{"id":"W2341384651","doi":"10.1145/2911451.2911510","title":"Engineering Quality and Reliability in Technology-Assisted Review","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reliability (semiconductor); Reliability engineering; Quality (philosophy); Computer science; Measure (data warehouse); Software quality; Taguchi methods; Data mining; Machine learning; Engineering; Software","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":[0.001024943,0.00007347543,0.0001509141,0.000142917,0.00001076206,0.00001457795,0.0004040101,0.00005208567,0.00001409247],"category_scores_gemma":[0.004177379,0.00004784477,0.00001654541,0.0006593916,0.0000295211,0.0001826415,0.0002818362,0.00009953404,0.00002418492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006872119,"about_ca_system_score_gemma":0.00002309153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001303747,"about_ca_topic_score_gemma":0.000002060596,"domain_scores_codex":[0.9991167,0.00002836394,0.0001988339,0.0003022263,0.0001461535,0.0002077504],"domain_scores_gemma":[0.9986053,0.0006608599,0.00001580763,0.0006195882,0.00004542106,0.00005308248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000003134655,0.0000941566,0.3664018,0.001769241,0.00001038636,0.00002968836,0.00003572113,0.00001761636,0.008865099,0.04906908,0.001115179,0.5725889],"study_design_scores_gemma":[0.0003404058,0.00002609422,0.9898998,0.00119479,0.00000103814,0.00001954559,9.735954e-7,0.001027872,0.001702616,0.00135703,0.004203566,0.0002262632],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1962842,0.004459627,0.7678531,0.02912141,0.0001375657,0.0004043535,9.986671e-7,0.001496754,0.0002419953],"genre_scores_gemma":[0.9140054,0.001218902,0.08437744,0.0001375309,0.000008178715,0.00005350055,1.07683e-7,0.000008066529,0.0001908516],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7177212,"threshold_uncertainty_score":0.5001014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02710917404402359,"score_gpt":0.3098347032712329,"score_spread":0.2827255292272093,"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."}}