{"id":"W2169863116","doi":"10.1145/1557019.1557119","title":"Effective multi-label active learning for text classification","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Simon Fraser University","keywords":"Computer science; Multi-label classification; Support vector machine; Labeled data; Reduction (mathematics); Artificial intelligence; Machine learning; Active learning (machine learning); Point (geometry); Semi-supervised learning; Data reduction; Data mining; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002128,0.000101172,0.0001054149,0.00006708462,0.0002078339,0.00009485043,0.0002877557,0.00004785378,0.000006187975],"category_scores_gemma":[0.0001759507,0.00008438536,0.00004443112,0.0001906497,0.00001229525,0.0002666574,0.0000303956,0.0001964952,0.00005785715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003479723,"about_ca_system_score_gemma":0.00001748809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001176584,"about_ca_topic_score_gemma":0.000001275171,"domain_scores_codex":[0.9991907,0.00008108048,0.00009984386,0.0003240888,0.0001068207,0.0001974285],"domain_scores_gemma":[0.9994053,0.0002039857,0.00007048712,0.0001818509,0.00008362214,0.00005475363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006813072,0.00007827853,0.00009260883,0.000002435976,0.000006126634,4.469678e-7,0.0004249945,0.000188748,0.002544017,0.01739398,0.000133572,0.979128],"study_design_scores_gemma":[0.0007163394,0.0003429208,0.03296718,0.000006736319,0.000003088187,0.000002371808,0.00004402555,0.9607892,0.001831934,0.0008161592,0.002355283,0.0001247467],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004584838,0.00001694047,0.988623,0.001595372,0.0001153056,0.0003155497,3.05443e-7,0.0003384183,0.004410244],"genre_scores_gemma":[0.7222141,0.000002105412,0.2735554,0.0002920317,0.00008086905,0.00003932298,0.000004179757,0.000005441153,0.003806594],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9790033,"threshold_uncertainty_score":0.3441135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02444210877789751,"score_gpt":0.3137702215281998,"score_spread":0.2893281127503023,"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."}}