{"id":"W2165679316","doi":"10.1109/icst.2008.18","title":"A Three-Tiered Testing Strategy for Cookies","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Scalability; Test suite; Random testing; Grammar; Suite; Reliability (semiconductor); Artificial intelligence; Test case; Machine learning; Database","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":[0.0001548895,0.00009679406,0.0001098367,0.00005767184,0.0002237743,0.00006394624,0.0004593364,0.00003881888,0.000002357464],"category_scores_gemma":[0.0005396601,0.00008222568,0.00003679107,0.0002470671,0.00004457054,0.0001832625,0.00009044919,0.0000533126,0.000009099615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001354772,"about_ca_system_score_gemma":0.00008439708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001658708,"about_ca_topic_score_gemma":0.000008890321,"domain_scores_codex":[0.9992759,0.000007465676,0.0001394627,0.000248885,0.0001149857,0.0002132649],"domain_scores_gemma":[0.9988001,0.0006111466,0.00004640286,0.0003514615,0.0001403766,0.00005049234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001480516,0.0001938721,0.06410253,0.00006778157,0.00003497013,0.0000884442,0.000524449,0.0002768108,0.0006865352,0.1479704,0.3930278,0.3930116],"study_design_scores_gemma":[0.0003675235,0.00049398,0.01105644,0.00004351478,0.000004167049,0.0002989186,0.000003629024,0.4155843,0.002490838,0.56846,0.0007907853,0.0004058238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004123496,0.00004928272,0.9758802,0.0001256667,0.00006231001,0.000151117,7.998167e-7,0.01491573,0.004691395],"genre_scores_gemma":[0.4030395,5.079352e-7,0.5966019,0.0001432081,0.00003244553,0.0000294964,5.044033e-7,0.000005548638,0.0001468962],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4204897,"threshold_uncertainty_score":0.3353066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1530131813642821,"score_gpt":0.2990189896137123,"score_spread":0.1460058082494302,"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."}}