{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009004658,0.0001002349,0.0002576696,0.0001711307,0.0001094418,0.00007771644,0.000323951,0.00005617366,7.763484e-7],"category_scores_gemma":[0.0007390483,0.0000679759,0.00005763063,0.0006747262,0.00003872168,0.0002997802,0.00007958269,0.00007592935,3.095224e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001867408,"about_ca_system_score_gemma":0.00003779785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007628338,"about_ca_topic_score_gemma":0.000006088473,"domain_scores_codex":[0.9991348,0.00007876338,0.0001806792,0.0002829217,0.0001214197,0.0002014119],"domain_scores_gemma":[0.9967955,0.002574824,0.00007026988,0.0003547085,0.0001369219,0.00006778054],"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":[0.00003172275,0.0001576205,0.9066599,0.0001231737,0.00005392892,7.284645e-7,0.000126138,0.00680615,0.0003019893,0.003586585,0.00005474541,0.08209734],"study_design_scores_gemma":[0.000151741,0.0002689335,0.07184025,0.00007055658,0.00003941952,0.000001988924,0.000001000941,0.9112579,0.00447268,0.01177244,0.000009578671,0.0001135615],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1295445,0.00001118208,0.8680755,0.00007653587,0.00001081333,0.0001600373,4.958085e-7,0.002005199,0.0001156681],"genre_scores_gemma":[0.5038372,3.96062e-8,0.4960512,0.00007760893,0.00001143825,0.00001765021,6.838229e-7,0.000003066948,0.000001188365],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9044517,"threshold_uncertainty_score":0.2771977,"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."}}