{"id":"W4401508395","doi":"10.1109/infocom52122.2024.10621164","title":"Titanic: Towards Production Federated Learning with Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Production (economics); Natural language processing; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003524952,0.000119455,0.00009552776,0.0001140133,0.0001293773,0.0005054446,0.005131458,0.00006763537,0.00003585835],"category_scores_gemma":[0.001566347,0.00008620501,0.0000203068,0.0007040482,0.00002595119,0.001375932,0.01508082,0.0003295554,0.0001028363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006513832,"about_ca_system_score_gemma":0.00007897157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005456281,"about_ca_topic_score_gemma":0.00004576281,"domain_scores_codex":[0.9987757,0.00003573181,0.0001102221,0.000547091,0.000251065,0.0002801829],"domain_scores_gemma":[0.9975636,0.00002288021,0.00002151961,0.002312684,0.00004877614,0.00003053673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002103005,0.0001529727,0.0001446072,0.000228986,0.0001921064,0.000547535,0.001775171,0.001654512,0.009190654,0.1537294,0.5178326,0.3145304],"study_design_scores_gemma":[0.00007057172,0.00006450676,0.00001803207,0.00006063976,0.000004158687,0.00005414251,0.0001756603,0.9562212,0.01148894,0.02751829,0.004157596,0.0001662183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01157894,0.0004670241,0.9505286,0.01979207,0.000336885,0.0001340317,0.000002715147,0.006042568,0.0111172],"genre_scores_gemma":[0.8090183,0.00002804372,0.1884678,0.00006559937,0.00004243945,0.00001466631,0.00001048092,0.00001548788,0.002337245],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9545667,"threshold_uncertainty_score":0.9928851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02488295360538529,"score_gpt":0.2738356930595304,"score_spread":0.2489527394541451,"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."}}