{"id":"W2012086719","doi":"10.1145/1022494.1022541","title":"Empirical studies of software testing techniques","year":2004,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Empirical research; Software testing; Software reliability testing; Software engineering; Regression testing; Test strategy; Software; Software construction; System integration testing; Software performance testing; Software development; Programming language","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005781625,0.0004744522,0.0006260723,0.000405963,0.0001702989,0.00008920566,0.001924871,0.0002045248,0.000001847226],"category_scores_gemma":[0.4144245,0.0004554234,0.0001656456,0.001270145,0.0001308739,0.0005043705,0.001144047,0.0003988775,0.00001191884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001696503,"about_ca_system_score_gemma":0.0001757555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007145204,"about_ca_topic_score_gemma":0.000001540278,"domain_scores_codex":[0.9974838,0.00003503407,0.0006526634,0.000694069,0.000513784,0.0006206591],"domain_scores_gemma":[0.9291527,0.06768756,0.0002971797,0.002000204,0.0006653249,0.0001970587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001049753,0.0002912853,0.8581385,0.0009064623,0.0001899455,0.000171632,0.0025241,0.002862707,0.003657379,0.00112847,0.002681093,0.1274379],"study_design_scores_gemma":[0.002342077,0.003231751,0.3001544,0.009991746,0.0002487356,0.001198016,0.00005712358,0.0009996144,0.5547635,0.1180773,0.002672102,0.006263646],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09857077,0.001743065,0.8525242,0.000432477,0.0003738462,0.0003106184,0.000009758553,0.04603185,0.000003462849],"genre_scores_gemma":[0.4250168,0.00001544086,0.5746526,0.0001389033,0.00007862172,0.00004986431,0.000002663561,0.00004153188,0.000003621445],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5579842,"threshold_uncertainty_score":0.9997898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07925087812671783,"score_gpt":0.3242008907103558,"score_spread":0.244950012583638,"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."}}