{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6DWLHGENBXMMXHPBKEQ3QIKWAY","short_pith_number":"pith:6DWLHGEN","schema_version":"1.0","canonical_sha256":"f0ecb3988d0dd8cb9de15121b821560637fb1a6fdb2bdce4cbe7bc6a2649780d","source":{"kind":"arxiv","id":"2503.12172","version":4},"attestation_state":"computed","paper":{"title":"SEAL: Semantic Aware Image Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chinmay Hegde, Kasra Arabi, Niv Cohen, R. Teal Witter","submitted_at":"2025-03-15T15:29:05Z","abstract_excerpt":"Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques. Watermarks are typically expected to preserve the integrity of the target image, withstand removal attempts, and prevent unauthorized replication onto unrelated images. To address this need, recent methods embed persistent watermarks into images produced by diffusion models using the initial noise. Yet, to do so, they either distort the distribution of generated"},"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":"2503.12172","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T15:29:05Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"3a7cb2f409d0f964d2fd48488a692ae48c0a81952b287c7da620357315be9a67","abstract_canon_sha256":"e1cd0e968737adb49b2b9f47e621838631327ce96e26bd838836480b8c580f8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:52.879171Z","signature_b64":"WXefdmD6CjX2TCn1FEH4LAtyo67G3aoQnp9j35DPwf5gROjV64yKl+fvbOMRy0mXWIQIwvQqSqeOc1Djix9ZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ecb3988d0dd8cb9de15121b821560637fb1a6fdb2bdce4cbe7bc6a2649780d","last_reissued_at":"2026-05-20T01:04:52.878254Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:52.878254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEAL: Semantic Aware Image Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chinmay Hegde, Kasra Arabi, Niv Cohen, R. Teal Witter","submitted_at":"2025-03-15T15:29:05Z","abstract_excerpt":"Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques. Watermarks are typically expected to preserve the integrity of the target image, withstand removal attempts, and prevent unauthorized replication onto unrelated images. To address this need, recent methods embed persistent watermarks into images produced by diffusion models using the initial noise. Yet, to do so, they either distort the distribution of generated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12172","kind":"arxiv","version":4},"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/2503.12172/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":"2503.12172","created_at":"2026-05-20T01:04:52.878406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12172v4","created_at":"2026-05-20T01:04:52.878406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12172","created_at":"2026-05-20T01:04:52.878406+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DWLHGENBXMM","created_at":"2026-05-20T01:04:52.878406+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DWLHGENBXMMXHPB","created_at":"2026-05-20T01:04:52.878406+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DWLHGEN","created_at":"2026-05-20T01:04:52.878406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.09203","citing_title":"Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09319","citing_title":"PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19090","citing_title":"Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY","json":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY.json","graph_json":"https://pith.science/api/pith-number/6DWLHGENBXMMXHPBKEQ3QIKWAY/graph.json","events_json":"https://pith.science/api/pith-number/6DWLHGENBXMMXHPBKEQ3QIKWAY/events.json","paper":"https://pith.science/paper/6DWLHGEN"},"agent_actions":{"view_html":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY","download_json":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY.json","view_paper":"https://pith.science/paper/6DWLHGEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12172&json=true","fetch_graph":"https://pith.science/api/pith-number/6DWLHGENBXMMXHPBKEQ3QIKWAY/graph.json","fetch_events":"https://pith.science/api/pith-number/6DWLHGENBXMMXHPBKEQ3QIKWAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY/action/storage_attestation","attest_author":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY/action/author_attestation","sign_citation":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY/action/citation_signature","submit_replication":"https://pith.science/pith/6DWLHGENBXMMXHPBKEQ3QIKWAY/action/replication_record"}},"created_at":"2026-05-20T01:04:52.878406+00:00","updated_at":"2026-05-20T01:04:52.878406+00:00"}