{"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"}