{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:537RW2AJPFMO4E3BFXNGU6IQTI","short_pith_number":"pith:537RW2AJ","schema_version":"1.0","canonical_sha256":"eeff1b68097958ee13612dda6a79109a2b792ba760c8766249ca0e1b4303394c","source":{"kind":"arxiv","id":"2406.13012","version":1},"attestation_state":"computed","paper":{"title":"Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi-Hua Wang, Guang Cheng, Joshua Ward","submitted_at":"2024-06-18T19:05:24Z","abstract_excerpt":"The promise of tabular generative models is to produce realistic synthetic data that can be shared and safely used without dangerous leakage of information from the training set. In evaluating these models, a variety of methods have been proposed to measure the tendency to copy data from the training dataset when generating a sample. However, these methods suffer from either not considering data-copying from a privacy threat perspective, not being motivated by recent results in the data-copying literature or being difficult to make compatible with the high dimensional, mixed type nature of tab"},"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":"2406.13012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T19:05:24Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"5f75337a92fa586f9110c585339d4b376dcf60855ce71d7b04edacfb9ecfa0a2","abstract_canon_sha256":"74a698c6a9d4f3d7718c72cec0dfe9e967ec911946b31aa07ade0f033b1e2f7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:23.854621Z","signature_b64":"vb2SXOQFrIolNMSYqBHsUFgZqwcrr1EiFAGHMHyFyYsXvob1Exencm2AW0HsXt6Q5RcMQXYZPIO0EeNAdTYhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeff1b68097958ee13612dda6a79109a2b792ba760c8766249ca0e1b4303394c","last_reissued_at":"2026-07-05T08:34:23.854274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:23.854274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi-Hua Wang, Guang Cheng, Joshua Ward","submitted_at":"2024-06-18T19:05:24Z","abstract_excerpt":"The promise of tabular generative models is to produce realistic synthetic data that can be shared and safely used without dangerous leakage of information from the training set. In evaluating these models, a variety of methods have been proposed to measure the tendency to copy data from the training dataset when generating a sample. However, these methods suffer from either not considering data-copying from a privacy threat perspective, not being motivated by recent results in the data-copying literature or being difficult to make compatible with the high dimensional, mixed type nature of tab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13012","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/2406.13012/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":"2406.13012","created_at":"2026-07-05T08:34:23.854336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13012v1","created_at":"2026-07-05T08:34:23.854336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13012","created_at":"2026-07-05T08:34:23.854336+00:00"},{"alias_kind":"pith_short_12","alias_value":"537RW2AJPFMO","created_at":"2026-07-05T08:34:23.854336+00:00"},{"alias_kind":"pith_short_16","alias_value":"537RW2AJPFMO4E3B","created_at":"2026-07-05T08:34:23.854336+00:00"},{"alias_kind":"pith_short_8","alias_value":"537RW2AJ","created_at":"2026-07-05T08:34:23.854336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06334","citing_title":"Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2508.21146","citing_title":"Privacy Auditing Synthetic Data Release through Local Likelihood Attacks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08875","citing_title":"When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI","json":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI.json","graph_json":"https://pith.science/api/pith-number/537RW2AJPFMO4E3BFXNGU6IQTI/graph.json","events_json":"https://pith.science/api/pith-number/537RW2AJPFMO4E3BFXNGU6IQTI/events.json","paper":"https://pith.science/paper/537RW2AJ"},"agent_actions":{"view_html":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI","download_json":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI.json","view_paper":"https://pith.science/paper/537RW2AJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13012&json=true","fetch_graph":"https://pith.science/api/pith-number/537RW2AJPFMO4E3BFXNGU6IQTI/graph.json","fetch_events":"https://pith.science/api/pith-number/537RW2AJPFMO4E3BFXNGU6IQTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/action/storage_attestation","attest_author":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/action/author_attestation","sign_citation":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/action/citation_signature","submit_replication":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/action/replication_record"}},"created_at":"2026-07-05T08:34:23.854336+00:00","updated_at":"2026-07-05T08:34:23.854336+00:00"}