{"id":"W110592620","doi":"10.5753/sbes.2007.21316","title":"Experimental Evaluation of Coverage Criteria for FSM-based Testing","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Code coverage; Finite-state machine; Reliability engineering; Test plan; Test strategy; Empirical research; Test (biology); Compromise; Plan (archaeology); Data mining; Machine learning; Artificial intelligence; Algorithm; Engineering; Mathematics; Statistics; Software","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002224013,0.0000672547,0.00008112724,0.00007909715,0.00005455119,0.00003658345,0.0002368739,0.00002971477,0.00001066364],"category_scores_gemma":[0.00100625,0.00006274475,0.00003180968,0.0001801694,0.00001755558,0.0001220959,0.00004306542,0.00002355151,0.000001070193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004730587,"about_ca_system_score_gemma":0.00007542061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004240994,"about_ca_topic_score_gemma":7.723452e-7,"domain_scores_codex":[0.9991825,0.00002936597,0.0001846813,0.0001764473,0.0002839025,0.0001431104],"domain_scores_gemma":[0.9985507,0.0007678725,0.00007752293,0.0002553478,0.0003172859,0.00003127602],"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":[0.00007963709,0.0009208931,0.02537888,0.0001275627,0.00002483579,0.00000700959,0.001278239,0.000987559,0.3196201,0.01385405,0.02744195,0.6102793],"study_design_scores_gemma":[0.0003907214,0.0001992855,0.002552639,0.00002938059,0.000004491901,0.000002791827,0.000003522063,0.5414935,0.4428262,0.0123687,0.00003729758,0.00009151356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09081292,0.00003128035,0.9041971,0.00002828001,0.0001083764,0.0002221122,7.885993e-7,0.002256973,0.002342181],"genre_scores_gemma":[0.5576077,8.094848e-9,0.442253,0.00009869,0.00001616808,0.00001433894,0.000001067797,0.000003148574,0.000005922142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6101877,"threshold_uncertainty_score":0.2558657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1379830994562716,"score_gpt":0.4016068810919319,"score_spread":0.2636237816356602,"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."}}