{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MJ4RGLWNEASWIWSC5AT2F544XQ","short_pith_number":"pith:MJ4RGLWN","canonical_record":{"source":{"id":"2302.02041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T00:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"1642978b84f3656a06b31f7f30eaa1bd8cc5c036a7ec38a14df38e0a7a4de0b6","abstract_canon_sha256":"acaafe3509c4ebf5c1c5f669d9fe900b80ca93fea38654bcb8d4859f75095a07"},"schema_version":"1.0"},"canonical_sha256":"6279132ecd2025645a42e827a2f79cbc1ae7680e3043d4c43d38cdc124f361f7","source":{"kind":"arxiv","id":"2302.02041","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02041","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02041v1","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02041","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"MJ4RGLWNEASW","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"pith_short_16","alias_value":"MJ4RGLWNEASWIWSC","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"pith_short_8","alias_value":"MJ4RGLWN","created_at":"2026-07-05T05:38:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MJ4RGLWNEASWIWSC5AT2F544XQ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.02041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T00:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"1642978b84f3656a06b31f7f30eaa1bd8cc5c036a7ec38a14df38e0a7a4de0b6","abstract_canon_sha256":"acaafe3509c4ebf5c1c5f669d9fe900b80ca93fea38654bcb8d4859f75095a07"},"schema_version":"1.0"},"canonical_sha256":"6279132ecd2025645a42e827a2f79cbc1ae7680e3043d4c43d38cdc124f361f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:48.066586Z","signature_b64":"s68gxAgP0P4aitHRgw0c01boG070ZZBas/Q8kFFdD0box41keIwGd1JS6VlkDGhYPtkh1Mvseec5ekeJBh79CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6279132ecd2025645a42e827a2f79cbc1ae7680e3043d4c43d38cdc124f361f7","last_reissued_at":"2026-07-05T05:38:48.066013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:48.066013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.02041","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":"2026-07-05T05:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/k7QYhPjLOV0ev12rGDzu/yaPPyvBR7HFugWAjlu2Y7ff9cus8fmnKUiOQUKRuJ7F3ObfPvJyJvjcdaLdkHuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T12:25:33.051942Z"},"content_sha256":"6c583101b9cb470cd45b218787d7ade73b4c6f3193db0c2fdc6ec204a4bfb302","schema_version":"1.0","event_id":"sha256:6c583101b9cb470cd45b218787d7ade73b4c6f3193db0c2fdc6ec204a4bfb302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MJ4RGLWNEASWIWSC5AT2F544XQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aivin V. Solatorio, Olivier Dupriez","submitted_at":"2023-02-04T00:32:50Z","abstract_excerpt":"Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling relational data is challenging as it requires modeling both a \"parent\" table and its relationships across tables. We introduce REaLTabFormer (Realistic Relational and Tabular Transformer), a tabular and relational synthetic data generation model. It first creates a parent table using an autoregressive GPT-2 model, then generates the relational dataset conditioned on the parent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02041","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/2302.02041/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":"2026-07-05T05:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PfUt9uT3MmCMG5IbaudjV4U/Fu/uO0/uxKQ+YthKFqtBrOpxZ6dbHxzhp+F9Lb67pcv3RJ3MMtLLynNksvnWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T12:25:33.052334Z"},"content_sha256":"0303cccf29590ec2fe1edbbdadf775b1718c9e2a0f26da1c332f393be6922f5f","schema_version":"1.0","event_id":"sha256:0303cccf29590ec2fe1edbbdadf775b1718c9e2a0f26da1c332f393be6922f5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/bundle.json","state_url":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/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":"2026-07-15T12:25:33Z","links":{"resolver":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ","bundle":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/bundle.json","state":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MJ4RGLWNEASWIWSC5AT2F544XQ","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":"acaafe3509c4ebf5c1c5f669d9fe900b80ca93fea38654bcb8d4859f75095a07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T00:32:50Z","title_canon_sha256":"1642978b84f3656a06b31f7f30eaa1bd8cc5c036a7ec38a14df38e0a7a4de0b6"},"schema_version":"1.0","source":{"id":"2302.02041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02041","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02041v1","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02041","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"MJ4RGLWNEASW","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"pith_short_16","alias_value":"MJ4RGLWNEASWIWSC","created_at":"2026-07-05T05:38:48Z"},{"alias_kind":"pith_short_8","alias_value":"MJ4RGLWN","created_at":"2026-07-05T05:38:48Z"}],"graph_snapshots":[{"event_id":"sha256:0303cccf29590ec2fe1edbbdadf775b1718c9e2a0f26da1c332f393be6922f5f","target":"graph","created_at":"2026-07-05T05:38:48Z","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/2302.02041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling relational data is challenging as it requires modeling both a \"parent\" table and its relationships across tables. We introduce REaLTabFormer (Realistic Relational and Tabular Transformer), a tabular and relational synthetic data generation model. It first creates a parent table using an autoregressive GPT-2 model, then generates the relational dataset conditioned on the parent","authors_text":"Aivin V. Solatorio, Olivier Dupriez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T00:32:50Z","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02041","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":"sha256:6c583101b9cb470cd45b218787d7ade73b4c6f3193db0c2fdc6ec204a4bfb302","target":"record","created_at":"2026-07-05T05:38:48Z","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":"acaafe3509c4ebf5c1c5f669d9fe900b80ca93fea38654bcb8d4859f75095a07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T00:32:50Z","title_canon_sha256":"1642978b84f3656a06b31f7f30eaa1bd8cc5c036a7ec38a14df38e0a7a4de0b6"},"schema_version":"1.0","source":{"id":"2302.02041","kind":"arxiv","version":1}},"canonical_sha256":"6279132ecd2025645a42e827a2f79cbc1ae7680e3043d4c43d38cdc124f361f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6279132ecd2025645a42e827a2f79cbc1ae7680e3043d4c43d38cdc124f361f7","first_computed_at":"2026-07-05T05:38:48.066013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:48.066013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s68gxAgP0P4aitHRgw0c01boG070ZZBas/Q8kFFdD0box41keIwGd1JS6VlkDGhYPtkh1Mvseec5ekeJBh79CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:48.066586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c583101b9cb470cd45b218787d7ade73b4c6f3193db0c2fdc6ec204a4bfb302","sha256:0303cccf29590ec2fe1edbbdadf775b1718c9e2a0f26da1c332f393be6922f5f"],"state_sha256":"3657b27e9ea6dc4a32f408b4978abea6a6561b22c7e7b59e0c43522daa0993ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"01PITBH2AS0zk/Z130MsOAEDr7t5rmz7ylO90OFRYrE4tazOYvmuFljgfxVBSXSvckOn9B4x2hesUroq8VdeBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T12:25:33.054564Z","bundle_sha256":"75cebf41050b8476f0b797cd629101906264bd69a7598a637b7d919423313ac3"}}