{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VPXEM6ESZOGQ25HZXNT2Q2YQZ3","short_pith_number":"pith:VPXEM6ES","canonical_record":{"source":{"id":"2403.05006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-08T03:05:11Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"cda025dc2b254b0d772c92ae3c957b474445365ca095908d0f4e4e58eef68ed4","abstract_canon_sha256":"6ededc216722f56f11acc847d7cf6147e8baf5e965e2eecb840d43d66c5d641c"},"schema_version":"1.0"},"canonical_sha256":"abee467892cb8d0d74f9bb67a86b10ceeffd8e8e430d775e166d757aa19e3c3c","source":{"kind":"arxiv","id":"2403.05006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05006","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05006v1","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05006","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"pith_short_12","alias_value":"VPXEM6ESZOGQ","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"pith_short_16","alias_value":"VPXEM6ESZOGQ25HZ","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"pith_short_8","alias_value":"VPXEM6ES","created_at":"2026-07-05T07:53:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VPXEM6ESZOGQ25HZXNT2Q2YQZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2403.05006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-08T03:05:11Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"cda025dc2b254b0d772c92ae3c957b474445365ca095908d0f4e4e58eef68ed4","abstract_canon_sha256":"6ededc216722f56f11acc847d7cf6147e8baf5e965e2eecb840d43d66c5d641c"},"schema_version":"1.0"},"canonical_sha256":"abee467892cb8d0d74f9bb67a86b10ceeffd8e8e430d775e166d757aa19e3c3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:37.089959Z","signature_b64":"wShuJvk99KTgeT8J1xpGm85hg6JOA8HrPEtjmMh+cB+zTFKQahsMAM1dxU++afVAkCPPF5mH4CpEcJfYXVXSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abee467892cb8d0d74f9bb67a86b10ceeffd8e8e430d775e166d757aa19e3c3c","last_reissued_at":"2026-07-05T07:53:37.089401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:37.089401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.05006","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g+G2IiZPIZWXpoAXIXuHIix3QymCK8db2mN4hVm4BHX3NKEzZlZ0FXkZJQ2RC0QXv8XXYsHv+15WjGLH7CofCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:56.279678Z"},"content_sha256":"b1db9801798085ab7822b9f801b55536d27c8f713d159bc49c01af0414738085","schema_version":"1.0","event_id":"sha256:b1db9801798085ab7822b9f801b55536d27c8f713d159bc49c01af0414738085"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VPXEM6ESZOGQ25HZXNT2Q2YQZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provable Multi-Party Reinforcement Learning with Diverse Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huiying Zhong, Linjun Zhang, Weijie J. Su, Zhiwei Steven Wu, Zhun Deng","submitted_at":"2024-03-08T03:05:11Z","abstract_excerpt":"Reinforcement learning with human feedback (RLHF) is an emerging paradigm to align models with human preferences. Typically, RLHF aggregates preferences from multiple individuals who have diverse viewpoints that may conflict with each other. Our work \\textit{initiates} the theoretical study of multi-party RLHF that explicitly models the diverse preferences of multiple individuals. We show how traditional RLHF approaches can fail since learning a single reward function cannot capture and balance the preferences of multiple individuals. To overcome such limitations, we incorporate meta-learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05006","kind":"arxiv","version":1},"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/2403.05006/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":"2026-07-05T07:53:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1RZJzZf5uaAKZ8JEfCsHyDkh8LfJ0J2NZ2WQc0yXjQj0NEvxsmcM3VDhGgG98SPC5I47LEf3Rdjz9UoGl5NmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:56.280290Z"},"content_sha256":"9293932defe2dd372273527de48f074193cb9e4bfdabe5a64ea7d7b672cc6689","schema_version":"1.0","event_id":"sha256:9293932defe2dd372273527de48f074193cb9e4bfdabe5a64ea7d7b672cc6689"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPXEM6ESZOGQ25HZXNT2Q2YQZ3/bundle.json","state_url":"https://pith.science/pith/VPXEM6ESZOGQ25HZXNT2Q2YQZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPXEM6ESZOGQ25HZXNT2Q2YQZ3/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":"2026-08-08T05:59:56Z","links":{"resolver":"https://pith.science/pith/VPXEM6ESZOGQ25HZXNT2Q2YQZ3","bundle":"https://pith.science/pith/VPXEM6ESZOGQ25HZXNT2Q2YQZ3/bundle.json","state":"https://pith.science/pith/VPXEM6ESZOGQ25HZXNT2Q2YQZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPXEM6ESZOGQ25HZXNT2Q2YQZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VPXEM6ESZOGQ25HZXNT2Q2YQZ3","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":"6ededc216722f56f11acc847d7cf6147e8baf5e965e2eecb840d43d66c5d641c","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-08T03:05:11Z","title_canon_sha256":"cda025dc2b254b0d772c92ae3c957b474445365ca095908d0f4e4e58eef68ed4"},"schema_version":"1.0","source":{"id":"2403.05006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05006","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05006v1","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05006","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"pith_short_12","alias_value":"VPXEM6ESZOGQ","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"pith_short_16","alias_value":"VPXEM6ESZOGQ25HZ","created_at":"2026-07-05T07:53:37Z"},{"alias_kind":"pith_short_8","alias_value":"VPXEM6ES","created_at":"2026-07-05T07:53:37Z"}],"graph_snapshots":[{"event_id":"sha256:9293932defe2dd372273527de48f074193cb9e4bfdabe5a64ea7d7b672cc6689","target":"graph","created_at":"2026-07-05T07:53:37Z","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/2403.05006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with human feedback (RLHF) is an emerging paradigm to align models with human preferences. Typically, RLHF aggregates preferences from multiple individuals who have diverse viewpoints that may conflict with each other. Our work \\textit{initiates} the theoretical study of multi-party RLHF that explicitly models the diverse preferences of multiple individuals. We show how traditional RLHF approaches can fail since learning a single reward function cannot capture and balance the preferences of multiple individuals. To overcome such limitations, we incorporate meta-learning ","authors_text":"Huiying Zhong, Linjun Zhang, Weijie J. Su, Zhiwei Steven Wu, Zhun Deng","cross_cats":["cs.AI","stat.ME","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-08T03:05:11Z","title":"Provable Multi-Party Reinforcement Learning with Diverse Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05006","kind":"arxiv","version":1},"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:b1db9801798085ab7822b9f801b55536d27c8f713d159bc49c01af0414738085","target":"record","created_at":"2026-07-05T07:53:37Z","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":"6ededc216722f56f11acc847d7cf6147e8baf5e965e2eecb840d43d66c5d641c","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-08T03:05:11Z","title_canon_sha256":"cda025dc2b254b0d772c92ae3c957b474445365ca095908d0f4e4e58eef68ed4"},"schema_version":"1.0","source":{"id":"2403.05006","kind":"arxiv","version":1}},"canonical_sha256":"abee467892cb8d0d74f9bb67a86b10ceeffd8e8e430d775e166d757aa19e3c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abee467892cb8d0d74f9bb67a86b10ceeffd8e8e430d775e166d757aa19e3c3c","first_computed_at":"2026-07-05T07:53:37.089401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:37.089401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wShuJvk99KTgeT8J1xpGm85hg6JOA8HrPEtjmMh+cB+zTFKQahsMAM1dxU++afVAkCPPF5mH4CpEcJfYXVXSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:37.089959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.05006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1db9801798085ab7822b9f801b55536d27c8f713d159bc49c01af0414738085","sha256:9293932defe2dd372273527de48f074193cb9e4bfdabe5a64ea7d7b672cc6689"],"state_sha256":"8b369eb5cc6447e1bab4f6ce863b1f34d4775d861479380cad68e49f0b635ae5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjHOq4Nel99sOFzj6HxszbMsd5p6DWEU1VjdZ8+5E5MNiyoXZHDBE6Qwo7ygE0mF5UuBSI90DSLsZRCwcJUzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:59:56.285635Z","bundle_sha256":"daed64c57cc7ab2e40c74ac70b322bc50fd9fb96b103f0549ba9c4675d84d978"}}