{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D3Y4Y3UAAIG6KAO46HDCS56J5X","short_pith_number":"pith:D3Y4Y3UA","schema_version":"1.0","canonical_sha256":"1ef1cc6e80020de501dcf1c62977c9edec3afd3058762feefda014f45f60d26c","source":{"kind":"arxiv","id":"2605.00348","version":2},"attestation_state":"computed","paper":{"title":"Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multi-bit LLM watermarking can reach 96.5 percent true positives at only 2 percent false positives by separating block-wise message estimation from window-shifting verification.","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Dongsup Jin, HoEun Kim, Joeun Kim, Young-Sik Kim","submitted_at":"2026-05-01T02:14:38Z","abstract_excerpt":"Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that existing ECC-based extractors suffer from catastrophic false positive rates (FPR), and applying rejection thresholds merely collapses detection sensitivity (TPR) to random guessing. To resolve this structural limitation, we propose BREW (Block-wise Reliable Embedding for Watermarking), a framework shifting the paradigm to designated verification. BREW employs a two-stage mechanism: (i) blind message estimation via indep"},"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":"2605.00348","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-01T02:14:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4ca2bdde56b513257ff507ae1f28d029ffdf3873c9723cf3edcfb4f1ca49c364","abstract_canon_sha256":"28a72ea14f482ecaa8763aeed73cc9423891c6b77830fe2e3feccf2f3150e2a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:28.156403Z","signature_b64":"gDd7GlMQ2uFkaMdUrJzRPgjFHip3q4W4dm+7lzctfcu8dnFufT4DM0h1FKhIPtNEdG40ApVCvLMpgLrli7WKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ef1cc6e80020de501dcf1c62977c9edec3afd3058762feefda014f45f60d26c","last_reissued_at":"2026-06-24T01:14:28.155958Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:28.155958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multi-bit LLM watermarking can reach 96.5 percent true positives at only 2 percent false positives by separating block-wise message estimation from window-shifting verification.","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Dongsup Jin, HoEun Kim, Joeun Kim, Young-Sik Kim","submitted_at":"2026-05-01T02:14:38Z","abstract_excerpt":"Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that existing ECC-based extractors suffer from catastrophic false positive rates (FPR), and applying rejection thresholds merely collapses detection sensitivity (TPR) to random guessing. To resolve this structural limitation, we propose BREW (Block-wise Reliable Embedding for Watermarking), a framework shifting the paradigm to designated verification. BREW employs a two-stage mechanism: (i) blind message estimation via indep"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"BREW achieves a TPR of 0.965 with an FPR of 0.02 under 10% synonym substitution, demonstrating that the high-FPR issue is not an inherent trade-off of multi-bit watermarking, but a solvable structural flaw of prior decoding-centric designs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The two-stage mechanism of blind message estimation via independent block voting followed by window-shifting verification will rigorously validate the payload against local edits without introducing new failure modes or depending on unstated properties of the underlying LLM distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"BREW achieves TPR of 0.965 and FPR of 0.02 under 10% synonym substitution by shifting from ECC decoding to designated verification with block voting and local validation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-bit LLM watermarking can reach 96.5 percent true positives at only 2 percent false positives by separating block-wise message estimation from window-shifting verification.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b93ed408c18f70d046c26235e83451050cc8471d734ee87a55802ce99ea28909"},"source":{"id":"2605.00348","kind":"arxiv","version":2},"verdict":{"id":"a3784704-10ea-49a3-811c-face440ae33c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T19:47:21.320421Z","strongest_claim":"BREW achieves a TPR of 0.965 with an FPR of 0.02 under 10% synonym substitution, demonstrating that the high-FPR issue is not an inherent trade-off of multi-bit watermarking, but a solvable structural flaw of prior decoding-centric designs.","one_line_summary":"BREW achieves TPR of 0.965 and FPR of 0.02 under 10% synonym substitution by shifting from ECC decoding to designated verification with block voting and local validation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The two-stage mechanism of blind message estimation via independent block voting followed by window-shifting verification will rigorously validate the payload against local edits without introducing new failure modes or depending on unstated properties of the underlying LLM distribution.","pith_extraction_headline":"Multi-bit LLM watermarking can reach 96.5 percent true positives at only 2 percent false positives by separating block-wise message estimation from window-shifting verification."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00348/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T20:34:05.716902Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:15:09.473497Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ea0137a75a35335d6421602ebe27dce79a09b89064afabd2a75d2f30a6a6258a"},"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":"2605.00348","created_at":"2026-06-24T01:14:28.156017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.00348v2","created_at":"2026-06-24T01:14:28.156017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00348","created_at":"2026-06-24T01:14:28.156017+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3Y4Y3UAAIG6","created_at":"2026-06-24T01:14:28.156017+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3Y4Y3UAAIG6KAO4","created_at":"2026-06-24T01:14:28.156017+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3Y4Y3UA","created_at":"2026-06-24T01:14:28.156017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X","json":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X.json","graph_json":"https://pith.science/api/pith-number/D3Y4Y3UAAIG6KAO46HDCS56J5X/graph.json","events_json":"https://pith.science/api/pith-number/D3Y4Y3UAAIG6KAO46HDCS56J5X/events.json","paper":"https://pith.science/paper/D3Y4Y3UA"},"agent_actions":{"view_html":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X","download_json":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X.json","view_paper":"https://pith.science/paper/D3Y4Y3UA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.00348&json=true","fetch_graph":"https://pith.science/api/pith-number/D3Y4Y3UAAIG6KAO46HDCS56J5X/graph.json","fetch_events":"https://pith.science/api/pith-number/D3Y4Y3UAAIG6KAO46HDCS56J5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X/action/storage_attestation","attest_author":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X/action/author_attestation","sign_citation":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X/action/citation_signature","submit_replication":"https://pith.science/pith/D3Y4Y3UAAIG6KAO46HDCS56J5X/action/replication_record"}},"created_at":"2026-06-24T01:14:28.156017+00:00","updated_at":"2026-06-24T01:14:28.156017+00:00"}