0.0003847296,0.00008041535,0.00008089904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001188322,0.0001115902,0.002547558,0.000343905,0.00006617128,0.00005511013,0.0040706,0.0004844207,0.003017588,0.01588898,0.1601619,0.8132403],"study_design_scores_gemma":[0.0001417027,0.0001187078,0.000008782969,0.0002179866,0.000005023501,0.00001642755,0.000003651261,0.7521303,0.0004098911,0.2458049,0.0009296926,0.0002129312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007322642,0.0006999146,0.9741086,0.0003813654,0.0001146038,0.0003292015,0.000008415857,0.01685763,0.0001776371],"genre_scores_gemma":[0.2059244,0.000006309649,0.7932374,0.0004318152,0.00004495733,0.0001292675,0.000003257376,0.00002214394,0.0002004727],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8130274,"threshold_uncertainty_score":0.6065867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05609008688266483,"score_gpt":0.298129347371713,"score_spread":0.2420392604890482,"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."}}