{"id":"W2620873247","doi":"10.5555/3104068.3104085","title":"Transforming workflow models into automated end-to-end acceptance test cases","year":2017,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Workflow; Computer science; Test suite; Heuristics; Test case; Regression testing; Software engineering; Programming language; Model-based testing; Data mining; Database; Software system; Machine learning; Software; Regression analysis; Software construction","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":[0.0004314198,0.0002102135,0.0002646105,0.00008605712,0.0008568602,0.0005895911,0.001912445,0.0001043665,0.00005486965],"category_scores_gemma":[0.0001889452,0.0001595546,0.00009719031,0.0002086332,0.00008767203,0.002562181,0.0002729307,0.0001239338,0.0001911982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008041116,"about_ca_system_score_gemma":0.0001183054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00074385,"about_ca_topic_score_gemma":0.0004002103,"domain_scores_codex":[0.998317,0.00002310678,0.0003391982,0.0005423463,0.0003498794,0.0004284737],"domain_scores_gemma":[0.9976838,0.0002023236,0.0001026787,0.001690657,0.0001244579,0.0001960562],"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":[0.00002524789,0.0002682443,0.03142086,0.000226611,0.00004824029,0.0001568655,0.005843339,0.00470508,0.002062856,0.005883431,0.003996265,0.945363],"study_design_scores_gemma":[0.0006689028,0.0002430508,0.02210552,0.0002572034,0.00001311247,0.0001218117,0.00008982173,0.9461482,0.02134569,0.004209463,0.003999917,0.0007973596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3625633,0.00009945993,0.6208481,0.002013844,0.001047473,0.0006066089,0.00000544711,0.002421506,0.01039418],"genre_scores_gemma":[0.9454211,0.00001662834,0.05368293,0.000250622,0.00008548181,0.00004770264,0.000001023739,0.00001141181,0.0004831116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9445656,"threshold_uncertainty_score":0.6590363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02689924794590318,"score_gpt":0.2891282796677941,"score_spread":0.2622290317218909,"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."}}