{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GBXYIWFJNRYBJ36S6KGX4RLNLG","short_pith_number":"pith:GBXYIWFJ","canonical_record":{"source":{"id":"2504.14439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T01:16:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4629822b2a45d965e804ca51797da9942ae9a7d5f7071eee8b886e93e45914f1","abstract_canon_sha256":"f6be715ca925aa591029ee1d5f4060d77cfd98f6647ed8807d141040f3991360"},"schema_version":"1.0"},"canonical_sha256":"306f8458a96c7014efd2f28d7e456d599fa50217837f5fa471c5397d28290727","source":{"kind":"arxiv","id":"2504.14439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14439","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14439v1","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14439","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"pith_short_12","alias_value":"GBXYIWFJNRYB","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"pith_short_16","alias_value":"GBXYIWFJNRYBJ36S","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"pith_short_8","alias_value":"GBXYIWFJ","created_at":"2026-07-05T10:51:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GBXYIWFJNRYBJ36S6KGX4RLNLG","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T01:16:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4629822b2a45d965e804ca51797da9942ae9a7d5f7071eee8b886e93e45914f1","abstract_canon_sha256":"f6be715ca925aa591029ee1d5f4060d77cfd98f6647ed8807d141040f3991360"},"schema_version":"1.0"},"canonical_sha256":"306f8458a96c7014efd2f28d7e456d599fa50217837f5fa471c5397d28290727","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:43.416802Z","signature_b64":"TqinpLMt13q93UFvooCe8ZbokJpCNG2h5iSnF2OBq1a77MgLyWF5JV7an2Fjo7uH2Ju1CmO61vfHRXqiZ8aSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"306f8458a96c7014efd2f28d7e456d599fa50217837f5fa471c5397d28290727","last_reissued_at":"2026-07-05T10:51:43.416272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:43.416272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14439","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":"2026-07-05T10:51:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GclYZDMKEa5i2ntJU9iBhWoIaZsxHQHgsZrnGsnc8syNnMbK/HtI4W47kvaAhLQo31fu89g5tiIIcd0uKQq4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:50:49.901435Z"},"content_sha256":"64dbe31e41f09178d70a8c91f5d2821cab74c9eafc7e91ce31f19161a3b71a52","schema_version":"1.0","event_id":"sha256:64dbe31e41f09178d70a8c91f5d2821cab74c9eafc7e91ce31f19161a3b71a52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GBXYIWFJNRYBJ36S6KGX4RLNLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Avinandan Bose, Lin Xiao, Maryam Fazel, Simon Shaolei Du, Yuejie Chi, Zhihan Xiong","submitted_at":"2025-04-20T01:16:24Z","abstract_excerpt":"Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches often rely on monolithic value representations, limiting their ability to adapt to individual preferences. We introduce a novel framework that leverages low-rank preference modeling to efficiently learn and generalize user-specific reward functions. By representing reward functions in a low-dimensional subspace and modeling individual preferences as weighted combinations of shared "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14439","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/2504.14439/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":"2026-07-05T10:51:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQKdZjliLXafIp5fJIrKm/RRLAVRDsH0eEdJR0v4rLPTMAHlyw9zRHpyXnzFKLMsCgIx82wVRZu/Wmd4fMEQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:50:49.902054Z"},"content_sha256":"039394cd6e55d84f604ed497a6ef4317a37314f9e2f379fc411d56e119d78b75","schema_version":"1.0","event_id":"sha256:039394cd6e55d84f604ed497a6ef4317a37314f9e2f379fc411d56e119d78b75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GBXYIWFJNRYBJ36S6KGX4RLNLG/bundle.json","state_url":"https://pith.science/pith/GBXYIWFJNRYBJ36S6KGX4RLNLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GBXYIWFJNRYBJ36S6KGX4RLNLG/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":"2026-08-23T18:50:49Z","links":{"resolver":"https://pith.science/pith/GBXYIWFJNRYBJ36S6KGX4RLNLG","bundle":"https://pith.science/pith/GBXYIWFJNRYBJ36S6KGX4RLNLG/bundle.json","state":"https://pith.science/pith/GBXYIWFJNRYBJ36S6KGX4RLNLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GBXYIWFJNRYBJ36S6KGX4RLNLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GBXYIWFJNRYBJ36S6KGX4RLNLG","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":"f6be715ca925aa591029ee1d5f4060d77cfd98f6647ed8807d141040f3991360","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T01:16:24Z","title_canon_sha256":"4629822b2a45d965e804ca51797da9942ae9a7d5f7071eee8b886e93e45914f1"},"schema_version":"1.0","source":{"id":"2504.14439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14439","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14439v1","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14439","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"pith_short_12","alias_value":"GBXYIWFJNRYB","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"pith_short_16","alias_value":"GBXYIWFJNRYBJ36S","created_at":"2026-07-05T10:51:43Z"},{"alias_kind":"pith_short_8","alias_value":"GBXYIWFJ","created_at":"2026-07-05T10:51:43Z"}],"graph_snapshots":[{"event_id":"sha256:039394cd6e55d84f604ed497a6ef4317a37314f9e2f379fc411d56e119d78b75","target":"graph","created_at":"2026-07-05T10:51:43Z","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/2504.14439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches often rely on monolithic value representations, limiting their ability to adapt to individual preferences. We introduce a novel framework that leverages low-rank preference modeling to efficiently learn and generalize user-specific reward functions. By representing reward functions in a low-dimensional subspace and modeling individual preferences as weighted combinations of shared ","authors_text":"Avinandan Bose, Lin Xiao, Maryam Fazel, Simon Shaolei Du, Yuejie Chi, Zhihan Xiong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T01:16:24Z","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14439","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":"sha256:64dbe31e41f09178d70a8c91f5d2821cab74c9eafc7e91ce31f19161a3b71a52","target":"record","created_at":"2026-07-05T10:51:43Z","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":"f6be715ca925aa591029ee1d5f4060d77cfd98f6647ed8807d141040f3991360","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T01:16:24Z","title_canon_sha256":"4629822b2a45d965e804ca51797da9942ae9a7d5f7071eee8b886e93e45914f1"},"schema_version":"1.0","source":{"id":"2504.14439","kind":"arxiv","version":1}},"canonical_sha256":"306f8458a96c7014efd2f28d7e456d599fa50217837f5fa471c5397d28290727","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"306f8458a96c7014efd2f28d7e456d599fa50217837f5fa471c5397d28290727","first_computed_at":"2026-07-05T10:51:43.416272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:43.416272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TqinpLMt13q93UFvooCe8ZbokJpCNG2h5iSnF2OBq1a77MgLyWF5JV7an2Fjo7uH2Ju1CmO61vfHRXqiZ8aSBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:43.416802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64dbe31e41f09178d70a8c91f5d2821cab74c9eafc7e91ce31f19161a3b71a52","sha256:039394cd6e55d84f604ed497a6ef4317a37314f9e2f379fc411d56e119d78b75"],"state_sha256":"b7d6348d0dd4d66d047eae9e6c2920ced2b6a5a88bea2090d7b6ec3048b63bc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YkYjXcmC2SbCO0j37hCO7ULxSsgpfm0p8s/DtCiBJZprhvBt8Q9OVByAlYImpgBLy9LhsI/L/0v85xMleGidAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:50:49.906647Z","bundle_sha256":"ad53ff61874f546914f0ae397e8e421200381a759df332b877d0f804340eaac9"}}