{"id":"W3176185023","doi":"10.1609/aaai.v35i12.17264","title":"Adversarial Partial Multi-Label Learning with Label Disambiguation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Machine learning; Feature (linguistics); Encoder; Minimax; Generative adversarial network; Feature vector; Adversarial system; Deep learning; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002769894,0.0001876937,0.0002001863,0.00008590614,0.0002744646,0.0003513446,0.001228853,0.00009977919,0.00004881842],"category_scores_gemma":[0.0006459914,0.0001366308,0.0000520405,0.000814484,0.0002640975,0.00059368,0.0003741348,0.0003448763,0.00007303154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004534424,"about_ca_system_score_gemma":0.0001544084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001691654,"about_ca_topic_score_gemma":0.00001349062,"domain_scores_codex":[0.9983044,0.00002357706,0.0003902352,0.0005099031,0.0004855984,0.0002863145],"domain_scores_gemma":[0.9984859,0.00006956291,0.0003642217,0.0003014403,0.0007237687,0.00005509768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000447798,0.0002486669,0.0005023733,0.00001416107,0.00001502163,8.245527e-7,0.0006942032,0.00003960737,0.06533845,0.768456,0.00004312295,0.1646027],"study_design_scores_gemma":[0.0001274574,0.0002168456,0.0002399407,0.000106704,0.00001447145,0.000004142669,0.001156456,0.1904906,0.7783468,0.02887721,0.0002044178,0.0002149413],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3044529,0.00006343004,0.6662607,0.01914068,0.0009401008,0.0006945672,0.000004882786,0.0008400093,0.007602759],"genre_scores_gemma":[0.9754775,0.00003268821,0.02358359,0.0000898899,0.00003999073,0.00003237016,0.000001244301,0.000009598521,0.0007331548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7395788,"threshold_uncertainty_score":0.5571641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1163529464583123,"score_gpt":0.3151711112700287,"score_spread":0.1988181648117164,"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."}}