{"id":"W2141291123","doi":"10.1145/1108768.1108795","title":"An empirical framework for comparing effectiveness of testing and property-based formal analysis","year":2005,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Debugging; Computer science; Software engineering; Software bug; Formal methods; Software testing; Empirical research; Formal specification; Software; Reliability engineering; Programming language; Engineering; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009246205,0.0002706444,0.0005073732,0.0003754218,0.0001446053,0.0001221167,0.0008504962,0.0001420346,8.21754e-7],"category_scores_gemma":[0.1191537,0.0002266011,0.0001243627,0.001040968,0.00004369324,0.0005045788,0.0002341535,0.0002094064,6.755541e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004865489,"about_ca_system_score_gemma":0.00005899998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005006901,"about_ca_topic_score_gemma":0.000002030168,"domain_scores_codex":[0.9984379,0.00005869266,0.0003395151,0.0005056238,0.0002251764,0.0004330965],"domain_scores_gemma":[0.9087674,0.08991007,0.0001186689,0.0008600082,0.0002075193,0.0001363413],"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":[0.00001794647,0.00007585135,0.9385486,0.000305077,0.00006830469,0.00000165639,0.0001339323,0.03541938,0.0004932426,0.0002858299,0.00001010558,0.02464011],"study_design_scores_gemma":[0.0003322727,0.0003880212,0.4237286,0.000422312,0.0001250371,0.000008170239,8.638476e-7,0.562957,0.01010312,0.001468089,0.00002591431,0.0004405188],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2813687,0.00007939571,0.7142541,0.00003981349,0.00003950562,0.0002004844,0.000004298284,0.004013329,3.665525e-7],"genre_scores_gemma":[0.5041639,2.705623e-7,0.4956968,0.00003243937,0.00003576134,0.00004874782,0.000005005658,0.00001684922,2.512297e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5275377,"threshold_uncertainty_score":0.9240527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04273890736513571,"score_gpt":0.3093231757345271,"score_spread":0.2665842683693914,"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."}}