{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JSOSMQV7QLP6HJG54VCPRJ2CCC","short_pith_number":"pith:JSOSMQV7","schema_version":"1.0","canonical_sha256":"4c9d2642bf82dfe3a4dde544f8a742108d592f3823d8fbd969cbbde52196bf2b","source":{"kind":"arxiv","id":"2506.11371","version":1},"attestation_state":"computed","paper":{"title":"A Watermark for Auto-Regressive Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Georgios Milis, Heng Huang, Ruibo Chen, Xuehao Cui, Yihan Wu","submitted_at":"2025-06-13T00:15:54Z","abstract_excerpt":"The rapid evolution of image generation models has revolutionized visual content creation, enabling the synthesis of highly realistic and contextually accurate images for diverse applications. However, the potential for misuse, such as deepfake generation, image based phishing attacks, and fabrication of misleading visual evidence, underscores the need for robust authenticity verification mechanisms. While traditional statistical watermarking techniques have proven effective for autoregressive language models, their direct adaptation to image generation models encounters significant challenges"},"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":"2506.11371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T00:15:54Z","cross_cats_sorted":[],"title_canon_sha256":"a7f2fd7e5510d540ec06e0c2b569ec586291839d5ff5d28c1af288f279ec454a","abstract_canon_sha256":"674320712aa74f8b33d90e11fa1cfc526eddac9d35f92b83fceb3015bef212b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:03.223293Z","signature_b64":"A/O6qLWXEANjsURef5HsAy3SFUMNtRiAxiLeUOz874JIJPvOmDx1KwMvJbpCQNyvtD1BVNsYMm1DuQNu4KDgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c9d2642bf82dfe3a4dde544f8a742108d592f3823d8fbd969cbbde52196bf2b","last_reissued_at":"2026-07-05T11:21:03.222932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:03.222932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Watermark for Auto-Regressive Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Georgios Milis, Heng Huang, Ruibo Chen, Xuehao Cui, Yihan Wu","submitted_at":"2025-06-13T00:15:54Z","abstract_excerpt":"The rapid evolution of image generation models has revolutionized visual content creation, enabling the synthesis of highly realistic and contextually accurate images for diverse applications. However, the potential for misuse, such as deepfake generation, image based phishing attacks, and fabrication of misleading visual evidence, underscores the need for robust authenticity verification mechanisms. While traditional statistical watermarking techniques have proven effective for autoregressive language models, their direct adaptation to image generation models encounters significant challenges"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11371","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/2506.11371/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":"2506.11371","created_at":"2026-07-05T11:21:03.222990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11371v1","created_at":"2026-07-05T11:21:03.222990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11371","created_at":"2026-07-05T11:21:03.222990+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSOSMQV7QLP6","created_at":"2026-07-05T11:21:03.222990+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSOSMQV7QLP6HJG5","created_at":"2026-07-05T11:21:03.222990+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSOSMQV7","created_at":"2026-07-05T11:21:03.222990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11720","citing_title":"On the Robustness of Watermarking for Autoregressive Image Generation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC","json":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC.json","graph_json":"https://pith.science/api/pith-number/JSOSMQV7QLP6HJG54VCPRJ2CCC/graph.json","events_json":"https://pith.science/api/pith-number/JSOSMQV7QLP6HJG54VCPRJ2CCC/events.json","paper":"https://pith.science/paper/JSOSMQV7"},"agent_actions":{"view_html":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC","download_json":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC.json","view_paper":"https://pith.science/paper/JSOSMQV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11371&json=true","fetch_graph":"https://pith.science/api/pith-number/JSOSMQV7QLP6HJG54VCPRJ2CCC/graph.json","fetch_events":"https://pith.science/api/pith-number/JSOSMQV7QLP6HJG54VCPRJ2CCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC/action/storage_attestation","attest_author":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC/action/author_attestation","sign_citation":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC/action/citation_signature","submit_replication":"https://pith.science/pith/JSOSMQV7QLP6HJG54VCPRJ2CCC/action/replication_record"}},"created_at":"2026-07-05T11:21:03.222990+00:00","updated_at":"2026-07-05T11:21:03.222990+00:00"}