{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NBQXGMFI23KJVA3YUNO4ASJI5Q","short_pith_number":"pith:NBQXGMFI","canonical_record":{"source":{"id":"2406.14541","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T17:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"317d904acc4a8b1082334e2751725e1286a57c43ed1e993cdaacc6b4a637005b","abstract_canon_sha256":"8b54ca002b718569ce4e4996ddbb99028e777a48e0429ba02addfb2c091e0088"},"schema_version":"1.0"},"canonical_sha256":"68617330a8d6d49a8378a35dc04928ec15e69ad1f2e2c94d8fb91cf2266b8150","source":{"kind":"arxiv","id":"2406.14541","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14541","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14541v3","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14541","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"NBQXGMFI23KJ","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"NBQXGMFI23KJVA3Y","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"NBQXGMFI","created_at":"2026-07-05T10:30:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NBQXGMFI23KJVA3YUNO4ASJI5Q","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14541","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T17:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"317d904acc4a8b1082334e2751725e1286a57c43ed1e993cdaacc6b4a637005b","abstract_canon_sha256":"8b54ca002b718569ce4e4996ddbb99028e777a48e0429ba02addfb2c091e0088"},"schema_version":"1.0"},"canonical_sha256":"68617330a8d6d49a8378a35dc04928ec15e69ad1f2e2c94d8fb91cf2266b8150","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:54.468042Z","signature_b64":"OUpquhkYJnGcOdn1aHbYyIsEX2kIO7r3BxwPQdRVP6CCcPohTyZQIV09LNhRO6gpkywrLJibcHO9EpMK3cbPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68617330a8d6d49a8378a35dc04928ec15e69ad1f2e2c94d8fb91cf2266b8150","last_reissued_at":"2026-07-05T10:30:54.467551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:54.467551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14541","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":"2026-07-05T10:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RR0L6uwxabtBLKdbXA2OvUyPWYPpJ3S9JOuwhXDDUyOHUJ+hLjNCY6Rkf8gMKzEU1qGqvI/lC2pKkmU05/WZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:55:24.506253Z"},"content_sha256":"4edaaff6fed12e77f3cc91f8f7f52d22c328d24d22c68a0679036921574c25b9","schema_version":"1.0","event_id":"sha256:4edaaff6fed12e77f3cc91f8f7f52d22c328d24d22c68a0679036921574c25b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NBQXGMFI23KJVA3YUNO4ASJI5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cho-Ting Lee, Mandar Sharma, Naren Ramakrishnan, Nikhil Muralidhar, Raquib Bin Yousuf, Shengzhe Xu","submitted_at":"2024-06-20T17:52:29Z","abstract_excerpt":"Synthetic data generation is integral to ML pipelines, e.g., to augment training data, replace sensitive information, and even to power advanced platforms like DeepSeek. While LLMs fine-tuned for synthetic data generation are gaining traction, synthetic table generation -- a critical data type in business and science -- remains under-explored compared to text and image synthesis. This paper shows that LLMs, whether used as-is or after traditional fine-tuning, are inadequate for generating synthetic tables. Their autoregressive nature, combined with random order permutation during fine-tuning, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14541","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/2406.14541/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":"2026-07-05T10:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gEX7r0Gbyu2ok7AGp7AILT5v26DSxxVq9f7/IUTNP8JDaUMqut0HsmgggTYQ5L234vfqaG2ZUzHjMhoVcw6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:55:24.506765Z"},"content_sha256":"e349167f31b473b725a5a71ad3c32456da748bf7c9a82921d72f9355bba1366d","schema_version":"1.0","event_id":"sha256:e349167f31b473b725a5a71ad3c32456da748bf7c9a82921d72f9355bba1366d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBQXGMFI23KJVA3YUNO4ASJI5Q/bundle.json","state_url":"https://pith.science/pith/NBQXGMFI23KJVA3YUNO4ASJI5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBQXGMFI23KJVA3YUNO4ASJI5Q/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":"2026-08-14T00:55:24Z","links":{"resolver":"https://pith.science/pith/NBQXGMFI23KJVA3YUNO4ASJI5Q","bundle":"https://pith.science/pith/NBQXGMFI23KJVA3YUNO4ASJI5Q/bundle.json","state":"https://pith.science/pith/NBQXGMFI23KJVA3YUNO4ASJI5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBQXGMFI23KJVA3YUNO4ASJI5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NBQXGMFI23KJVA3YUNO4ASJI5Q","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":"8b54ca002b718569ce4e4996ddbb99028e777a48e0429ba02addfb2c091e0088","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T17:52:29Z","title_canon_sha256":"317d904acc4a8b1082334e2751725e1286a57c43ed1e993cdaacc6b4a637005b"},"schema_version":"1.0","source":{"id":"2406.14541","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14541","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14541v3","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14541","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"NBQXGMFI23KJ","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"NBQXGMFI23KJVA3Y","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"NBQXGMFI","created_at":"2026-07-05T10:30:54Z"}],"graph_snapshots":[{"event_id":"sha256:e349167f31b473b725a5a71ad3c32456da748bf7c9a82921d72f9355bba1366d","target":"graph","created_at":"2026-07-05T10:30:54Z","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/2406.14541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic data generation is integral to ML pipelines, e.g., to augment training data, replace sensitive information, and even to power advanced platforms like DeepSeek. While LLMs fine-tuned for synthetic data generation are gaining traction, synthetic table generation -- a critical data type in business and science -- remains under-explored compared to text and image synthesis. This paper shows that LLMs, whether used as-is or after traditional fine-tuning, are inadequate for generating synthetic tables. Their autoregressive nature, combined with random order permutation during fine-tuning, ","authors_text":"Cho-Ting Lee, Mandar Sharma, Naren Ramakrishnan, Nikhil Muralidhar, Raquib Bin Yousuf, Shengzhe Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T17:52:29Z","title":"Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14541","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":"sha256:4edaaff6fed12e77f3cc91f8f7f52d22c328d24d22c68a0679036921574c25b9","target":"record","created_at":"2026-07-05T10:30:54Z","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":"8b54ca002b718569ce4e4996ddbb99028e777a48e0429ba02addfb2c091e0088","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T17:52:29Z","title_canon_sha256":"317d904acc4a8b1082334e2751725e1286a57c43ed1e993cdaacc6b4a637005b"},"schema_version":"1.0","source":{"id":"2406.14541","kind":"arxiv","version":3}},"canonical_sha256":"68617330a8d6d49a8378a35dc04928ec15e69ad1f2e2c94d8fb91cf2266b8150","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68617330a8d6d49a8378a35dc04928ec15e69ad1f2e2c94d8fb91cf2266b8150","first_computed_at":"2026-07-05T10:30:54.467551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:54.467551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OUpquhkYJnGcOdn1aHbYyIsEX2kIO7r3BxwPQdRVP6CCcPohTyZQIV09LNhRO6gpkywrLJibcHO9EpMK3cbPAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:54.468042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14541","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4edaaff6fed12e77f3cc91f8f7f52d22c328d24d22c68a0679036921574c25b9","sha256:e349167f31b473b725a5a71ad3c32456da748bf7c9a82921d72f9355bba1366d"],"state_sha256":"20aa7f8e9eebcebc2ee46aa229d79eb82d388e5c717fa901fc989a669f6a7c14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CB40bXmX8V4ZX+xW6yukzKFvSpmTZiVJvN64RVohS4kbUqjiXU7g3Sf1jb+XKHFdAC5DT2H/CIkVShnny+Q4AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T00:55:24.547832Z","bundle_sha256":"d97e39dce25bcdb808cb40fab22994e6f24c819e0f8ca1ba066017526e906136"}}