{"id":"W4401023823","doi":"10.24963/ijcai.2024/587","title":"Towards Debiased Generalized Category Discovery","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Government of Jiangsu Province; Hong Kong Baptist University","keywords":"Computer science; Set (abstract data type); Artificial intelligence; Programming language","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":[0.0001840486,0.0001164824,0.0001023288,0.0001031812,0.00005536235,0.0009754315,0.0006264391,0.00004301566,0.0001108438],"category_scores_gemma":[0.00002664263,0.00008946383,0.00008097135,0.0003352189,0.00002534989,0.0009760039,0.0002346683,0.0001232572,0.0004403887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005295259,"about_ca_system_score_gemma":0.0001543608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009155741,"about_ca_topic_score_gemma":0.000002553201,"domain_scores_codex":[0.9989607,0.00003556456,0.0001748785,0.0003033607,0.0002822084,0.0002432443],"domain_scores_gemma":[0.9993919,0.00005598612,0.00001845953,0.0004480583,0.00002335227,0.00006226575],"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":[0.0000018169,0.000008554616,0.00005034089,0.00003629386,0.00003697781,0.00007207286,0.0003209398,0.1309338,0.001119402,0.8371207,0.01828093,0.01201818],"study_design_scores_gemma":[0.0001167445,0.00003760157,0.0001662843,0.00001618123,0.000005848209,0.00001168583,0.000008469436,0.9576981,0.003100892,0.002190518,0.03647536,0.0001723329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001200927,0.0002142609,0.9454881,0.001241766,0.001068555,0.00007668912,3.249922e-7,0.0007110306,0.04999836],"genre_scores_gemma":[0.8597316,0.00004158868,0.07489354,0.001156139,0.000145553,0.00001281037,0.000007234663,0.00001876258,0.06399281],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8705946,"threshold_uncertainty_score":0.9406109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02250795283475315,"score_gpt":0.2682820168396056,"score_spread":0.2457740640048524,"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."}}