{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EDG2WLORPGSNXCO65TOS4Q6YQB","short_pith_number":"pith:EDG2WLOR","schema_version":"1.0","canonical_sha256":"20cdab2dd179a4db89deecdd2e43d8804bedc49b86a8e6a6c3a1b57ee53d90fd","source":{"kind":"arxiv","id":"2406.08337","version":1},"attestation_state":"computed","paper":{"title":"WMAdapter: Adding WaterMark Control to Latent Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Hai Ci, Jinheng Xie, Mike Zheng Shou, Pei Yang, Yiren Song","submitted_at":"2024-06-12T15:42:52Z","abstract_excerpt":"Watermarking is crucial for protecting the copyright of AI-generated images. We propose WMAdapter, a diffusion model watermark plugin that takes user-specified watermark information and allows for seamless watermark imprinting during the diffusion generation process. WMAdapter is efficient and robust, with a strong emphasis on high generation quality. To achieve this, we make two key designs: (1) We develop a contextual adapter structure that is lightweight and enables effective knowledge transfer from heavily pretrained post-hoc watermarking models. (2) We introduce an extra finetuning step a"},"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":"2406.08337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T15:42:52Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"38dd7ee656528cc305521b9e1a6ac686ae949340a21251333326a991fb76d754","abstract_canon_sha256":"b445ea2972ab39584d8f6a0fcf614aeb25ec1bfb4d5b3194f9926fb0fd0dd1b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:58.206729Z","signature_b64":"GAwx9ghSoyWnTf9Y+VN1BlQLB6N33FiW3jpK/EPMh7TA4YMGwhavNRR81BmvNGa5NXWwc9w/ISHQ9WONJ0u3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20cdab2dd179a4db89deecdd2e43d8804bedc49b86a8e6a6c3a1b57ee53d90fd","last_reissued_at":"2026-07-05T08:30:58.206219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:58.206219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WMAdapter: Adding WaterMark Control to Latent Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Hai Ci, Jinheng Xie, Mike Zheng Shou, Pei Yang, Yiren Song","submitted_at":"2024-06-12T15:42:52Z","abstract_excerpt":"Watermarking is crucial for protecting the copyright of AI-generated images. We propose WMAdapter, a diffusion model watermark plugin that takes user-specified watermark information and allows for seamless watermark imprinting during the diffusion generation process. WMAdapter is efficient and robust, with a strong emphasis on high generation quality. To achieve this, we make two key designs: (1) We develop a contextual adapter structure that is lightweight and enables effective knowledge transfer from heavily pretrained post-hoc watermarking models. (2) We introduce an extra finetuning step a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08337","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/2406.08337/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":"2406.08337","created_at":"2026-07-05T08:30:58.206279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08337v1","created_at":"2026-07-05T08:30:58.206279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08337","created_at":"2026-07-05T08:30:58.206279+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDG2WLORPGSN","created_at":"2026-07-05T08:30:58.206279+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDG2WLORPGSNXCO6","created_at":"2026-07-05T08:30:58.206279+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDG2WLOR","created_at":"2026-07-05T08:30:58.206279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16363","citing_title":"CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB","json":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB.json","graph_json":"https://pith.science/api/pith-number/EDG2WLORPGSNXCO65TOS4Q6YQB/graph.json","events_json":"https://pith.science/api/pith-number/EDG2WLORPGSNXCO65TOS4Q6YQB/events.json","paper":"https://pith.science/paper/EDG2WLOR"},"agent_actions":{"view_html":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB","download_json":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB.json","view_paper":"https://pith.science/paper/EDG2WLOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08337&json=true","fetch_graph":"https://pith.science/api/pith-number/EDG2WLORPGSNXCO65TOS4Q6YQB/graph.json","fetch_events":"https://pith.science/api/pith-number/EDG2WLORPGSNXCO65TOS4Q6YQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB/action/storage_attestation","attest_author":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB/action/author_attestation","sign_citation":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB/action/citation_signature","submit_replication":"https://pith.science/pith/EDG2WLORPGSNXCO65TOS4Q6YQB/action/replication_record"}},"created_at":"2026-07-05T08:30:58.206279+00:00","updated_at":"2026-07-05T08:30:58.206279+00:00"}