{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:72PMFWHBGTRQDBEN5LMC24A26B","short_pith_number":"pith:72PMFWHB","schema_version":"1.0","canonical_sha256":"fe9ec2d8e134e301848dead82d701af07d8f97b1cf55e40d8575a3ad0073b1b2","source":{"kind":"arxiv","id":"2409.09739","version":2},"attestation_state":"computed","paper":{"title":"PersonaMark: Personalized LLM watermarking for model protection and user attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Jiawei Liu, Peizhuo Lv, Wei Lu, Xiaofeng Wang, Xiaozhong Liu, Yinpeng Liu, Yongqiang Ma, Yuehan Zhang","submitted_at":"2024-09-15T14:10:01Z","abstract_excerpt":"The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private LLMs, safeguarding model copyright and ensuring data privacy have become critical. Text watermarking has emerged as a viable solution for detecting AI-generated content and protecting models. However, existing methods fall short in providing individualized watermarks for each user, a critical feature for enhancing accountability and traceability. In this pape"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.09739","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-09-15T14:10:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c16ba8f96bdf305b788de9adc1a2819e44581b45be4c43ac7303f2f1b87c4180","abstract_canon_sha256":"2d8c35e9ed0b880c4373d334a6a2a6cde2b83e72dc908339423e7b21eea5bccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:33.021147Z","signature_b64":"Vm1zCDGZAtwQyc5ToJyMwxQH8uobZoFRhL3SOawJIpq7Fxn4vS54Lwoxd/DMpAIUQq3Pt1swgiUf6MaKioDRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9ec2d8e134e301848dead82d701af07d8f97b1cf55e40d8575a3ad0073b1b2","last_reissued_at":"2026-07-05T09:50:33.020665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:33.020665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PersonaMark: Personalized LLM watermarking for model protection and user attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Jiawei Liu, Peizhuo Lv, Wei Lu, Xiaofeng Wang, Xiaozhong Liu, Yinpeng Liu, Yongqiang Ma, Yuehan Zhang","submitted_at":"2024-09-15T14:10:01Z","abstract_excerpt":"The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private LLMs, safeguarding model copyright and ensuring data privacy have become critical. Text watermarking has emerged as a viable solution for detecting AI-generated content and protecting models. However, existing methods fall short in providing individualized watermarks for each user, a critical feature for enhancing accountability and traceability. In this pape"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09739","kind":"arxiv","version":2},"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/2409.09739/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.09739","created_at":"2026-07-05T09:50:33.020722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09739v2","created_at":"2026-07-05T09:50:33.020722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09739","created_at":"2026-07-05T09:50:33.020722+00:00"},{"alias_kind":"pith_short_12","alias_value":"72PMFWHBGTRQ","created_at":"2026-07-05T09:50:33.020722+00:00"},{"alias_kind":"pith_short_16","alias_value":"72PMFWHBGTRQDBEN","created_at":"2026-07-05T09:50:33.020722+00:00"},{"alias_kind":"pith_short_8","alias_value":"72PMFWHB","created_at":"2026-07-05T09:50:33.020722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25796","citing_title":"SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B","json":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B.json","graph_json":"https://pith.science/api/pith-number/72PMFWHBGTRQDBEN5LMC24A26B/graph.json","events_json":"https://pith.science/api/pith-number/72PMFWHBGTRQDBEN5LMC24A26B/events.json","paper":"https://pith.science/paper/72PMFWHB"},"agent_actions":{"view_html":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B","download_json":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B.json","view_paper":"https://pith.science/paper/72PMFWHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09739&json=true","fetch_graph":"https://pith.science/api/pith-number/72PMFWHBGTRQDBEN5LMC24A26B/graph.json","fetch_events":"https://pith.science/api/pith-number/72PMFWHBGTRQDBEN5LMC24A26B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B/action/storage_attestation","attest_author":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B/action/author_attestation","sign_citation":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B/action/citation_signature","submit_replication":"https://pith.science/pith/72PMFWHBGTRQDBEN5LMC24A26B/action/replication_record"}},"created_at":"2026-07-05T09:50:33.020722+00:00","updated_at":"2026-07-05T09:50:33.020722+00:00"}