{"id":"W2099441126","doi":"10.1109/tse.2003.1214327","title":"General test result checking with log file analysis","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Random testing; Formalism (music); Programming language; Unit testing; Operating system; Software; Test case","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":[0.0001922093,0.0002528651,0.0002522806,0.0005018831,0.0001844781,0.0001355094,0.0003802889,0.00009058866,0.00007920685],"category_scores_gemma":[0.0002134777,0.0002372688,0.0001436497,0.001882013,0.00002207403,0.0002567336,0.00000238204,0.0003181418,0.00001739912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008885792,"about_ca_system_score_gemma":0.00005345914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004145673,"about_ca_topic_score_gemma":0.000007751677,"domain_scores_codex":[0.9986122,0.00002543399,0.0002293232,0.0004713261,0.0002861109,0.0003756013],"domain_scores_gemma":[0.998276,0.0007479516,0.00005811886,0.0007035306,0.00008917283,0.0001252535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006637182,0.0002065263,0.00191652,0.00003514298,0.0003575011,0.000076666,0.0003438007,0.9820529,0.0002106727,0.0002887506,0.002587913,0.01191697],"study_design_scores_gemma":[0.001179208,0.0007925229,0.006258056,0.0004341477,0.0005773937,0.0003197308,0.00001048547,0.9119093,0.06935214,0.0004664742,0.006286966,0.002413544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002097336,0.00002534465,0.9867371,0.00001593493,0.0001798991,0.00009430626,0.00003921776,0.01072938,0.00008148545],"genre_scores_gemma":[0.4250256,0.000002955168,0.5746192,0.00005397941,0.00001700989,0.00005709665,0.000003760957,0.00002411502,0.0001962879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4229282,"threshold_uncertainty_score":0.9675543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01114718760434826,"score_gpt":0.215001202784079,"score_spread":0.2038540151797307,"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."}}