{"id":"W2808417254","doi":"10.24963/ijcai.2018/395","title":"Does Tail Label Help for Large-Scale Multi-Label Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Trimming; Computer science; Multi-label classification; Artificial intelligence; Scale (ratio); Machine learning; Learning to rank; Fraction (chemistry); Pattern recognition (psychology); Ranking (information retrieval)","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":[0.005124908,0.001564801,0.001777216,0.0008514889,0.001453638,0.002632777,0.003533649,0.003368834,0.005243871],"category_scores_gemma":[0.02406773,0.000694151,0.001157362,0.001358887,0.001732366,0.008874291,0.003147439,0.004014139,0.004972439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001463966,"about_ca_system_score_gemma":0.002420388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00482297,"about_ca_topic_score_gemma":0.007432547,"domain_scores_codex":[0.9973778,0.0008822563,0.0001104306,0.0008374783,0.0005242245,0.000267818],"domain_scores_gemma":[0.9853855,0.006301773,0.0007373775,0.005333535,0.001562023,0.0006797861],"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":[0.001731197,0.00118005,0.009881847,0.0004013354,0.0001854437,0.0002217588,0.0005384138,0.2116773,0.01012794,0.02675603,0.0428654,0.6944333],"study_design_scores_gemma":[0.00007838062,0.00009896405,0.0004475855,0.00003396541,0.00002962004,0.00005634356,0.0001298098,0.9455844,0.003631311,0.04648237,0.003401369,0.00002588601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06298198,0.001058882,0.9164935,0.0044187,0.000437399,0.0002048177,0.0004834638,0.01046095,0.003460334],"genre_scores_gemma":[0.6224774,0.000560612,0.3668726,0.002116123,0.0004811129,0.0002591845,0.001887463,0.0009683546,0.004377101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005243871,"threshold_uncertainty_score":0.02710342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03686393115797922,"score_gpt":0.3014385748661733,"score_spread":0.2645746437081941,"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."}}