{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6I4A45FNXLOTDBQ26TJ6V3KHX","short_pith_number":"pith:M6I4A45F","schema_version":"1.0","canonical_sha256":"6791c073a56dd6e98c30d7a69f576a3ddd98ea4ddc846b4563c9033b1fa0fe61","source":{"kind":"arxiv","id":"2402.16578","version":1},"attestation_state":"computed","paper":{"title":"Multi-Bit Distortion-Free Watermarking for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Brian Mark, Kai Zeng, Massieh Kordi Boroujeny, Ya Jiang","submitted_at":"2024-02-26T14:01:34Z","abstract_excerpt":"Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the watermark to adversarial detection. More recently, distortion-free watermarking methods were proposed that require a secret key to detect the watermark. The prior methods generally embed zero-bit watermarks that do not provide additional information beyond tagging a text as being AI-generated. We extend an existing zero-bit distortion-free watermarking method"},"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":"2402.16578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T14:01:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e333c15042697e987ef02fa3ef3ad1df6fb372893c7ed6dfb8dbac907e7d8599","abstract_canon_sha256":"dc2b50d315c161feb3ace2da10917572633c7bc3fdc332785b344010acee10d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:23.866278Z","signature_b64":"yMxJZ7IHC++qXc3Vu1lU9orrk3fS3db1u8bhPDZvOdByDaQaRPEbtcS7q4dUCgRPGaqMP6HpWCuJHHsw0ezHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6791c073a56dd6e98c30d7a69f576a3ddd98ea4ddc846b4563c9033b1fa0fe61","last_reissued_at":"2026-07-05T07:49:23.865813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:23.865813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Bit Distortion-Free Watermarking for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Brian Mark, Kai Zeng, Massieh Kordi Boroujeny, Ya Jiang","submitted_at":"2024-02-26T14:01:34Z","abstract_excerpt":"Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the watermark to adversarial detection. More recently, distortion-free watermarking methods were proposed that require a secret key to detect the watermark. The prior methods generally embed zero-bit watermarks that do not provide additional information beyond tagging a text as being AI-generated. We extend an existing zero-bit distortion-free watermarking method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16578","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/2402.16578/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":"2402.16578","created_at":"2026-07-05T07:49:23.865881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16578v1","created_at":"2026-07-05T07:49:23.865881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16578","created_at":"2026-07-05T07:49:23.865881+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6I4A45FNXLO","created_at":"2026-07-05T07:49:23.865881+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6I4A45FNXLOTDBQ","created_at":"2026-07-05T07:49:23.865881+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6I4A45F","created_at":"2026-07-05T07:49:23.865881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05353","citing_title":"Selective Disclosure Watermarking for Large Language Models","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28425","citing_title":"Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18333","citing_title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08826","citing_title":"Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08759","citing_title":"Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX","json":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX.json","graph_json":"https://pith.science/api/pith-number/M6I4A45FNXLOTDBQ26TJ6V3KHX/graph.json","events_json":"https://pith.science/api/pith-number/M6I4A45FNXLOTDBQ26TJ6V3KHX/events.json","paper":"https://pith.science/paper/M6I4A45F"},"agent_actions":{"view_html":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX","download_json":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX.json","view_paper":"https://pith.science/paper/M6I4A45F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16578&json=true","fetch_graph":"https://pith.science/api/pith-number/M6I4A45FNXLOTDBQ26TJ6V3KHX/graph.json","fetch_events":"https://pith.science/api/pith-number/M6I4A45FNXLOTDBQ26TJ6V3KHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX/action/storage_attestation","attest_author":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX/action/author_attestation","sign_citation":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX/action/citation_signature","submit_replication":"https://pith.science/pith/M6I4A45FNXLOTDBQ26TJ6V3KHX/action/replication_record"}},"created_at":"2026-07-05T07:49:23.865881+00:00","updated_at":"2026-07-05T07:49:23.865881+00:00"}