{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O2U4ZQ4DVQMRSG6IBZNXHKI5JN","short_pith_number":"pith:O2U4ZQ4D","canonical_record":{"source":{"id":"2502.02787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T00:21:01Z","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"title_canon_sha256":"551945bda66c65087e5744697473966e7d77013e16c56a1732c0abb038f6150e","abstract_canon_sha256":"700d61b33023a5a09c25e3f8d68e8dde1c4fa95b466ad08670a7c12f3c8b7665"},"schema_version":"1.0"},"canonical_sha256":"76a9ccc383ac19191bc80e5b73a91d4b4bf125097af9f5dc7b3ae5b6da144c3e","source":{"kind":"arxiv","id":"2502.02787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02787","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02787v2","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02787","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"O2U4ZQ4DVQMR","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"O2U4ZQ4DVQMRSG6I","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"O2U4ZQ4D","created_at":"2026-07-05T12:09:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O2U4ZQ4DVQMRSG6IBZNXHKI5JN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T00:21:01Z","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"title_canon_sha256":"551945bda66c65087e5744697473966e7d77013e16c56a1732c0abb038f6150e","abstract_canon_sha256":"700d61b33023a5a09c25e3f8d68e8dde1c4fa95b466ad08670a7c12f3c8b7665"},"schema_version":"1.0"},"canonical_sha256":"76a9ccc383ac19191bc80e5b73a91d4b4bf125097af9f5dc7b3ae5b6da144c3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:12.847690Z","signature_b64":"Bl7ndXn9WiwCNwJhDKCFDFxpE6I2OftqcEPCTOjNAVbEfABQK+J2wOHAzME6Oe3V2QG0FbiWlda3WpYZbTDiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a9ccc383ac19191bc80e5b73a91d4b4bf125097af9f5dc7b3ae5b6da144c3e","last_reissued_at":"2026-07-05T12:09:12.847191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:12.847191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02787","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RrwXXVd3OMKrBL6iz5TQrqVL8SZR2ie0WPqcWORDQoIW4g/vIcbJM2lNG/FRHKHLBA3oofSGSbRoPtahZ4EMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:11:22.324354Z"},"content_sha256":"5f2c124c84f9042dd7a2a5154a2ba3efa4fb46bc6739c62468976705e3278b4b","schema_version":"1.0","event_id":"sha256:5f2c124c84f9042dd7a2a5154a2ba3efa4fb46bc6739c62468976705e3278b4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O2U4ZQ4DVQMRSG6IBZNXHKI5JN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amirhossein Dabiriaghdam, Lele Wang","submitted_at":"2025-02-05T00:21:01Z","abstract_excerpt":"The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring access to model internals, making it compatible with both open and API-based LLMs. By leveraging the similarity of semantic sentence embeddings combined with rejection sampling to embed detectable statistical patterns imperceptible to humans, and employing a soft counting mechanism, SimMark achieves robustness against paraphrasing attacks. Experimental results"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02787","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/2502.02787/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":"2026-07-05T12:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tuscR9qECMJ+7SWWGddOD7fB6cZ0EuwsCMwmieYhCqBncas4hWjKHu6E7nCSDIP7rxcaosyTFSQT8dKOa4IUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:11:22.324954Z"},"content_sha256":"1c58caa809788b4610f6948940ab54d0d01aedf09cdffea9843edf5cfd2a5176","schema_version":"1.0","event_id":"sha256:1c58caa809788b4610f6948940ab54d0d01aedf09cdffea9843edf5cfd2a5176"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O2U4ZQ4DVQMRSG6IBZNXHKI5JN/bundle.json","state_url":"https://pith.science/pith/O2U4ZQ4DVQMRSG6IBZNXHKI5JN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O2U4ZQ4DVQMRSG6IBZNXHKI5JN/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":"2026-08-07T19:11:22Z","links":{"resolver":"https://pith.science/pith/O2U4ZQ4DVQMRSG6IBZNXHKI5JN","bundle":"https://pith.science/pith/O2U4ZQ4DVQMRSG6IBZNXHKI5JN/bundle.json","state":"https://pith.science/pith/O2U4ZQ4DVQMRSG6IBZNXHKI5JN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O2U4ZQ4DVQMRSG6IBZNXHKI5JN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O2U4ZQ4DVQMRSG6IBZNXHKI5JN","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":"700d61b33023a5a09c25e3f8d68e8dde1c4fa95b466ad08670a7c12f3c8b7665","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T00:21:01Z","title_canon_sha256":"551945bda66c65087e5744697473966e7d77013e16c56a1732c0abb038f6150e"},"schema_version":"1.0","source":{"id":"2502.02787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02787","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02787v2","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02787","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"O2U4ZQ4DVQMR","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"O2U4ZQ4DVQMRSG6I","created_at":"2026-07-05T12:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"O2U4ZQ4D","created_at":"2026-07-05T12:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:1c58caa809788b4610f6948940ab54d0d01aedf09cdffea9843edf5cfd2a5176","target":"graph","created_at":"2026-07-05T12:09:12Z","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/2502.02787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring access to model internals, making it compatible with both open and API-based LLMs. By leveraging the similarity of semantic sentence embeddings combined with rejection sampling to embed detectable statistical patterns imperceptible to humans, and employing a soft counting mechanism, SimMark achieves robustness against paraphrasing attacks. Experimental results","authors_text":"Amirhossein Dabiriaghdam, Lele Wang","cross_cats":["cs.CR","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T00:21:01Z","title":"SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02787","kind":"arxiv","version":2},"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":"sha256:5f2c124c84f9042dd7a2a5154a2ba3efa4fb46bc6739c62468976705e3278b4b","target":"record","created_at":"2026-07-05T12:09:12Z","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":"700d61b33023a5a09c25e3f8d68e8dde1c4fa95b466ad08670a7c12f3c8b7665","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T00:21:01Z","title_canon_sha256":"551945bda66c65087e5744697473966e7d77013e16c56a1732c0abb038f6150e"},"schema_version":"1.0","source":{"id":"2502.02787","kind":"arxiv","version":2}},"canonical_sha256":"76a9ccc383ac19191bc80e5b73a91d4b4bf125097af9f5dc7b3ae5b6da144c3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76a9ccc383ac19191bc80e5b73a91d4b4bf125097af9f5dc7b3ae5b6da144c3e","first_computed_at":"2026-07-05T12:09:12.847191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:12.847191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bl7ndXn9WiwCNwJhDKCFDFxpE6I2OftqcEPCTOjNAVbEfABQK+J2wOHAzME6Oe3V2QG0FbiWlda3WpYZbTDiBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:12.847690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f2c124c84f9042dd7a2a5154a2ba3efa4fb46bc6739c62468976705e3278b4b","sha256:1c58caa809788b4610f6948940ab54d0d01aedf09cdffea9843edf5cfd2a5176"],"state_sha256":"c33732566876a6e6ab2c97385ed57003e7a161bba9a81d4768197d5636fb22b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKJlHSRKJ0Cd6lPH+qOQ122RtrlEbHETT1Yp1LcYguks+Xhzrbs/sTgQSTXTnvFJzoWFRCPwUhXhNFAi9xlFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:11:22.328950Z","bundle_sha256":"4b8683ccf04fbd857a49b97b6bd259cc35fe9f33aacb57fcda74233436e36423"}}