{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6EEJ7DARGDAPWMBKWXKBDMGFTN","short_pith_number":"pith:6EEJ7DAR","schema_version":"1.0","canonical_sha256":"f1089f8c1130c0fb302ab5d411b0c59b72be8e39f461d969d1e46b71f02e3fac","source":{"kind":"arxiv","id":"2505.14673","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Watermarking for Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CV","authors_text":"Kaiyang Zhou, Shuai Yang, Yu Tong, Zihao Pan","submitted_at":"2025-05-20T17:58:02Z","abstract_excerpt":"Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored. We propose IndexMark, a training-free watermarking framework for autoregressive image generation models. IndexMark is inspired by the redundancy property of the codebook: replacing autoregressively generated indices with similar indices produces negligible visual differences. The core component in In"},"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":"2505.14673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:58:02Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"cc91199842da22eac8cae0510d6f5273c9f20e07b4418d69ee534466834b42f7","abstract_canon_sha256":"97dd9d2283496726425ae0d875adae71f9660875029a75f900fb2e4b92b6e4d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:17.395870Z","signature_b64":"uoIn+VYkuJiKwNBkdbS866zl2dHkgSnulYOiW1U3FyY/v+UokWoOVN4jLqOaTWjBvQoKwhLNfHD/IefIyezYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1089f8c1130c0fb302ab5d411b0c59b72be8e39f461d969d1e46b71f02e3fac","last_reissued_at":"2026-07-05T11:06:17.395332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:17.395332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Watermarking for Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CV","authors_text":"Kaiyang Zhou, Shuai Yang, Yu Tong, Zihao Pan","submitted_at":"2025-05-20T17:58:02Z","abstract_excerpt":"Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored. We propose IndexMark, a training-free watermarking framework for autoregressive image generation models. IndexMark is inspired by the redundancy property of the codebook: replacing autoregressively generated indices with similar indices produces negligible visual differences. The core component in In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14673","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/2505.14673/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":"2505.14673","created_at":"2026-07-05T11:06:17.395392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14673v1","created_at":"2026-07-05T11:06:17.395392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14673","created_at":"2026-07-05T11:06:17.395392+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EEJ7DARGDAP","created_at":"2026-07-05T11:06:17.395392+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EEJ7DARGDAPWMBK","created_at":"2026-07-05T11:06:17.395392+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EEJ7DAR","created_at":"2026-07-05T11:06:17.395392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28386","citing_title":"Data Provenance for Image Auto-Regressive Generation","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25967","citing_title":"Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11720","citing_title":"On the Robustness of Watermarking for Autoregressive Image Generation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN","json":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN.json","graph_json":"https://pith.science/api/pith-number/6EEJ7DARGDAPWMBKWXKBDMGFTN/graph.json","events_json":"https://pith.science/api/pith-number/6EEJ7DARGDAPWMBKWXKBDMGFTN/events.json","paper":"https://pith.science/paper/6EEJ7DAR"},"agent_actions":{"view_html":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN","download_json":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN.json","view_paper":"https://pith.science/paper/6EEJ7DAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14673&json=true","fetch_graph":"https://pith.science/api/pith-number/6EEJ7DARGDAPWMBKWXKBDMGFTN/graph.json","fetch_events":"https://pith.science/api/pith-number/6EEJ7DARGDAPWMBKWXKBDMGFTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN/action/storage_attestation","attest_author":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN/action/author_attestation","sign_citation":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN/action/citation_signature","submit_replication":"https://pith.science/pith/6EEJ7DARGDAPWMBKWXKBDMGFTN/action/replication_record"}},"created_at":"2026-07-05T11:06:17.395392+00:00","updated_at":"2026-07-05T11:06:17.395392+00:00"}