{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P53UNYGIV2O4ZVHYFY66WVDXBZ","short_pith_number":"pith:P53UNYGI","canonical_record":{"source":{"id":"2408.10075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T15:18:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"62b36c3662a8989bae5278dcb1defce990f44172d2534b0fec24a9f34a7cfc40","abstract_canon_sha256":"3c838fcaf55d46072f05c60175663dbb057b252d98f82d06dec8bfdd1a891045"},"schema_version":"1.0"},"canonical_sha256":"7f7746e0c8ae9dccd4f82e3deb54770e767a3892789286a7ba86b30412ced4de","source":{"kind":"arxiv","id":"2408.10075","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10075","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10075v1","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10075","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"pith_short_12","alias_value":"P53UNYGIV2O4","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"pith_short_16","alias_value":"P53UNYGIV2O4ZVHY","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"pith_short_8","alias_value":"P53UNYGI","created_at":"2026-07-05T08:56:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P53UNYGIV2O4ZVHYFY66WVDXBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T15:18:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"62b36c3662a8989bae5278dcb1defce990f44172d2534b0fec24a9f34a7cfc40","abstract_canon_sha256":"3c838fcaf55d46072f05c60175663dbb057b252d98f82d06dec8bfdd1a891045"},"schema_version":"1.0"},"canonical_sha256":"7f7746e0c8ae9dccd4f82e3deb54770e767a3892789286a7ba86b30412ced4de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:50.997814Z","signature_b64":"MjOoU00W34S9hYDKFYeaONLMMxVLcjKBegKQMUN5jx7YxQpwvvIbw2a1JG2M2wsomOePswOZUTIXk6zAIAs9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f7746e0c8ae9dccd4f82e3deb54770e767a3892789286a7ba86b30412ced4de","last_reissued_at":"2026-07-05T08:56:50.997437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:50.997437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10075","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":"2026-07-05T08:56:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sh6QpEei3GBDJAhiIm0aoEfoehclaL/+w7zVFtwQR7/lPQ/u10t3tm2BbR1SHmrcKb1XncgKr8llzXPcmPRcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:11:38.016227Z"},"content_sha256":"3a6bb2d7f051db79a10d2b20273a7535cd5b2c01a995c60ba13a60e4cc9ed1f9","schema_version":"1.0","event_id":"sha256:3a6bb2d7f051db79a10d2b20273a7535cd5b2c01a995c60ba13a60e4cc9ed1f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P53UNYGIV2O4ZVHYFY66WVDXBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Hamish Ivison, Natasha Jaques, Sriyash Poddar, Yanming Wan","submitted_at":"2024-08-19T15:18:30Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. When these differences arise, traditional RLHF frameworks simply average over them, leading to inaccurate rewards and poor performance for individual subgroups. To address the need for pluralistic alignment, we develop a class of multimodal RLHF methods. Our proposed techniques are based on a latent variable form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10075","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/2408.10075/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":"2026-07-05T08:56:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aqJASEP6IBPjLUTN5/L9ABMW8vGTsQrbnqHtpfDO7Ys7QwXPkcmk9uHaL/0al7rMBATENShMrkqK7q2OXbrADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:11:38.016764Z"},"content_sha256":"5ee87742b250d6d35d4e46db7b9148c61670b4b9565573799a80b0f09900b7eb","schema_version":"1.0","event_id":"sha256:5ee87742b250d6d35d4e46db7b9148c61670b4b9565573799a80b0f09900b7eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P53UNYGIV2O4ZVHYFY66WVDXBZ/bundle.json","state_url":"https://pith.science/pith/P53UNYGIV2O4ZVHYFY66WVDXBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P53UNYGIV2O4ZVHYFY66WVDXBZ/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":"2026-08-07T20:11:38Z","links":{"resolver":"https://pith.science/pith/P53UNYGIV2O4ZVHYFY66WVDXBZ","bundle":"https://pith.science/pith/P53UNYGIV2O4ZVHYFY66WVDXBZ/bundle.json","state":"https://pith.science/pith/P53UNYGIV2O4ZVHYFY66WVDXBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P53UNYGIV2O4ZVHYFY66WVDXBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P53UNYGIV2O4ZVHYFY66WVDXBZ","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":"3c838fcaf55d46072f05c60175663dbb057b252d98f82d06dec8bfdd1a891045","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T15:18:30Z","title_canon_sha256":"62b36c3662a8989bae5278dcb1defce990f44172d2534b0fec24a9f34a7cfc40"},"schema_version":"1.0","source":{"id":"2408.10075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10075","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10075v1","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10075","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"pith_short_12","alias_value":"P53UNYGIV2O4","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"pith_short_16","alias_value":"P53UNYGIV2O4ZVHY","created_at":"2026-07-05T08:56:50Z"},{"alias_kind":"pith_short_8","alias_value":"P53UNYGI","created_at":"2026-07-05T08:56:50Z"}],"graph_snapshots":[{"event_id":"sha256:5ee87742b250d6d35d4e46db7b9148c61670b4b9565573799a80b0f09900b7eb","target":"graph","created_at":"2026-07-05T08:56:50Z","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/2408.10075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. When these differences arise, traditional RLHF frameworks simply average over them, leading to inaccurate rewards and poor performance for individual subgroups. To address the need for pluralistic alignment, we develop a class of multimodal RLHF methods. Our proposed techniques are based on a latent variable form","authors_text":"Abhishek Gupta, Hamish Ivison, Natasha Jaques, Sriyash Poddar, Yanming Wan","cross_cats":["cs.AI","cs.CL","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T15:18:30Z","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10075","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":"sha256:3a6bb2d7f051db79a10d2b20273a7535cd5b2c01a995c60ba13a60e4cc9ed1f9","target":"record","created_at":"2026-07-05T08:56:50Z","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":"3c838fcaf55d46072f05c60175663dbb057b252d98f82d06dec8bfdd1a891045","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T15:18:30Z","title_canon_sha256":"62b36c3662a8989bae5278dcb1defce990f44172d2534b0fec24a9f34a7cfc40"},"schema_version":"1.0","source":{"id":"2408.10075","kind":"arxiv","version":1}},"canonical_sha256":"7f7746e0c8ae9dccd4f82e3deb54770e767a3892789286a7ba86b30412ced4de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f7746e0c8ae9dccd4f82e3deb54770e767a3892789286a7ba86b30412ced4de","first_computed_at":"2026-07-05T08:56:50.997437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:50.997437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MjOoU00W34S9hYDKFYeaONLMMxVLcjKBegKQMUN5jx7YxQpwvvIbw2a1JG2M2wsomOePswOZUTIXk6zAIAs9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:50.997814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a6bb2d7f051db79a10d2b20273a7535cd5b2c01a995c60ba13a60e4cc9ed1f9","sha256:5ee87742b250d6d35d4e46db7b9148c61670b4b9565573799a80b0f09900b7eb"],"state_sha256":"737b15e8d74ad07e5f456772f8e00165d4ec25b32a9ae2c61f632343a3457d2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5eEdVaoJDTBF+fHvriHux1SG5FVnf1aox4YYlqpQKKRmMf0PW+4HO1Ac3nwJjc3OwDyMdpXiGXK++NsFdriBAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:11:38.020718Z","bundle_sha256":"13b1a0eb13848059cf1eeab636a1e5f845a7831884165b4b71e98b807983676b"}}