{"id":"W4402571307","doi":"10.1109/icstw60967.2024.00021","title":"Annotating Control-Flow Graphs for Formalized Test Coverage Criteria","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Computer science; Control flow; Test (biology); Control flow graph; Control (management); Programming language; Software engineering; Artificial intelligence","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":[0.00829849,0.002379326,0.001201076,0.006711958,0.001338487,0.004017894,0.002082382,0.002443037,0.004487192],"category_scores_gemma":[0.04824405,0.001209156,0.003129033,0.003346264,0.003304545,0.005102865,0.003729718,0.003220579,0.001002796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003406793,"about_ca_system_score_gemma":0.003455769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008849689,"about_ca_topic_score_gemma":0.01046418,"domain_scores_codex":[0.9891905,0.00437934,0.001200581,0.001473709,0.002980732,0.0007752571],"domain_scores_gemma":[0.9529493,0.03420071,0.003177644,0.00415622,0.005089792,0.0004264017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003706961,0.0003595827,0.01191218,0.00150212,0.000175604,0.001756504,0.003149539,0.3943467,0.02627379,0.2698803,0.008595984,0.2816771],"study_design_scores_gemma":[0.00006758388,0.00007958469,0.0009433712,0.0004427391,0.00008029873,0.0003345844,0.0003149041,0.6934144,0.02450865,0.258702,0.02100728,0.0001046017],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006785348,0.00005936694,0.9878196,0.0001612252,0.00002707201,0.0002375919,0.0004952783,0.003398944,0.00101562],"genre_scores_gemma":[0.08915808,0.0001308825,0.9056098,0.0001856943,0.00003110457,0.000481121,0.00193438,0.001641306,0.000827636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008849689,"threshold_uncertainty_score":0.04388714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01748680288172474,"score_gpt":0.2954803116486411,"score_spread":0.2779935087669164,"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."}}