{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WJMDRGEZLS6YM7EBPETPUB7N43","short_pith_number":"pith:WJMDRGEZ","schema_version":"1.0","canonical_sha256":"b2583898995cbd867c817926fa07ede6c636cec4615575d49bacf6ff3b98450e","source":{"kind":"arxiv","id":"2607.10554","version":1},"attestation_state":"computed","paper":{"title":"Observation-Level Watermarking and Detection for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Dongyu Cui, Xuan Bi","submitted_at":"2026-07-12T04:03:55Z","abstract_excerpt":"With the development of generative AI, watermarking techniques have been widely used to detect the authenticity of AI-generated data and protect the rights of users and creators. While it is already well applied in data types including imaging and text data, watermarking tabular data is still under-explored. Existing methods primarily focus on numerical data, leaving discrete, categorical, and mixed data less studied. In this work, we propose STAMP (Single-observation Tabular Attribution and Marking Procedure), a novel framework for watermarking tabular data that can accommodate and preserve a"},"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":"2607.10554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-12T04:03:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1737c9a043b9f1ba967ee738f05216edd9690f5bf0d126df7fb2dfe59cc00807","abstract_canon_sha256":"f9736536484f3a1e788f4e1dcfdc60c5cf029653a85d4c32ddcb948e742ceff7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:21.119050Z","signature_b64":"OEV4UXMJvsH4BnvU3QtsBWyQh9fIAQaWxGqiUarF4Gk8JZ4z5uE7mdSEqYPuCmIzrDxjlOW4P+3RcTb+vry6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2583898995cbd867c817926fa07ede6c636cec4615575d49bacf6ff3b98450e","last_reissued_at":"2026-07-14T01:21:21.118237Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:21.118237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Observation-Level Watermarking and Detection for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Dongyu Cui, Xuan Bi","submitted_at":"2026-07-12T04:03:55Z","abstract_excerpt":"With the development of generative AI, watermarking techniques have been widely used to detect the authenticity of AI-generated data and protect the rights of users and creators. While it is already well applied in data types including imaging and text data, watermarking tabular data is still under-explored. Existing methods primarily focus on numerical data, leaving discrete, categorical, and mixed data less studied. In this work, we propose STAMP (Single-observation Tabular Attribution and Marking Procedure), a novel framework for watermarking tabular data that can accommodate and preserve a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10554","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/2607.10554/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":"2607.10554","created_at":"2026-07-14T01:21:21.118663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10554v1","created_at":"2026-07-14T01:21:21.118663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10554","created_at":"2026-07-14T01:21:21.118663+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJMDRGEZLS6Y","created_at":"2026-07-14T01:21:21.118663+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJMDRGEZLS6YM7EB","created_at":"2026-07-14T01:21:21.118663+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJMDRGEZ","created_at":"2026-07-14T01:21:21.118663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43","json":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43.json","graph_json":"https://pith.science/api/pith-number/WJMDRGEZLS6YM7EBPETPUB7N43/graph.json","events_json":"https://pith.science/api/pith-number/WJMDRGEZLS6YM7EBPETPUB7N43/events.json","paper":"https://pith.science/paper/WJMDRGEZ"},"agent_actions":{"view_html":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43","download_json":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43.json","view_paper":"https://pith.science/paper/WJMDRGEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10554&json=true","fetch_graph":"https://pith.science/api/pith-number/WJMDRGEZLS6YM7EBPETPUB7N43/graph.json","fetch_events":"https://pith.science/api/pith-number/WJMDRGEZLS6YM7EBPETPUB7N43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43/action/storage_attestation","attest_author":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43/action/author_attestation","sign_citation":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43/action/citation_signature","submit_replication":"https://pith.science/pith/WJMDRGEZLS6YM7EBPETPUB7N43/action/replication_record"}},"created_at":"2026-07-14T01:21:21.118663+00:00","updated_at":"2026-07-14T01:21:21.118663+00:00"}