{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BU733HFJ2QERI6RZHNQ3FU7CFR","short_pith_number":"pith:BU733HFJ","canonical_record":{"source":{"id":"2503.04036","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-06T02:40:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6dd411147f98a8a853a01bc2dd6cc15dd3743d352fd6dc498d2e3a26ac6e579b","abstract_canon_sha256":"ea122faa87ee0a3bd409ab40f0d976de575be6db7d286ac217396540881a1849"},"schema_version":"1.0"},"canonical_sha256":"0d3fbd9ca9d409147a393b61b2d3e22c67407569e6a5c1330a8b15015be69693","source":{"kind":"arxiv","id":"2503.04036","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04036","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04036v3","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04036","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"BU733HFJ2QER","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"BU733HFJ2QERI6RZ","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"BU733HFJ","created_at":"2026-07-05T11:43:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BU733HFJ2QERI6RZHNQ3FU7CFR","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04036","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-06T02:40:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6dd411147f98a8a853a01bc2dd6cc15dd3743d352fd6dc498d2e3a26ac6e579b","abstract_canon_sha256":"ea122faa87ee0a3bd409ab40f0d976de575be6db7d286ac217396540881a1849"},"schema_version":"1.0"},"canonical_sha256":"0d3fbd9ca9d409147a393b61b2d3e22c67407569e6a5c1330a8b15015be69693","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:30.966882Z","signature_b64":"n4zZta7QjxLoyDN3RDFaAPpH8UURMkzSVpmBMS90KQvBBeTY5Eblt/O5/S7DEifXaXL5FeLZ2dNcbJkDcFXmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d3fbd9ca9d409147a393b61b2d3e22c67407569e6a5c1330a8b15015be69693","last_reissued_at":"2026-07-05T11:43:30.966370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:30.966370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04036","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j1aP/C3loOT37MCNiSYsGRTOhQ3jr6U4ZSr6M+kZjDvVy9+nveIK0I6qYkNl1X8GEJY10iAkvnfj+A+C9cQGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:14:09.784749Z"},"content_sha256":"fa5bf37f163868490cd253e847084b8e93d0276d7139d115c4fee6b38ef01a92","schema_version":"1.0","event_id":"sha256:fa5bf37f163868490cd253e847084b8e93d0276d7139d115c4fee6b38ef01a92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BU733HFJ2QERI6RZHNQ3FU7CFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Johnny Tian-Zheng Wei, Robin Jia, Swabha Swayamdipta, Xinyue Cui","submitted_at":"2025-03-06T02:40:51Z","abstract_excerpt":"Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data watermarking techniques primarily focus on effective memorization during pretraining, while overlooking challenges that arise in other stages of the LLM lifecycle, such as the risk of watermark filtering during data preprocessing and verification difficulties due to API-only access. To address these challenges, we propose a novel data watermarking approach that injects"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04036","kind":"arxiv","version":3},"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/2503.04036/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":"2026-07-05T11:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSwmesw3yTD2N5nW9OhrdpJbTfM589HVoDlY1HZTZ8jSIv94/AqETUuz0RfsQUtMSuHi1ZVPjxOisZDc1AHTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:14:09.785296Z"},"content_sha256":"228d8d3e13c2065a108bd2bad0a2a1adf7ead05f81920063b5c485b06fe687f5","schema_version":"1.0","event_id":"sha256:228d8d3e13c2065a108bd2bad0a2a1adf7ead05f81920063b5c485b06fe687f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BU733HFJ2QERI6RZHNQ3FU7CFR/bundle.json","state_url":"https://pith.science/pith/BU733HFJ2QERI6RZHNQ3FU7CFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BU733HFJ2QERI6RZHNQ3FU7CFR/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":"2026-08-09T20:14:09Z","links":{"resolver":"https://pith.science/pith/BU733HFJ2QERI6RZHNQ3FU7CFR","bundle":"https://pith.science/pith/BU733HFJ2QERI6RZHNQ3FU7CFR/bundle.json","state":"https://pith.science/pith/BU733HFJ2QERI6RZHNQ3FU7CFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BU733HFJ2QERI6RZHNQ3FU7CFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BU733HFJ2QERI6RZHNQ3FU7CFR","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":"ea122faa87ee0a3bd409ab40f0d976de575be6db7d286ac217396540881a1849","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-06T02:40:51Z","title_canon_sha256":"6dd411147f98a8a853a01bc2dd6cc15dd3743d352fd6dc498d2e3a26ac6e579b"},"schema_version":"1.0","source":{"id":"2503.04036","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04036","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04036v3","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04036","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"BU733HFJ2QER","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"BU733HFJ2QERI6RZ","created_at":"2026-07-05T11:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"BU733HFJ","created_at":"2026-07-05T11:43:30Z"}],"graph_snapshots":[{"event_id":"sha256:228d8d3e13c2065a108bd2bad0a2a1adf7ead05f81920063b5c485b06fe687f5","target":"graph","created_at":"2026-07-05T11:43:30Z","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/2503.04036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data watermarking techniques primarily focus on effective memorization during pretraining, while overlooking challenges that arise in other stages of the LLM lifecycle, such as the risk of watermark filtering during data preprocessing and verification difficulties due to API-only access. To address these challenges, we propose a novel data watermarking approach that injects","authors_text":"Johnny Tian-Zheng Wei, Robin Jia, Swabha Swayamdipta, Xinyue Cui","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-06T02:40:51Z","title":"Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04036","kind":"arxiv","version":3},"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:fa5bf37f163868490cd253e847084b8e93d0276d7139d115c4fee6b38ef01a92","target":"record","created_at":"2026-07-05T11:43:30Z","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":"ea122faa87ee0a3bd409ab40f0d976de575be6db7d286ac217396540881a1849","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-06T02:40:51Z","title_canon_sha256":"6dd411147f98a8a853a01bc2dd6cc15dd3743d352fd6dc498d2e3a26ac6e579b"},"schema_version":"1.0","source":{"id":"2503.04036","kind":"arxiv","version":3}},"canonical_sha256":"0d3fbd9ca9d409147a393b61b2d3e22c67407569e6a5c1330a8b15015be69693","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d3fbd9ca9d409147a393b61b2d3e22c67407569e6a5c1330a8b15015be69693","first_computed_at":"2026-07-05T11:43:30.966370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:30.966370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n4zZta7QjxLoyDN3RDFaAPpH8UURMkzSVpmBMS90KQvBBeTY5Eblt/O5/S7DEifXaXL5FeLZ2dNcbJkDcFXmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:30.966882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04036","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa5bf37f163868490cd253e847084b8e93d0276d7139d115c4fee6b38ef01a92","sha256:228d8d3e13c2065a108bd2bad0a2a1adf7ead05f81920063b5c485b06fe687f5"],"state_sha256":"afd2116a0ac6c4c1b1fb54c22f65206b24d3e21d85d71e613c1847ae778c1f57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LOBeyRQsOCqEMcEuBWwfP2FE8ZDTKj/iRr0hKyZMpn37Z5oxNYCuT0ls23BW5xf1w1l4c/WcDoOOinQr4Yj2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:14:09.790630Z","bundle_sha256":"5e611a66b0a213aa12ca3fde8eba68c4d3115f39cae1d1ef321720bb06d8eeec"}}