{"id":"W4409150274","doi":"10.1145/3690624.3709290","title":"On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Data science; Artificial intelligence; Knowledge management","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":[0.007213229,0.001490889,0.002108398,0.002172087,0.001758722,0.002838868,0.003515767,0.002791045,0.002226201],"category_scores_gemma":[0.03329045,0.0006823826,0.001191603,0.002659673,0.003080964,0.008818392,0.005420865,0.005012205,0.001527758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001596083,"about_ca_system_score_gemma":0.002476577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00515058,"about_ca_topic_score_gemma":0.00575324,"domain_scores_codex":[0.9950629,0.001840657,0.0002833767,0.001159898,0.001273895,0.0003793307],"domain_scores_gemma":[0.978115,0.01348277,0.001306752,0.004458938,0.002040053,0.0005964252],"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":[0.001312273,0.0008390662,0.01504582,0.0004663408,0.000264555,0.0005405487,0.001503175,0.267348,0.00847563,0.05033651,0.02305773,0.6308103],"study_design_scores_gemma":[0.00007697102,0.0001759629,0.001030924,0.0000686694,0.00004582324,0.0001929981,0.00018177,0.9198137,0.004412352,0.07027518,0.003681311,0.00004434425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05024168,0.001265275,0.9403289,0.001870403,0.00009253053,0.0001168939,0.0004842925,0.003552548,0.002047522],"genre_scores_gemma":[0.6514553,0.0006693887,0.3389604,0.001936423,0.0003393517,0.0003477014,0.002621923,0.0004306342,0.003238833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007213229,"threshold_uncertainty_score":0.03814769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1096775247010008,"score_gpt":0.3328740019953946,"score_spread":0.2231964772943938,"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."}}