{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BO72QISZEPQR6GJBNDHNHSFN2B","short_pith_number":"pith:BO72QISZ","canonical_record":{"source":{"id":"2503.15564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T04:16:05Z","cross_cats_sorted":[],"title_canon_sha256":"ad5d1067834c0e7970c20716f35c35a147ef19c4e03e8ad4e053fdefd9a57308","abstract_canon_sha256":"8dec84b7483549526894f22b3777fa92500db6ed62aae0def2e3b784b2b38fdf"},"schema_version":"1.0"},"canonical_sha256":"0bbfa8225923e11f192168ced3c8add05ab5e7c5d6053f05561f2d1b251b072c","source":{"kind":"arxiv","id":"2503.15564","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15564","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15564v1","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15564","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"BO72QISZEPQR","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"BO72QISZEPQR6GJB","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"BO72QISZ","created_at":"2026-07-05T10:35:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BO72QISZEPQR6GJBNDHNHSFN2B","target":"record","payload":{"canonical_record":{"source":{"id":"2503.15564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T04:16:05Z","cross_cats_sorted":[],"title_canon_sha256":"ad5d1067834c0e7970c20716f35c35a147ef19c4e03e8ad4e053fdefd9a57308","abstract_canon_sha256":"8dec84b7483549526894f22b3777fa92500db6ed62aae0def2e3b784b2b38fdf"},"schema_version":"1.0"},"canonical_sha256":"0bbfa8225923e11f192168ced3c8add05ab5e7c5d6053f05561f2d1b251b072c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:52.761293Z","signature_b64":"BDvcKpNHBoMfrB7NQCZP8NvkBEkUckd5DkgBmI+GjAZZ8Ddr19PfLzDy1pxcRaB78j5U9KAjPC0J/aUEInFjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bbfa8225923e11f192168ced3c8add05ab5e7c5d6053f05561f2d1b251b072c","last_reissued_at":"2026-07-05T10:35:52.760742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:52.760742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.15564","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":"2026-07-05T10:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EH2UtKNbVLb3r28j64+u44rIz5sdRN/uk/5mhc/qaLEnIdNv0cbL986wCVWMVwVGmfAi6bKf5eypYpmrLyDUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:49:13.973301Z"},"content_sha256":"21fe723a02a3bfd4c76806000888c5e2aee97c5ad213cf4d94754fecacecb4fc","schema_version":"1.0","event_id":"sha256:21fe723a02a3bfd4c76806000888c5e2aee97c5ad213cf4d94754fecacecb4fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BO72QISZEPQR6GJBNDHNHSFN2B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chi-Hua Wang, Guang Cheng, Tung Sum Thomas Kwok","submitted_at":"2025-03-19T04:16:05Z","abstract_excerpt":"Tabular data synthesis involves not only multi-table synthesis but also generating multi-modal data (e.g., strings and categories), which enables diverse knowledge synthesis. However, separating numerical and categorical data has limited the effectiveness of tabular data generation. The GReaT (Generate Realistic Tabular Data) framework uses Large Language Models (LLMs) to encode entire rows, eliminating the need to partition data types. Despite this, the framework's performance is constrained by two issues: (1) tabular data entries lack sufficient semantic meaning, limiting LLM's ability to le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15564","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/2503.15564/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":"2026-07-05T10:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XrVJb6YyIx4zS9S3sTSAABONeibngUDCaSaP9AtIsMsOQJypT0xl5LSNt3hDlq84S1GJrUawIDmKk256Zqq0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:49:13.973691Z"},"content_sha256":"51029b4d7e6923cc5c7d8b493cea02b79fdc536879db2f4d6a51c15c71a0168b","schema_version":"1.0","event_id":"sha256:51029b4d7e6923cc5c7d8b493cea02b79fdc536879db2f4d6a51c15c71a0168b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BO72QISZEPQR6GJBNDHNHSFN2B/bundle.json","state_url":"https://pith.science/pith/BO72QISZEPQR6GJBNDHNHSFN2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BO72QISZEPQR6GJBNDHNHSFN2B/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":"2026-07-07T12:49:13Z","links":{"resolver":"https://pith.science/pith/BO72QISZEPQR6GJBNDHNHSFN2B","bundle":"https://pith.science/pith/BO72QISZEPQR6GJBNDHNHSFN2B/bundle.json","state":"https://pith.science/pith/BO72QISZEPQR6GJBNDHNHSFN2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BO72QISZEPQR6GJBNDHNHSFN2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BO72QISZEPQR6GJBNDHNHSFN2B","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":"8dec84b7483549526894f22b3777fa92500db6ed62aae0def2e3b784b2b38fdf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T04:16:05Z","title_canon_sha256":"ad5d1067834c0e7970c20716f35c35a147ef19c4e03e8ad4e053fdefd9a57308"},"schema_version":"1.0","source":{"id":"2503.15564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15564","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15564v1","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15564","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"BO72QISZEPQR","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"BO72QISZEPQR6GJB","created_at":"2026-07-05T10:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"BO72QISZ","created_at":"2026-07-05T10:35:52Z"}],"graph_snapshots":[{"event_id":"sha256:51029b4d7e6923cc5c7d8b493cea02b79fdc536879db2f4d6a51c15c71a0168b","target":"graph","created_at":"2026-07-05T10:35:52Z","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/2503.15564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data synthesis involves not only multi-table synthesis but also generating multi-modal data (e.g., strings and categories), which enables diverse knowledge synthesis. However, separating numerical and categorical data has limited the effectiveness of tabular data generation. The GReaT (Generate Realistic Tabular Data) framework uses Large Language Models (LLMs) to encode entire rows, eliminating the need to partition data types. Despite this, the framework's performance is constrained by two issues: (1) tabular data entries lack sufficient semantic meaning, limiting LLM's ability to le","authors_text":"Chi-Hua Wang, Guang Cheng, Tung Sum Thomas Kwok","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T04:16:05Z","title":"GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15564","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":"sha256:21fe723a02a3bfd4c76806000888c5e2aee97c5ad213cf4d94754fecacecb4fc","target":"record","created_at":"2026-07-05T10:35:52Z","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":"8dec84b7483549526894f22b3777fa92500db6ed62aae0def2e3b784b2b38fdf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T04:16:05Z","title_canon_sha256":"ad5d1067834c0e7970c20716f35c35a147ef19c4e03e8ad4e053fdefd9a57308"},"schema_version":"1.0","source":{"id":"2503.15564","kind":"arxiv","version":1}},"canonical_sha256":"0bbfa8225923e11f192168ced3c8add05ab5e7c5d6053f05561f2d1b251b072c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bbfa8225923e11f192168ced3c8add05ab5e7c5d6053f05561f2d1b251b072c","first_computed_at":"2026-07-05T10:35:52.760742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:52.760742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDvcKpNHBoMfrB7NQCZP8NvkBEkUckd5DkgBmI+GjAZZ8Ddr19PfLzDy1pxcRaB78j5U9KAjPC0J/aUEInFjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:52.761293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21fe723a02a3bfd4c76806000888c5e2aee97c5ad213cf4d94754fecacecb4fc","sha256:51029b4d7e6923cc5c7d8b493cea02b79fdc536879db2f4d6a51c15c71a0168b"],"state_sha256":"e1adb0ee47a9a97907db635d20f3fd05526c4368edbd47ef893038021513324b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qKfDWUKtO+v3kooKbXOKnDkISFDNXTVP7nDFGt3ldqzQFOXiT5ogYKYtrEBNwEmo60ijWhyCFurpUe1vt+0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:49:13.975687Z","bundle_sha256":"90130a17d3dbc2e0c8e94b892c7f74685b5c3a1a3ae51a1a87196b38951368cc"}}