{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X6JA7PIUVVQWXF65NOIBCN6J4L","short_pith_number":"pith:X6JA7PIU","schema_version":"1.0","canonical_sha256":"bf920fbd14ad616b97dd6b901137c9e2c2cb0d1c4d2ff857bb17a78d7d08011c","source":{"kind":"arxiv","id":"2606.31602","version":1},"attestation_state":"computed","paper":{"title":"Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Cezary Pilaszewicz, Gerhard Wunder, Jonas Sch\\\"afer","submitted_at":"2026-06-30T12:51:30Z","abstract_excerpt":"This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and token-level embeddings to enhance robustness against paraphrasing and translation. DEW utilizes a signal-processing methodology, applying algebraic vector-space operations to \\mbox{token and context embeddings to derive a watermark signal that degrades gracefully under semantic shifts. The method obfuscates the watermark by projecting embedding vectors through pseudo-random matrices seeded with a secret key. Relevant distributions derived from the "},"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":"2606.31602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T12:51:30Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"c2ee992a12cbd00e9e7d223c2f417a55157bfb41403f6da9263a19a61f5a3db7","abstract_canon_sha256":"7bc79ab5699076e57bf3b8b71687d6a6f0b9dbdce2fe3a17229a8ca6c697f968"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:08.836583Z","signature_b64":"4G46S3LutmEG+nAZbuTDUXTn57GJTsEkg9tPlz9cdI4p/b1LFvv3N+T+MAT57oaPk3iiG5tM8EQR+0cyC4uwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf920fbd14ad616b97dd6b901137c9e2c2cb0d1c4d2ff857bb17a78d7d08011c","last_reissued_at":"2026-07-01T01:18:08.836170Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:08.836170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Cezary Pilaszewicz, Gerhard Wunder, Jonas Sch\\\"afer","submitted_at":"2026-06-30T12:51:30Z","abstract_excerpt":"This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and token-level embeddings to enhance robustness against paraphrasing and translation. DEW utilizes a signal-processing methodology, applying algebraic vector-space operations to \\mbox{token and context embeddings to derive a watermark signal that degrades gracefully under semantic shifts. The method obfuscates the watermark by projecting embedding vectors through pseudo-random matrices seeded with a secret key. Relevant distributions derived from the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31602","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/2606.31602/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":"2606.31602","created_at":"2026-07-01T01:18:08.836229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31602v1","created_at":"2026-07-01T01:18:08.836229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31602","created_at":"2026-07-01T01:18:08.836229+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6JA7PIUVVQW","created_at":"2026-07-01T01:18:08.836229+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6JA7PIUVVQWXF65","created_at":"2026-07-01T01:18:08.836229+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6JA7PIU","created_at":"2026-07-01T01:18:08.836229+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/X6JA7PIUVVQWXF65NOIBCN6J4L","json":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L.json","graph_json":"https://pith.science/api/pith-number/X6JA7PIUVVQWXF65NOIBCN6J4L/graph.json","events_json":"https://pith.science/api/pith-number/X6JA7PIUVVQWXF65NOIBCN6J4L/events.json","paper":"https://pith.science/paper/X6JA7PIU"},"agent_actions":{"view_html":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L","download_json":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L.json","view_paper":"https://pith.science/paper/X6JA7PIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31602&json=true","fetch_graph":"https://pith.science/api/pith-number/X6JA7PIUVVQWXF65NOIBCN6J4L/graph.json","fetch_events":"https://pith.science/api/pith-number/X6JA7PIUVVQWXF65NOIBCN6J4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L/action/storage_attestation","attest_author":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L/action/author_attestation","sign_citation":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L/action/citation_signature","submit_replication":"https://pith.science/pith/X6JA7PIUVVQWXF65NOIBCN6J4L/action/replication_record"}},"created_at":"2026-07-01T01:18:08.836229+00:00","updated_at":"2026-07-01T01:18:08.836229+00:00"}