{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:POXXJHGIESYU3ODWKMTEQIS4SA","short_pith_number":"pith:POXXJHGI","canonical_record":{"source":{"id":"2607.21067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T09:00:20Z","cross_cats_sorted":[],"title_canon_sha256":"30b2a00965806fb633e153e011a37cb05e24cc419e4c479d1951b5f47eec8b0b","abstract_canon_sha256":"6d3774e3800961310ed6041cf3b44ad61d9d9cb9d6d03b1bf52439316245e0b1"},"schema_version":"1.0"},"canonical_sha256":"7baf749cc824b14db876532648225c9000041bd5379a3cb0019d559f13698637","source":{"kind":"arxiv","id":"2607.21067","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21067","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21067v1","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21067","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"POXXJHGIESYU","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"POXXJHGIESYU3ODW","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"POXXJHGI","created_at":"2026-07-24T01:23:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:POXXJHGIESYU3ODWKMTEQIS4SA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T09:00:20Z","cross_cats_sorted":[],"title_canon_sha256":"30b2a00965806fb633e153e011a37cb05e24cc419e4c479d1951b5f47eec8b0b","abstract_canon_sha256":"6d3774e3800961310ed6041cf3b44ad61d9d9cb9d6d03b1bf52439316245e0b1"},"schema_version":"1.0"},"canonical_sha256":"7baf749cc824b14db876532648225c9000041bd5379a3cb0019d559f13698637","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:50.109373Z","signature_b64":"8aqwwCg7/WUcbBu14HulxSXvIL3sHgTDaT7rH8u8kGCWXiV69WomS9pa2MqcTDPHHNYrwvsyrL6P54PIUrHsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7baf749cc824b14db876532648225c9000041bd5379a3cb0019d559f13698637","last_reissued_at":"2026-07-24T01:23:50.108532Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:50.108532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21067","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":"2026-07-24T01:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YV+V0EupXZtrzRp+fkZrGZyt7dmeeycjEin6CMzJ1/I7CyOLle/nh1TJZ7VsJOBRJfU83qSxMvRXsrVepmZKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:48:01.162223Z"},"content_sha256":"6af7f705bd044b318dd79b76c40f26737c5dc84411b6cbd5d135c702ef32c49c","schema_version":"1.0","event_id":"sha256:6af7f705bd044b318dd79b76c40f26737c5dc84411b6cbd5d135c702ef32c49c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:POXXJHGIESYU3ODWKMTEQIS4SA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PrefReward: Learning User Preference Matrix for Personalized Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengbing Wang, Fuli Feng, Xiaoyan Zhao, Yang Zhang, Yimeng Bai, Yue Wu","submitted_at":"2026-07-23T09:00:20Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. However, most existing personalization approaches rely on implicit representations within model parameters, making it difficult to interpret user-specific preferences or effectively handle long-context dependencies. To address these challenges, we propose PrefReward, a novel preference-aware generative framework that explicitly models user styles through a structured preference matrix and integrates it into the decoding process as a reward signa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21067","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/2607.21067/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":"2026-07-24T01:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R0V87Pgv0uWL/GXE2KIWkZmoOngxzn5BKh46QRs48/hIippqL52eN9vG/03lCN6aX5G+8I75p0z8f0Mj09zIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:48:01.163162Z"},"content_sha256":"23d0419eaf58e774e004286dcf36d697cf278a52b2a1a764616235fb299fdc1a","schema_version":"1.0","event_id":"sha256:23d0419eaf58e774e004286dcf36d697cf278a52b2a1a764616235fb299fdc1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POXXJHGIESYU3ODWKMTEQIS4SA/bundle.json","state_url":"https://pith.science/pith/POXXJHGIESYU3ODWKMTEQIS4SA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POXXJHGIESYU3ODWKMTEQIS4SA/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":"2026-08-05T02:48:01Z","links":{"resolver":"https://pith.science/pith/POXXJHGIESYU3ODWKMTEQIS4SA","bundle":"https://pith.science/pith/POXXJHGIESYU3ODWKMTEQIS4SA/bundle.json","state":"https://pith.science/pith/POXXJHGIESYU3ODWKMTEQIS4SA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POXXJHGIESYU3ODWKMTEQIS4SA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:POXXJHGIESYU3ODWKMTEQIS4SA","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":"6d3774e3800961310ed6041cf3b44ad61d9d9cb9d6d03b1bf52439316245e0b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T09:00:20Z","title_canon_sha256":"30b2a00965806fb633e153e011a37cb05e24cc419e4c479d1951b5f47eec8b0b"},"schema_version":"1.0","source":{"id":"2607.21067","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21067","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21067v1","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21067","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"POXXJHGIESYU","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"POXXJHGIESYU3ODW","created_at":"2026-07-24T01:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"POXXJHGI","created_at":"2026-07-24T01:23:50Z"}],"graph_snapshots":[{"event_id":"sha256:23d0419eaf58e774e004286dcf36d697cf278a52b2a1a764616235fb299fdc1a","target":"graph","created_at":"2026-07-24T01:23:50Z","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/2607.21067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable ability in generating personalized content by leveraging user histories and contextual cues. However, most existing personalization approaches rely on implicit representations within model parameters, making it difficult to interpret user-specific preferences or effectively handle long-context dependencies. To address these challenges, we propose PrefReward, a novel preference-aware generative framework that explicitly models user styles through a structured preference matrix and integrates it into the decoding process as a reward signa","authors_text":"Chengbing Wang, Fuli Feng, Xiaoyan Zhao, Yang Zhang, Yimeng Bai, Yue Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T09:00:20Z","title":"PrefReward: Learning User Preference Matrix for Personalized Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21067","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":"sha256:6af7f705bd044b318dd79b76c40f26737c5dc84411b6cbd5d135c702ef32c49c","target":"record","created_at":"2026-07-24T01:23:50Z","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":"6d3774e3800961310ed6041cf3b44ad61d9d9cb9d6d03b1bf52439316245e0b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T09:00:20Z","title_canon_sha256":"30b2a00965806fb633e153e011a37cb05e24cc419e4c479d1951b5f47eec8b0b"},"schema_version":"1.0","source":{"id":"2607.21067","kind":"arxiv","version":1}},"canonical_sha256":"7baf749cc824b14db876532648225c9000041bd5379a3cb0019d559f13698637","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7baf749cc824b14db876532648225c9000041bd5379a3cb0019d559f13698637","first_computed_at":"2026-07-24T01:23:50.108532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:50.108532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8aqwwCg7/WUcbBu14HulxSXvIL3sHgTDaT7rH8u8kGCWXiV69WomS9pa2MqcTDPHHNYrwvsyrL6P54PIUrHsCA==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:50.109373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21067","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6af7f705bd044b318dd79b76c40f26737c5dc84411b6cbd5d135c702ef32c49c","sha256:23d0419eaf58e774e004286dcf36d697cf278a52b2a1a764616235fb299fdc1a"],"state_sha256":"9f9d1c25e93cd796275b86ff198a789737b50702f38c32b9c9ac1b4b80e5b850"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPSGgtR+UOmLulFxio1X7b3din5q/QBkGK+dZCKqkDRTv6b4YOV+4N1hr2oPUU7xRHV75dS3GUc3cOAuIXX4BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:48:01.168529Z","bundle_sha256":"0a91756fc8e319491c56399ef609268fa59292a9b8fc65e890d677f01c03e9c8"}}