{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DN4PKUTH2XDR3OOEEXMP747UZL","short_pith_number":"pith:DN4PKUTH","canonical_record":{"source":{"id":"2210.06280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T15:03:28Z","cross_cats_sorted":[],"title_canon_sha256":"203b38cae19055448d3dac4fd3e186e0c1773561583619673b60c4393865171e","abstract_canon_sha256":"95dd1a40c36b95e9ba2713831959e654b86edf275716cc2c20d5240dadb4f127"},"schema_version":"1.0"},"canonical_sha256":"1b78f55267d5c71db9c425d8fff3f4cad4f4a30b8209aab267ddaef149a53070","source":{"kind":"arxiv","id":"2210.06280","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06280","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06280v2","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06280","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"DN4PKUTH2XDR","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"DN4PKUTH2XDR3OOE","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"DN4PKUTH","created_at":"2026-07-05T06:03:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DN4PKUTH2XDR3OOEEXMP747UZL","target":"record","payload":{"canonical_record":{"source":{"id":"2210.06280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T15:03:28Z","cross_cats_sorted":[],"title_canon_sha256":"203b38cae19055448d3dac4fd3e186e0c1773561583619673b60c4393865171e","abstract_canon_sha256":"95dd1a40c36b95e9ba2713831959e654b86edf275716cc2c20d5240dadb4f127"},"schema_version":"1.0"},"canonical_sha256":"1b78f55267d5c71db9c425d8fff3f4cad4f4a30b8209aab267ddaef149a53070","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:25.837681Z","signature_b64":"TBH8Zpz+arjKN4McVCV4xufxkobWRCG2kwaBPXAZYtpPEn8wl7oZReWd67dxnMgYDrZws27WpfbJHLOyyb89Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b78f55267d5c71db9c425d8fff3f4cad4f4a30b8209aab267ddaef149a53070","last_reissued_at":"2026-07-05T06:03:25.837302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:25.837302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.06280","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNM1fbQeo+bEheG5h/w8WZJU1MHGMpBoe7LRO76Y1q5qqtidWXdKLVQUD7gQXphqzYJvrm4ML1wBMFORQXhUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:13:51.775654Z"},"content_sha256":"6bb1ba72f4570d0d5060ff56847e10eb3d5977d6485f999c46e576a269281d44","schema_version":"1.0","event_id":"sha256:6bb1ba72f4570d0d5060ff56847e10eb3d5977d6485f999c46e576a269281d44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DN4PKUTH2XDR3OOEEXMP747UZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models are Realistic Tabular Data Generators","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gjergji Kasneci, Kathrin Se{\\ss}ler, Martin Pawelczyk, Tobias Leemann, Vadim Borisov","submitted_at":"2022-10-12T15:03:28Z","abstract_excerpt":"Tabular data is among the oldest and most ubiquitous forms of data. However, the generation of synthetic samples with the original data's characteristics remains a significant challenge for tabular data. While many generative models from the computer vision domain, such as variational autoencoders or generative adversarial networks, have been adapted for tabular data generation, less research has been directed towards recent transformer-based large language models (LLMs), which are also generative in nature. To this end, we propose GReaT (Generation of Realistic Tabular data), which exploits a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06280","kind":"arxiv","version":2},"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/2210.06280/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":"2026-07-05T06:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsJhRWI4r6iwTeO/C+Ngx6mXIgFRpmT5TDlbkqMb6XLLJWqo/4tY3dONsTLa9rCh1rCftMowGDDDRe1CBMyIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:13:51.776160Z"},"content_sha256":"02daf7de987401841dd3ea30748e253c7b1ee6ac0aa3712323f98377f791fc3c","schema_version":"1.0","event_id":"sha256:02daf7de987401841dd3ea30748e253c7b1ee6ac0aa3712323f98377f791fc3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DN4PKUTH2XDR3OOEEXMP747UZL/bundle.json","state_url":"https://pith.science/pith/DN4PKUTH2XDR3OOEEXMP747UZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DN4PKUTH2XDR3OOEEXMP747UZL/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":"2026-08-15T01:13:51Z","links":{"resolver":"https://pith.science/pith/DN4PKUTH2XDR3OOEEXMP747UZL","bundle":"https://pith.science/pith/DN4PKUTH2XDR3OOEEXMP747UZL/bundle.json","state":"https://pith.science/pith/DN4PKUTH2XDR3OOEEXMP747UZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DN4PKUTH2XDR3OOEEXMP747UZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DN4PKUTH2XDR3OOEEXMP747UZL","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":"95dd1a40c36b95e9ba2713831959e654b86edf275716cc2c20d5240dadb4f127","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T15:03:28Z","title_canon_sha256":"203b38cae19055448d3dac4fd3e186e0c1773561583619673b60c4393865171e"},"schema_version":"1.0","source":{"id":"2210.06280","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06280","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06280v2","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06280","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"DN4PKUTH2XDR","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"DN4PKUTH2XDR3OOE","created_at":"2026-07-05T06:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"DN4PKUTH","created_at":"2026-07-05T06:03:25Z"}],"graph_snapshots":[{"event_id":"sha256:02daf7de987401841dd3ea30748e253c7b1ee6ac0aa3712323f98377f791fc3c","target":"graph","created_at":"2026-07-05T06:03:25Z","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/2210.06280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data is among the oldest and most ubiquitous forms of data. However, the generation of synthetic samples with the original data's characteristics remains a significant challenge for tabular data. While many generative models from the computer vision domain, such as variational autoencoders or generative adversarial networks, have been adapted for tabular data generation, less research has been directed towards recent transformer-based large language models (LLMs), which are also generative in nature. To this end, we propose GReaT (Generation of Realistic Tabular data), which exploits a","authors_text":"Gjergji Kasneci, Kathrin Se{\\ss}ler, Martin Pawelczyk, Tobias Leemann, Vadim Borisov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T15:03:28Z","title":"Language Models are Realistic Tabular Data Generators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06280","kind":"arxiv","version":2},"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":"sha256:6bb1ba72f4570d0d5060ff56847e10eb3d5977d6485f999c46e576a269281d44","target":"record","created_at":"2026-07-05T06:03:25Z","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":"95dd1a40c36b95e9ba2713831959e654b86edf275716cc2c20d5240dadb4f127","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T15:03:28Z","title_canon_sha256":"203b38cae19055448d3dac4fd3e186e0c1773561583619673b60c4393865171e"},"schema_version":"1.0","source":{"id":"2210.06280","kind":"arxiv","version":2}},"canonical_sha256":"1b78f55267d5c71db9c425d8fff3f4cad4f4a30b8209aab267ddaef149a53070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b78f55267d5c71db9c425d8fff3f4cad4f4a30b8209aab267ddaef149a53070","first_computed_at":"2026-07-05T06:03:25.837302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:25.837302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TBH8Zpz+arjKN4McVCV4xufxkobWRCG2kwaBPXAZYtpPEn8wl7oZReWd67dxnMgYDrZws27WpfbJHLOyyb89Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:25.837681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06280","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bb1ba72f4570d0d5060ff56847e10eb3d5977d6485f999c46e576a269281d44","sha256:02daf7de987401841dd3ea30748e253c7b1ee6ac0aa3712323f98377f791fc3c"],"state_sha256":"0823a4aa0b5d60b8eb04cb5eb4297d3fabcbfe969d7313c343fc98746daa9b12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qle/2KkfxTcu9lzgbYB1wekOzrIXl+6BhmIQ54u6CBGz7LQ2n8wC3f9nq0Hmg9xXkPLPP3Ev4YRbjfKSbZ64Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T01:13:51.782275Z","bundle_sha256":"00cad1dff99cc39346e16ba017779a3c95d226ac80cc41897ecd0230327f281f"}}