{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:56SPFVZ2T5QVBKAX772A3J2MZ7","short_pith_number":"pith:56SPFVZ2","schema_version":"1.0","canonical_sha256":"efa4f2d73a9f6150a817fff40da74ccff8bb2e10b981ad50548f682def5c64b6","source":{"kind":"arxiv","id":"2505.24267","version":1},"attestation_state":"computed","paper":{"title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Aiwei Liu, Hengrui Zhang, Henry Peng Zou, Liancheng Fang, Philip S. Yu, Yankai Chen, Zhongfen Deng","submitted_at":"2025-05-30T06:45:31Z","abstract_excerpt":"We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer invertibility compared to other modalities, compromising performance. Simultaneously, tabular diffusion models require substantially less computation than other modalities, enabling a multi-sample selection approach to tabular generative model watermarking. MUSE embeds watermarks by generating multiple candidate samples and selecting one based on a specialized scoring"},"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":"2505.24267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-30T06:45:31Z","cross_cats_sorted":[],"title_canon_sha256":"c752cf8582c7a5c088ebe7e3249f7b0316731dacdf1d0ec9fa18310b59147bb5","abstract_canon_sha256":"938ebfe77a1f2bde5592e8adccc811f99937ce55115e020a12bf0fc34ff49ab3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:45.515947Z","signature_b64":"FLHuR6JA1gne6D9xrqBGrgOMEz1xnWXViJPKjYuaN4B0VtOAlGTWIMkxCYHddvBV3HYmN4CdxvKbtEAwXiRdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efa4f2d73a9f6150a817fff40da74ccff8bb2e10b981ad50548f682def5c64b6","last_reissued_at":"2026-07-05T11:12:45.515404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:45.515404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Aiwei Liu, Hengrui Zhang, Henry Peng Zou, Liancheng Fang, Philip S. Yu, Yankai Chen, Zhongfen Deng","submitted_at":"2025-05-30T06:45:31Z","abstract_excerpt":"We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer invertibility compared to other modalities, compromising performance. Simultaneously, tabular diffusion models require substantially less computation than other modalities, enabling a multi-sample selection approach to tabular generative model watermarking. MUSE embeds watermarks by generating multiple candidate samples and selecting one based on a specialized scoring"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24267","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/2505.24267/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":"2505.24267","created_at":"2026-07-05T11:12:45.515466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24267v1","created_at":"2026-07-05T11:12:45.515466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24267","created_at":"2026-07-05T11:12:45.515466+00:00"},{"alias_kind":"pith_short_12","alias_value":"56SPFVZ2T5QV","created_at":"2026-07-05T11:12:45.515466+00:00"},{"alias_kind":"pith_short_16","alias_value":"56SPFVZ2T5QVBKAX","created_at":"2026-07-05T11:12:45.515466+00:00"},{"alias_kind":"pith_short_8","alias_value":"56SPFVZ2","created_at":"2026-07-05T11:12:45.515466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.21600","citing_title":"Robust Spectral Watermark for Synthetic Tabular Data","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7","json":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7.json","graph_json":"https://pith.science/api/pith-number/56SPFVZ2T5QVBKAX772A3J2MZ7/graph.json","events_json":"https://pith.science/api/pith-number/56SPFVZ2T5QVBKAX772A3J2MZ7/events.json","paper":"https://pith.science/paper/56SPFVZ2"},"agent_actions":{"view_html":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7","download_json":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7.json","view_paper":"https://pith.science/paper/56SPFVZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24267&json=true","fetch_graph":"https://pith.science/api/pith-number/56SPFVZ2T5QVBKAX772A3J2MZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/56SPFVZ2T5QVBKAX772A3J2MZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7/action/storage_attestation","attest_author":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7/action/author_attestation","sign_citation":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7/action/citation_signature","submit_replication":"https://pith.science/pith/56SPFVZ2T5QVBKAX772A3J2MZ7/action/replication_record"}},"created_at":"2026-07-05T11:12:45.515466+00:00","updated_at":"2026-07-05T11:12:45.515466+00:00"}