{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LZVGL7G6L6BEWFH5JTH6ZLIPLU","short_pith_number":"pith:LZVGL7G6","canonical_record":{"source":{"id":"2407.03038","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:02:24Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"bb1455013b54007c8ba787874af3b059a21204281d4910493ae7bb39c6021b9e","abstract_canon_sha256":"c6ae028259c22654ce63f9b8c3ab7bdf5fe9ff678257fa94e5452b8b684513f6"},"schema_version":"1.0"},"canonical_sha256":"5e6a65fcde5f824b14fd4ccfecad0f5d21797a508f57574de89b0c45e7eb8170","source":{"kind":"arxiv","id":"2407.03038","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03038","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03038v3","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03038","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"LZVGL7G6L6BE","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"LZVGL7G6L6BEWFH5","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"LZVGL7G6","created_at":"2026-07-05T10:46:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LZVGL7G6L6BEWFH5JTH6ZLIPLU","target":"record","payload":{"canonical_record":{"source":{"id":"2407.03038","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:02:24Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"bb1455013b54007c8ba787874af3b059a21204281d4910493ae7bb39c6021b9e","abstract_canon_sha256":"c6ae028259c22654ce63f9b8c3ab7bdf5fe9ff678257fa94e5452b8b684513f6"},"schema_version":"1.0"},"canonical_sha256":"5e6a65fcde5f824b14fd4ccfecad0f5d21797a508f57574de89b0c45e7eb8170","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:19.710425Z","signature_b64":"hVGFklYOQtJkfVGOclf+CpoYai4NSOjTnH2YasaopyKdIiosPQ3BcuciJLFKX9w+8/TPsaiR3zcSN4z/pxp5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e6a65fcde5f824b14fd4ccfecad0f5d21797a508f57574de89b0c45e7eb8170","last_reissued_at":"2026-07-05T10:46:19.709949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:19.709949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.03038","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knPjKmRkqeKVMIm+uS4dKk3yGcYD8WNdD6T9TpXkl6mpDpglnmOAv5xrM3r8pXOJSPFgOh5rUY/w8CnJbtEiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:19:45.582094Z"},"content_sha256":"f3202c61e8079d5fb1fca9e81b37acd9337e81b792f8319ce9b26ae026bc88f5","schema_version":"1.0","event_id":"sha256:f3202c61e8079d5fb1fca9e81b37acd9337e81b792f8319ce9b26ae026bc88f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LZVGL7G6L6BEWFH5JTH6ZLIPLU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Feijie Wu, Haoyu Wang, Jing Gao, Lu Su, Xiaoze Liu, Xingchen Wang","submitted_at":"2024-07-03T12:02:24Z","abstract_excerpt":"Reinforcement learning with human feedback (RLHF) fine-tunes a pretrained large language model (LLM) using user preference data, enabling it to generate content aligned with human preferences. However, due to privacy concerns, users may be reluctant to share sensitive preference data. To address this, we propose utilizing Federated Learning (FL) techniques, allowing large-scale preference collection from diverse real-world users without requiring them to transmit data to a central server. Our federated RLHF methods (i.e., FedBis and FedBiscuit) encode each client's preferences into binary sele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03038","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.03038/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWRJvRQHujhuFM+7ggVmtrlzb9KW/sIE1XdkFpo5+b6T4+q6Rq45VSzlwLbtc+yZyNvS36Dh/ALLgzelMVToDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:19:45.582691Z"},"content_sha256":"1b3467f5c6fdd507a254d5d4312d6164ad80c9f8e84df96385bf689d6274b08a","schema_version":"1.0","event_id":"sha256:1b3467f5c6fdd507a254d5d4312d6164ad80c9f8e84df96385bf689d6274b08a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZVGL7G6L6BEWFH5JTH6ZLIPLU/bundle.json","state_url":"https://pith.science/pith/LZVGL7G6L6BEWFH5JTH6ZLIPLU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZVGL7G6L6BEWFH5JTH6ZLIPLU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T22:19:45Z","links":{"resolver":"https://pith.science/pith/LZVGL7G6L6BEWFH5JTH6ZLIPLU","bundle":"https://pith.science/pith/LZVGL7G6L6BEWFH5JTH6ZLIPLU/bundle.json","state":"https://pith.science/pith/LZVGL7G6L6BEWFH5JTH6ZLIPLU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZVGL7G6L6BEWFH5JTH6ZLIPLU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZVGL7G6L6BEWFH5JTH6ZLIPLU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c6ae028259c22654ce63f9b8c3ab7bdf5fe9ff678257fa94e5452b8b684513f6","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:02:24Z","title_canon_sha256":"bb1455013b54007c8ba787874af3b059a21204281d4910493ae7bb39c6021b9e"},"schema_version":"1.0","source":{"id":"2407.03038","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03038","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03038v3","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03038","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"LZVGL7G6L6BE","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"LZVGL7G6L6BEWFH5","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"LZVGL7G6","created_at":"2026-07-05T10:46:19Z"}],"graph_snapshots":[{"event_id":"sha256:1b3467f5c6fdd507a254d5d4312d6164ad80c9f8e84df96385bf689d6274b08a","target":"graph","created_at":"2026-07-05T10:46:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.03038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with human feedback (RLHF) fine-tunes a pretrained large language model (LLM) using user preference data, enabling it to generate content aligned with human preferences. However, due to privacy concerns, users may be reluctant to share sensitive preference data. To address this, we propose utilizing Federated Learning (FL) techniques, allowing large-scale preference collection from diverse real-world users without requiring them to transmit data to a central server. Our federated RLHF methods (i.e., FedBis and FedBiscuit) encode each client's preferences into binary sele","authors_text":"Feijie Wu, Haoyu Wang, Jing Gao, Lu Su, Xiaoze Liu, Xingchen Wang","cross_cats":["cs.DC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:02:24Z","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03038","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f3202c61e8079d5fb1fca9e81b37acd9337e81b792f8319ce9b26ae026bc88f5","target":"record","created_at":"2026-07-05T10:46:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c6ae028259c22654ce63f9b8c3ab7bdf5fe9ff678257fa94e5452b8b684513f6","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:02:24Z","title_canon_sha256":"bb1455013b54007c8ba787874af3b059a21204281d4910493ae7bb39c6021b9e"},"schema_version":"1.0","source":{"id":"2407.03038","kind":"arxiv","version":3}},"canonical_sha256":"5e6a65fcde5f824b14fd4ccfecad0f5d21797a508f57574de89b0c45e7eb8170","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e6a65fcde5f824b14fd4ccfecad0f5d21797a508f57574de89b0c45e7eb8170","first_computed_at":"2026-07-05T10:46:19.709949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:19.709949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hVGFklYOQtJkfVGOclf+CpoYai4NSOjTnH2YasaopyKdIiosPQ3BcuciJLFKX9w+8/TPsaiR3zcSN4z/pxp5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:19.710425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03038","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3202c61e8079d5fb1fca9e81b37acd9337e81b792f8319ce9b26ae026bc88f5","sha256:1b3467f5c6fdd507a254d5d4312d6164ad80c9f8e84df96385bf689d6274b08a"],"state_sha256":"00462f78cabbe038b1779c8962a8a4a96f237c8c3cc1612f4c9d86f938d63624"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TDZhuwnq4j2W9hg0naSbl99pY1svVbUnTNMVr1/zKOAOZGBPTxoCTuEGDy3OABxzbT2YXAybU10Ag1NL1gViCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:19:45.588045Z","bundle_sha256":"feed2eab0d019f6e20ce6da830061c77ecf57dd2e1b2c7aad1b60d1c27a97803"}}