{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:537RW2AJPFMO4E3BFXNGU6IQTI","short_pith_number":"pith:537RW2AJ","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"},"canonical_sha256":"eeff1b68097958ee13612dda6a79109a2b792ba760c8766249ca0e1b4303394c","source":{"kind":"arxiv","id":"2406.13012","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13012","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13012v1","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13012","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"pith_short_12","alias_value":"537RW2AJPFMO","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"pith_short_16","alias_value":"537RW2AJPFMO4E3B","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"pith_short_8","alias_value":"537RW2AJ","created_at":"2026-07-05T08:34:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:537RW2AJPFMO4E3BFXNGU6IQTI","target":"record","payload":{"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"},"canonical_sha256":"eeff1b68097958ee13612dda6a79109a2b792ba760c8766249ca0e1b4303394c","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"},"source_kind":"arxiv","source_id":"2406.13012","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WvzGCjtn+dzuOEHtbCF1PAwhsv7R2zW+GvpYdlez6/eFu9kWgouUjSSgn3HTQiIw8ZcUl5wrzuVZPNOT3KrWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:45:46.198143Z"},"content_sha256":"f7dee2616e283ad3ab152177b6af01fb3b8c6737279a4681c172137d09085262","schema_version":"1.0","event_id":"sha256:f7dee2616e283ad3ab152177b6af01fb3b8c6737279a4681c172137d09085262"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:537RW2AJPFMO4E3BFXNGU6IQTI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8ImR7Ws+H+XWjHbA7u2K+vuKJjjKouWXeaiviP+Oukjz7q9yAm3/ZhHkZ2PfTZYBlvqvGMYNHKc+74JOyamDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:45:46.198667Z"},"content_sha256":"d71bfacb29ed89d8cd38b76bd611ba4d4e6a11bde6a0b27fd6e5094980943c3e","schema_version":"1.0","event_id":"sha256:d71bfacb29ed89d8cd38b76bd611ba4d4e6a11bde6a0b27fd6e5094980943c3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/bundle.json","state_url":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/537RW2AJPFMO4E3BFXNGU6IQTI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T04:45:46Z","links":{"resolver":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI","bundle":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/bundle.json","state":"https://pith.science/pith/537RW2AJPFMO4E3BFXNGU6IQTI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/537RW2AJPFMO4E3BFXNGU6IQTI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:537RW2AJPFMO4E3BFXNGU6IQTI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"74a698c6a9d4f3d7718c72cec0dfe9e967ec911946b31aa07ade0f033b1e2f7e","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T19:05:24Z","title_canon_sha256":"5f75337a92fa586f9110c585339d4b376dcf60855ce71d7b04edacfb9ecfa0a2"},"schema_version":"1.0","source":{"id":"2406.13012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13012","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13012v1","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13012","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"pith_short_12","alias_value":"537RW2AJPFMO","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"pith_short_16","alias_value":"537RW2AJPFMO4E3B","created_at":"2026-07-05T08:34:23Z"},{"alias_kind":"pith_short_8","alias_value":"537RW2AJ","created_at":"2026-07-05T08:34:23Z"}],"graph_snapshots":[{"event_id":"sha256:d71bfacb29ed89d8cd38b76bd611ba4d4e6a11bde6a0b27fd6e5094980943c3e","target":"graph","created_at":"2026-07-05T08:34:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.13012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chi-Hua Wang, Guang Cheng, Joshua Ward","cross_cats":["cs.CR","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T19:05:24Z","title":"Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13012","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f7dee2616e283ad3ab152177b6af01fb3b8c6737279a4681c172137d09085262","target":"record","created_at":"2026-07-05T08:34:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"74a698c6a9d4f3d7718c72cec0dfe9e967ec911946b31aa07ade0f033b1e2f7e","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T19:05:24Z","title_canon_sha256":"5f75337a92fa586f9110c585339d4b376dcf60855ce71d7b04edacfb9ecfa0a2"},"schema_version":"1.0","source":{"id":"2406.13012","kind":"arxiv","version":1}},"canonical_sha256":"eeff1b68097958ee13612dda6a79109a2b792ba760c8766249ca0e1b4303394c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eeff1b68097958ee13612dda6a79109a2b792ba760c8766249ca0e1b4303394c","first_computed_at":"2026-07-05T08:34:23.854274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:23.854274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vb2SXOQFrIolNMSYqBHsUFgZqwcrr1EiFAGHMHyFyYsXvob1Exencm2AW0HsXt6Q5RcMQXYZPIO0EeNAdTYhCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:23.854621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7dee2616e283ad3ab152177b6af01fb3b8c6737279a4681c172137d09085262","sha256:d71bfacb29ed89d8cd38b76bd611ba4d4e6a11bde6a0b27fd6e5094980943c3e"],"state_sha256":"b7bb391fe310575399c8dcbccce2867d027a445d4bd971c6e25495cc13803b26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m07nBEymxEyDv3mT/XjTCgL7IR8A9Y3XP2HmrKCWUoPS6sfZH/7sIx3yF/KPUgqRd5i3xeLs5l7/oEGWp3CEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:45:46.203308Z","bundle_sha256":"1430636526272ebba4668b589614b985f55868825d2832f7e0cb81e3f0686d31"}}