{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008466406,0.00006582068,0.00009172667,0.0001636,0.0001269448,0.00007331096,0.0004878213,0.00002685383,0.000008430214],"category_scores_gemma":[0.0005429021,0.00004616824,0.00002898851,0.0007149382,0.00002928091,0.0001423016,0.00006819327,0.0001132314,0.000005100111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000034394,"about_ca_system_score_gemma":0.00006872148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003343141,"about_ca_topic_score_gemma":0.0001509133,"domain_scores_codex":[0.9992092,0.0001361003,0.0002324851,0.0002313031,0.00007866277,0.0001122236],"domain_scores_gemma":[0.9981653,0.001201606,0.000109817,0.0004415391,0.00006541722,0.00001629673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003793858,0.00005734854,0.003218835,0.00003042518,0.000002571478,3.517489e-8,0.0001832568,0.00001732998,0.005038621,0.8496531,0.001892517,0.1399021],"study_design_scores_gemma":[0.0003493796,0.00002349056,0.101162,0.0002546583,0.000004523864,1.424459e-7,0.00009473541,0.8354408,0.008945602,0.04674723,0.006870656,0.0001068834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01651217,0.00007761876,0.8959385,0.0208513,0.0001326816,0.0002584379,0.000001837561,0.0000750765,0.0661524],"genre_scores_gemma":[0.9770236,0.000001584409,0.01984561,0.0003309146,0.000011941,0.00002708742,0.000006625709,0.000002633233,0.002750001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9605114,"threshold_uncertainty_score":0.1882686,"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."}}