{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MOFZIGGGCB456J5VVDJ4QJAVOK","short_pith_number":"pith:MOFZIGGG","schema_version":"1.0","canonical_sha256":"638b9418c61079df27b5a8d3c8241572ace4989f7b5d4a6f3950a3c714c6aa89","source":{"kind":"arxiv","id":"2411.07231","version":2},"attestation_state":"computed","paper":{"title":"Watermark Anything with Localized Messages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Alain Durmus, Matthijs Douze, Pierre Fernandez, Teddy Furon, Tom Sander","submitted_at":"2024-11-11T18:49:58Z","abstract_excerpt":"Image watermarking methods are not tailored to handle small watermarked areas. This restricts applications in real-world scenarios where parts of the image may come from different sources or have been edited. We introduce a deep-learning model for localized image watermarking, dubbed the Watermark Anything Model (WAM). The WAM embedder imperceptibly modifies the input image, while the extractor segments the received image into watermarked and non-watermarked areas and recovers one or several hidden messages from the areas found to be watermarked. The models are jointly trained at low resolutio"},"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":"2411.07231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T18:49:58Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"35cd1715e0fa6f1d4a56fd7edf2c0b1db8ac911226c3369b7e89bafd3e34327f","abstract_canon_sha256":"a55730b4e38d1f41fad6fee69d34fe4d8233d6547e582312a64a51af71f605e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:19.683758Z","signature_b64":"MvP11u6/Q0v0ZZqu9XLe85r21ojFsGkBY3LokXVll0LnxprYIulL8o7vShjDI2vNxC0R4wY8yx3cd3sraA2SDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"638b9418c61079df27b5a8d3c8241572ace4989f7b5d4a6f3950a3c714c6aa89","last_reissued_at":"2026-07-05T11:41:19.683236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:19.683236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watermark Anything with Localized Messages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Alain Durmus, Matthijs Douze, Pierre Fernandez, Teddy Furon, Tom Sander","submitted_at":"2024-11-11T18:49:58Z","abstract_excerpt":"Image watermarking methods are not tailored to handle small watermarked areas. This restricts applications in real-world scenarios where parts of the image may come from different sources or have been edited. We introduce a deep-learning model for localized image watermarking, dubbed the Watermark Anything Model (WAM). The WAM embedder imperceptibly modifies the input image, while the extractor segments the received image into watermarked and non-watermarked areas and recovers one or several hidden messages from the areas found to be watermarked. The models are jointly trained at low resolutio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07231","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/2411.07231/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":"2411.07231","created_at":"2026-07-05T11:41:19.683301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07231v2","created_at":"2026-07-05T11:41:19.683301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07231","created_at":"2026-07-05T11:41:19.683301+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOFZIGGGCB45","created_at":"2026-07-05T11:41:19.683301+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOFZIGGGCB456J5V","created_at":"2026-07-05T11:41:19.683301+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOFZIGGG","created_at":"2026-07-05T11:41:19.683301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.12172","citing_title":"SEAL: Semantic Aware Image Watermarking","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK","json":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK.json","graph_json":"https://pith.science/api/pith-number/MOFZIGGGCB456J5VVDJ4QJAVOK/graph.json","events_json":"https://pith.science/api/pith-number/MOFZIGGGCB456J5VVDJ4QJAVOK/events.json","paper":"https://pith.science/paper/MOFZIGGG"},"agent_actions":{"view_html":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK","download_json":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK.json","view_paper":"https://pith.science/paper/MOFZIGGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07231&json=true","fetch_graph":"https://pith.science/api/pith-number/MOFZIGGGCB456J5VVDJ4QJAVOK/graph.json","fetch_events":"https://pith.science/api/pith-number/MOFZIGGGCB456J5VVDJ4QJAVOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK/action/storage_attestation","attest_author":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK/action/author_attestation","sign_citation":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK/action/citation_signature","submit_replication":"https://pith.science/pith/MOFZIGGGCB456J5VVDJ4QJAVOK/action/replication_record"}},"created_at":"2026-07-05T11:41:19.683301+00:00","updated_at":"2026-07-05T11:41:19.683301+00:00"}