{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C7LDKPI7CR6QTP3TAVF2YM7GPP","short_pith_number":"pith:C7LDKPI7","canonical_record":{"source":{"id":"2503.19201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T23:01:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4ec4886af0e529e0dd154a90ad64ac724ba5389dc7699f8a49a96c827e95fa3","abstract_canon_sha256":"8860e6366b9e5dd549691e6e7ba731c90a3f249eb8a1a3b3670f7ac58f67af15"},"schema_version":"1.0"},"canonical_sha256":"17d6353d1f147d09bf73054bac33e67bd88b1fe3450123a52b509f010c1b093f","source":{"kind":"arxiv","id":"2503.19201","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19201","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19201v1","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19201","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"C7LDKPI7CR6Q","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"C7LDKPI7CR6QTP3T","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"C7LDKPI7","created_at":"2026-07-05T10:38:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C7LDKPI7CR6QTP3TAVF2YM7GPP","target":"record","payload":{"canonical_record":{"source":{"id":"2503.19201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T23:01:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4ec4886af0e529e0dd154a90ad64ac724ba5389dc7699f8a49a96c827e95fa3","abstract_canon_sha256":"8860e6366b9e5dd549691e6e7ba731c90a3f249eb8a1a3b3670f7ac58f67af15"},"schema_version":"1.0"},"canonical_sha256":"17d6353d1f147d09bf73054bac33e67bd88b1fe3450123a52b509f010c1b093f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:51.214550Z","signature_b64":"evT7x/05zk9t+pDLfwMeIky6cz+Yg4QK3Z6EkLSUyL/0E9zyT9WRREsjNMTSFIl2MOD5zj/qR7eF8Uevj+L+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17d6353d1f147d09bf73054bac33e67bd88b1fe3450123a52b509f010c1b093f","last_reissued_at":"2026-07-05T10:38:51.214079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:51.214079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.19201","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":"2026-07-05T10:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aYyN9pXJIQdLSoR1QshgrowZf5x9Pn60Rdm4W1MARct3LzDf/PeP79lDnKRBb4KdvuPkFXRJ5k3MwhXU/SArBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:13:15.292342Z"},"content_sha256":"311ea1662b00ad428c53fb29aff76166a2e03bc60f5b3007f20f163b0ef35249","schema_version":"1.0","event_id":"sha256:311ea1662b00ad428c53fb29aff76166a2e03bc60f5b3007f20f163b0ef35249"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C7LDKPI7CR6QTP3TAVF2YM7GPP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cong Shen, Donghao Li, Jing Yang, Peng Wang, Renpu Liu","submitted_at":"2025-03-24T23:01:08Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models. However, existing RLHF frameworks often assume that human preferences are relatively homogeneous and can be captured by a single, unified reward model. This assumption overlooks the inherent diversity and heterogeneity across individuals, limiting the adaptability of RLHF to personalized scenarios and risking misalignments that can diminish user satisfaction and trust in AI systems"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19201","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/2503.19201/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":"2026-07-05T10:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fVlkpm6Q6/JKZymUMaDMRQrMD6TMUhfXkLMXZAaqSE/TuRLD1e/S/Mpf6ejW0fUExC04RHMnjBOk4LH4BnAaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:13:15.292925Z"},"content_sha256":"b1f6d6c68b6a339964ea439022a294e4a64729c09c7df6f54e9aa414fd0ee463","schema_version":"1.0","event_id":"sha256:b1f6d6c68b6a339964ea439022a294e4a64729c09c7df6f54e9aa414fd0ee463"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C7LDKPI7CR6QTP3TAVF2YM7GPP/bundle.json","state_url":"https://pith.science/pith/C7LDKPI7CR6QTP3TAVF2YM7GPP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C7LDKPI7CR6QTP3TAVF2YM7GPP/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":"2026-08-05T08:13:15Z","links":{"resolver":"https://pith.science/pith/C7LDKPI7CR6QTP3TAVF2YM7GPP","bundle":"https://pith.science/pith/C7LDKPI7CR6QTP3TAVF2YM7GPP/bundle.json","state":"https://pith.science/pith/C7LDKPI7CR6QTP3TAVF2YM7GPP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C7LDKPI7CR6QTP3TAVF2YM7GPP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C7LDKPI7CR6QTP3TAVF2YM7GPP","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":"8860e6366b9e5dd549691e6e7ba731c90a3f249eb8a1a3b3670f7ac58f67af15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T23:01:08Z","title_canon_sha256":"e4ec4886af0e529e0dd154a90ad64ac724ba5389dc7699f8a49a96c827e95fa3"},"schema_version":"1.0","source":{"id":"2503.19201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19201","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19201v1","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19201","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"C7LDKPI7CR6Q","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"C7LDKPI7CR6QTP3T","created_at":"2026-07-05T10:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"C7LDKPI7","created_at":"2026-07-05T10:38:51Z"}],"graph_snapshots":[{"event_id":"sha256:b1f6d6c68b6a339964ea439022a294e4a64729c09c7df6f54e9aa414fd0ee463","target":"graph","created_at":"2026-07-05T10:38:51Z","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/2503.19201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models. However, existing RLHF frameworks often assume that human preferences are relatively homogeneous and can be captured by a single, unified reward model. This assumption overlooks the inherent diversity and heterogeneity across individuals, limiting the adaptability of RLHF to personalized scenarios and risking misalignments that can diminish user satisfaction and trust in AI systems","authors_text":"Cong Shen, Donghao Li, Jing Yang, Peng Wang, Renpu Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T23:01:08Z","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19201","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":"sha256:311ea1662b00ad428c53fb29aff76166a2e03bc60f5b3007f20f163b0ef35249","target":"record","created_at":"2026-07-05T10:38:51Z","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":"8860e6366b9e5dd549691e6e7ba731c90a3f249eb8a1a3b3670f7ac58f67af15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T23:01:08Z","title_canon_sha256":"e4ec4886af0e529e0dd154a90ad64ac724ba5389dc7699f8a49a96c827e95fa3"},"schema_version":"1.0","source":{"id":"2503.19201","kind":"arxiv","version":1}},"canonical_sha256":"17d6353d1f147d09bf73054bac33e67bd88b1fe3450123a52b509f010c1b093f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17d6353d1f147d09bf73054bac33e67bd88b1fe3450123a52b509f010c1b093f","first_computed_at":"2026-07-05T10:38:51.214079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:51.214079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"evT7x/05zk9t+pDLfwMeIky6cz+Yg4QK3Z6EkLSUyL/0E9zyT9WRREsjNMTSFIl2MOD5zj/qR7eF8Uevj+L+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:51.214550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:311ea1662b00ad428c53fb29aff76166a2e03bc60f5b3007f20f163b0ef35249","sha256:b1f6d6c68b6a339964ea439022a294e4a64729c09c7df6f54e9aa414fd0ee463"],"state_sha256":"e065b4f3809fe9234bae2fb98a30aab3fdaa2e5b374227c6f56a95f76d4e655c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HlUWdMvjgqSN3PJoEz3zmlWNg1/uon4UIOoZjRObc+JNm3uRYqTKaGlNp71iGZp+LN0fRRkzfkrNUuUrrSIiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:13:15.296824Z","bundle_sha256":"c621bf9d5a7a74b35ee17907a9943fc97abac113c24a8cb25eeced16da49e74b"}}