{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005447642,0.002134967,0.002192847,0.003310692,0.0007711643,0.00184859,0.004317307,0.001702742,0.001734542],"category_scores_gemma":[0.01925476,0.0003882143,0.000879688,0.002091353,0.0009750638,0.002280725,0.002300657,0.001663551,0.001340235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001110811,"about_ca_system_score_gemma":0.001092077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004095014,"about_ca_topic_score_gemma":0.005798416,"domain_scores_codex":[0.9949096,0.001611839,0.000330712,0.001483176,0.001284679,0.0003800878],"domain_scores_gemma":[0.9740645,0.0138492,0.00321515,0.002606717,0.005205344,0.001059153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001859325,0.001390862,0.05174527,0.0007347256,0.0002526575,0.001002585,0.002020312,0.1375442,0.02373523,0.002835944,0.02629254,0.7505865],"study_design_scores_gemma":[0.00005759195,0.0002113573,0.005043348,0.00005942868,0.00006294069,0.0001776991,0.0004815486,0.9713905,0.01256969,0.00523259,0.004667853,0.00004537929],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1888351,0.001675318,0.7851619,0.001607483,0.0004562212,0.0005824495,0.001778338,0.01305559,0.006847523],"genre_scores_gemma":[0.8835,0.0002046034,0.1095257,0.0005146901,0.0001942585,0.0004118359,0.001953852,0.0003250719,0.003370033],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005447642,"threshold_uncertainty_score":0.0288102,"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."}}