{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MSBQ75IB3OD5K46NXCXUM5X5HN","short_pith_number":"pith:MSBQ75IB","schema_version":"1.0","canonical_sha256":"64830ff501db87d573cdb8af4676fd3b56dc4f91a373666b402ffcf41ba9f3bc","source":{"kind":"arxiv","id":"2503.11945","version":1},"attestation_state":"computed","paper":{"title":"Your Text Encoder Can Be An Object-Level Watermarking Controller","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mingzhen Huang, Naresh Kumar Devulapally, Shruti Agarwal, Siwei Lyu, Vishal Asnani, Vishnu Suresh Lokhande","submitted_at":"2025-03-15T01:35:39Z","abstract_excerpt":"Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models (LDMs). By only fine-tuning text token embeddings $W_*$, we enable watermarking in selected objects or parts of the image, offering greater flexibility compared to traditional full-image watermarking. Our method leverages the text encoder's compatibility across various LDMs, allowing plug-and-play integration for different LDMs. Moreover, introducing the waterma"},"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":"2503.11945","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-15T01:35:39Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"2ffe123a6efb14a983766f8c0b97365187ed2008d05afdea25773fdf2528e64b","abstract_canon_sha256":"89411fee7bb2ca1edf6ebe118cab9ba627b972c188f8ef2330d5c84b9c02e759"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:42.597378Z","signature_b64":"daUgc7XASTqZqfdEWPwLNvR1s6KdIROCVZH9B4YuFfVeJAlVYZbkPOTrhDBGSSiOiaf/fqUdpjx8Mn4l3WmNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64830ff501db87d573cdb8af4676fd3b56dc4f91a373666b402ffcf41ba9f3bc","last_reissued_at":"2026-07-05T10:32:42.596878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:42.596878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Your Text Encoder Can Be An Object-Level Watermarking Controller","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mingzhen Huang, Naresh Kumar Devulapally, Shruti Agarwal, Siwei Lyu, Vishal Asnani, Vishnu Suresh Lokhande","submitted_at":"2025-03-15T01:35:39Z","abstract_excerpt":"Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models (LDMs). By only fine-tuning text token embeddings $W_*$, we enable watermarking in selected objects or parts of the image, offering greater flexibility compared to traditional full-image watermarking. Our method leverages the text encoder's compatibility across various LDMs, allowing plug-and-play integration for different LDMs. Moreover, introducing the waterma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11945","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/2503.11945/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":"2503.11945","created_at":"2026-07-05T10:32:42.596937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11945v1","created_at":"2026-07-05T10:32:42.596937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11945","created_at":"2026-07-05T10:32:42.596937+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSBQ75IB3OD5","created_at":"2026-07-05T10:32:42.596937+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSBQ75IB3OD5K46N","created_at":"2026-07-05T10:32:42.596937+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSBQ75IB","created_at":"2026-07-05T10:32:42.596937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00377","citing_title":"Score-Control for Hallucination Reduction in Diffusion Models","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN","json":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN.json","graph_json":"https://pith.science/api/pith-number/MSBQ75IB3OD5K46NXCXUM5X5HN/graph.json","events_json":"https://pith.science/api/pith-number/MSBQ75IB3OD5K46NXCXUM5X5HN/events.json","paper":"https://pith.science/paper/MSBQ75IB"},"agent_actions":{"view_html":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN","download_json":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN.json","view_paper":"https://pith.science/paper/MSBQ75IB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11945&json=true","fetch_graph":"https://pith.science/api/pith-number/MSBQ75IB3OD5K46NXCXUM5X5HN/graph.json","fetch_events":"https://pith.science/api/pith-number/MSBQ75IB3OD5K46NXCXUM5X5HN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN/action/storage_attestation","attest_author":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN/action/author_attestation","sign_citation":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN/action/citation_signature","submit_replication":"https://pith.science/pith/MSBQ75IB3OD5K46NXCXUM5X5HN/action/replication_record"}},"created_at":"2026-07-05T10:32:42.596937+00:00","updated_at":"2026-07-05T10:32:42.596937+00:00"}