{"id":"W4403889819","doi":"10.1007/978-3-031-72754-2_3","title":"Federated Learning with Local Openset Noisy Labels","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009076838,0.0005319822,0.0004512269,0.0006794013,0.0004210629,0.001835894,0.002125575,0.0002757141,0.00003108811],"category_scores_gemma":[0.00007170017,0.0004172105,0.00006720388,0.0008904756,0.0006124493,0.0006237927,0.001170208,0.001875235,0.0003519281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002496444,"about_ca_system_score_gemma":0.0005879631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006580443,"about_ca_topic_score_gemma":0.0001688083,"domain_scores_codex":[0.9960986,0.0000550172,0.0004103164,0.001869532,0.0009729963,0.0005934776],"domain_scores_gemma":[0.9981312,0.0003342779,0.0002224494,0.0009060558,0.0002263624,0.000179727],"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":[0.00001075595,0.00001882605,0.00007643803,0.00006598876,0.00001954519,0.0002522925,0.0004192889,0.06959972,0.00008601543,0.04067275,0.00006556238,0.8887128],"study_design_scores_gemma":[0.0002179408,0.000327832,0.0001114092,0.0006133636,0.00001231084,0.0001918282,4.112361e-7,0.9572393,0.0002860786,0.01953361,0.02078669,0.0006792629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00004295998,0.0003976818,0.9841073,0.001988835,0.0007457901,0.000254702,0.000005098691,0.0004599463,0.01199775],"genre_scores_gemma":[0.7240472,0.00007628251,0.2622581,0.001911211,0.0006132644,0.00002345901,0.0001148162,0.0001259225,0.01082981],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8880336,"threshold_uncertainty_score":0.999828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01411810448870606,"score_gpt":0.250326107689976,"score_spread":0.23620800320127,"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."}}