{"id":"W2514090203","doi":"10.1145/2970276.2970300","title":"Local-based active classification of test report to assist crowdsourced testing","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Machine learning; Classifier (UML); Artificial intelligence; Crowdsourcing; Task (project management); Labeled data; Training set; Process (computing); Test data; Test (biology); Supervised learning; Data mining; Engineering; Artificial neural network; Software engineering","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":[0.0003254881,0.0000871286,0.000115067,0.00008827681,0.00006766014,0.00003333206,0.0003592783,0.0000334433,0.00002163475],"category_scores_gemma":[0.00159057,0.000055727,0.00003423625,0.0004265029,0.00004111258,0.0001176237,0.00007730517,0.00006001854,0.00005059052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004268587,"about_ca_system_score_gemma":0.0000948209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001051978,"about_ca_topic_score_gemma":0.000006090405,"domain_scores_codex":[0.999008,0.00003975536,0.0002404723,0.0003290005,0.0002247535,0.0001580167],"domain_scores_gemma":[0.9983224,0.0006992049,0.0001739104,0.0005106538,0.0002015158,0.00009236885],"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":[0.000005339383,0.0001135533,0.03988271,0.00001037749,0.000006726845,0.00002489197,0.00009277963,0.0004752777,0.09664745,0.002061241,0.000452617,0.860227],"study_design_scores_gemma":[0.0004619863,0.0003210584,0.535162,0.0001327824,0.000005942661,0.00004267709,0.00003408427,0.3630053,0.09703204,0.0003467762,0.003165163,0.0002902033],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0203313,9.635038e-7,0.965486,0.003333152,0.00006708536,0.00007625498,0.00000130982,0.0001968425,0.01050702],"genre_scores_gemma":[0.8790972,2.767516e-8,0.1189749,0.0001367718,0.00002873959,0.000008695157,7.782915e-7,0.000005786426,0.001747185],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8599368,"threshold_uncertainty_score":0.2272481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02679950523859292,"score_gpt":0.2768267888599649,"score_spread":0.250027283621372,"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."}}