{"id":"W4234480656","doi":"10.1145/1108792.1108795","title":"An empirical framework for comparing effectiveness of testing and property-based formal analysis","year":2005,"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":"Queen's University","funders":"","keywords":"Debugging; Computer science; Software engineering; Software bug; Formal methods; Random testing; Formal specification; Empirical research; Formal verification; Measure (data warehouse); Software testing; Software; Programming language; Data mining; Test case; Machine learning; Mathematics","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":[0.1644941,0.001383852,0.001427479,0.009356646,0.001055517,0.003996932,0.002072572,0.002648528,0.002514619],"category_scores_gemma":[0.5871231,0.0004318826,0.001746516,0.00698683,0.007255799,0.007953887,0.003427599,0.002986537,0.0005548862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00208244,"about_ca_system_score_gemma":0.001820854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009305927,"about_ca_topic_score_gemma":0.0004897852,"domain_scores_codex":[0.7122272,0.2273579,0.0134746,0.006291751,0.03882209,0.001826376],"domain_scores_gemma":[0.1626647,0.7729352,0.02098961,0.02495708,0.01705681,0.001396547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006897229,0.005749008,0.3375926,0.004243935,0.004459649,0.0004281285,0.006977807,0.0523955,0.006826506,0.2791284,0.006157697,0.2891436],"study_design_scores_gemma":[0.002846257,0.03516693,0.3187849,0.002949649,0.00212488,0.002025178,0.006884784,0.2961023,0.0132135,0.2852987,0.03396941,0.0006334405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3565685,0.005507601,0.5881298,0.002713204,0.000393042,0.006180468,0.002570286,0.0005279097,0.03740918],"genre_scores_gemma":[0.8713796,0.0006809516,0.1181715,0.0005576054,0.0002256534,0.007161431,0.001024674,0.000162493,0.0006361884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1644941,"threshold_uncertainty_score":0.8699384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06517471039457418,"score_gpt":0.3506701034153422,"score_spread":0.285495393020768,"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."}}