{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RL64GNQIXGRQ255UVR5M7N6XRA","short_pith_number":"pith:RL64GNQI","canonical_record":{"source":{"id":"2505.22322","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T13:06:00Z","cross_cats_sorted":[],"title_canon_sha256":"6fb39a569f35bdf88b5dac5f65e7da57f06af0f0799f1d14c114e0f9ea210f04","abstract_canon_sha256":"143ad4bde7b8859ffae61f6983c2209f614a740e39d87bd1c37514c05515f95f"},"schema_version":"1.0"},"canonical_sha256":"8afdc33608b9a30d77b4ac7acfb7d7883ce9d01ad3d0290131f3f699ac1f355a","source":{"kind":"arxiv","id":"2505.22322","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22322","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22322v3","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22322","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"RL64GNQIXGRQ","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"RL64GNQIXGRQ255U","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"RL64GNQI","created_at":"2026-05-26T02:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RL64GNQIXGRQ255UVR5M7N6XRA","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22322","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T13:06:00Z","cross_cats_sorted":[],"title_canon_sha256":"6fb39a569f35bdf88b5dac5f65e7da57f06af0f0799f1d14c114e0f9ea210f04","abstract_canon_sha256":"143ad4bde7b8859ffae61f6983c2209f614a740e39d87bd1c37514c05515f95f"},"schema_version":"1.0"},"canonical_sha256":"8afdc33608b9a30d77b4ac7acfb7d7883ce9d01ad3d0290131f3f699ac1f355a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:00.454802Z","signature_b64":"gfamm5ewEUsM6/qS8oCKp8p30x0LSfkWU5rWbEDdfZFH23goqlok89HiDHLA9OYJAkapq+8s++d8gz6Tw3PrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8afdc33608b9a30d77b4ac7acfb7d7883ce9d01ad3d0290131f3f699ac1f355a","last_reissued_at":"2026-05-26T02:05:00.453924Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:00.453924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22322","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"omMcIBlTjlyl7S0A+HF7BmdtJABfOL4qCQQYgadKLE6EllBjMycpRcZRI4ThjL4DyGS4xRroLYhtYOjmo/RSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:50:48.009066Z"},"content_sha256":"12dac595dac0d0b46a6100fb835efd44a369401756f70870230b37a1202c778b","schema_version":"1.0","event_id":"sha256:12dac595dac0d0b46a6100fb835efd44a369401756f70870230b37a1202c778b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RL64GNQIXGRQ255UVR5M7N6XRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huiyuan Chen, Jing Li, Kaiyu Tang, Xiaoge Zhang, Xiao Li, Zhengyu Fang, Zhimeng Jiang","submitted_at":"2025-05-28T13:06:00Z","abstract_excerpt":"Diffusion models have shown strong performance in generating high-quality tabular data, but they carry privacy risks by reproducing exact training samples. While prior work focuses on dataset-level augmentation to reduce memorization, little is known about which individual samples contribute most. We present the first data-centric study of memorization dynamics in tabular diffusion models. We quantify memorization for each real sample based on how many generated samples are flagged as replicas, using a relative distance ratio. Our empirical analysis reveals a heavy-tailed distribution of memor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22322","kind":"arxiv","version":3},"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/2505.22322/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":"2026-05-26T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cmm+xIaLQqnAEmQBR/hp/AgtLhTjPZ1lSPByFgP9HwSTiUWc83l7FIwCN4sglfpBATdQ/IV62o3MJ3NgfxdXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:50:48.009773Z"},"content_sha256":"19f30b79f57e6d9ed945fb1d92d152742f36fb41e4e49b528239bbb6e5288336","schema_version":"1.0","event_id":"sha256:19f30b79f57e6d9ed945fb1d92d152742f36fb41e4e49b528239bbb6e5288336"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RL64GNQIXGRQ255UVR5M7N6XRA/bundle.json","state_url":"https://pith.science/pith/RL64GNQIXGRQ255UVR5M7N6XRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RL64GNQIXGRQ255UVR5M7N6XRA/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":"2026-05-29T16:50:48Z","links":{"resolver":"https://pith.science/pith/RL64GNQIXGRQ255UVR5M7N6XRA","bundle":"https://pith.science/pith/RL64GNQIXGRQ255UVR5M7N6XRA/bundle.json","state":"https://pith.science/pith/RL64GNQIXGRQ255UVR5M7N6XRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RL64GNQIXGRQ255UVR5M7N6XRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RL64GNQIXGRQ255UVR5M7N6XRA","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":"143ad4bde7b8859ffae61f6983c2209f614a740e39d87bd1c37514c05515f95f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T13:06:00Z","title_canon_sha256":"6fb39a569f35bdf88b5dac5f65e7da57f06af0f0799f1d14c114e0f9ea210f04"},"schema_version":"1.0","source":{"id":"2505.22322","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22322","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22322v3","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22322","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"RL64GNQIXGRQ","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"RL64GNQIXGRQ255U","created_at":"2026-05-26T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"RL64GNQI","created_at":"2026-05-26T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:19f30b79f57e6d9ed945fb1d92d152742f36fb41e4e49b528239bbb6e5288336","target":"graph","created_at":"2026-05-26T02:05:00Z","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/2505.22322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have shown strong performance in generating high-quality tabular data, but they carry privacy risks by reproducing exact training samples. While prior work focuses on dataset-level augmentation to reduce memorization, little is known about which individual samples contribute most. We present the first data-centric study of memorization dynamics in tabular diffusion models. We quantify memorization for each real sample based on how many generated samples are flagged as replicas, using a relative distance ratio. Our empirical analysis reveals a heavy-tailed distribution of memor","authors_text":"Huiyuan Chen, Jing Li, Kaiyu Tang, Xiaoge Zhang, Xiao Li, Zhengyu Fang, Zhimeng Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T13:06:00Z","title":"A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22322","kind":"arxiv","version":3},"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":"sha256:12dac595dac0d0b46a6100fb835efd44a369401756f70870230b37a1202c778b","target":"record","created_at":"2026-05-26T02:05:00Z","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":"143ad4bde7b8859ffae61f6983c2209f614a740e39d87bd1c37514c05515f95f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T13:06:00Z","title_canon_sha256":"6fb39a569f35bdf88b5dac5f65e7da57f06af0f0799f1d14c114e0f9ea210f04"},"schema_version":"1.0","source":{"id":"2505.22322","kind":"arxiv","version":3}},"canonical_sha256":"8afdc33608b9a30d77b4ac7acfb7d7883ce9d01ad3d0290131f3f699ac1f355a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8afdc33608b9a30d77b4ac7acfb7d7883ce9d01ad3d0290131f3f699ac1f355a","first_computed_at":"2026-05-26T02:05:00.453924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:00.453924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gfamm5ewEUsM6/qS8oCKp8p30x0LSfkWU5rWbEDdfZFH23goqlok89HiDHLA9OYJAkapq+8s++d8gz6Tw3PrDw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:00.454802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22322","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12dac595dac0d0b46a6100fb835efd44a369401756f70870230b37a1202c778b","sha256:19f30b79f57e6d9ed945fb1d92d152742f36fb41e4e49b528239bbb6e5288336"],"state_sha256":"d2244ff679e5f610f041840c1e97d586505a9d7707849ccfe57d8da85f630461"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/IeszwDsaZFN3Bx2x4hUiP2BRBmDdG/UgTB9JNE5ShRHgIx6HPvWSZHsuCQd1XqaQ4VCmPAqSd0stbYBEX/mBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:50:48.013346Z","bundle_sha256":"0dc7c851be289cfb433339f2b6ca3aba532da5044e6d09e8b6b82dc59146cb15"}}