{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6YO3QPES52UTPNML4QVIQHIU5Q","short_pith_number":"pith:6YO3QPES","canonical_record":{"source":{"id":"2505.02659","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T14:05:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49799db794d2e2e4e84f48b03112f038b8636d02046953a60800133d0e197e2c","abstract_canon_sha256":"25a3e2b108535d987f622dfd21019e7b182fe9e33a37543f6db7b3c07aecb891"},"schema_version":"1.0"},"canonical_sha256":"f61db83c92eea937b58be42a881d14ec0e6e4e81474049186b85f2a501cdf7b1","source":{"kind":"arxiv","id":"2505.02659","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02659","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02659v2","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02659","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"6YO3QPES52UT","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"6YO3QPES52UTPNML","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"6YO3QPES","created_at":"2026-07-05T10:59:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6YO3QPES52UTPNML4QVIQHIU5Q","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02659","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T14:05:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49799db794d2e2e4e84f48b03112f038b8636d02046953a60800133d0e197e2c","abstract_canon_sha256":"25a3e2b108535d987f622dfd21019e7b182fe9e33a37543f6db7b3c07aecb891"},"schema_version":"1.0"},"canonical_sha256":"f61db83c92eea937b58be42a881d14ec0e6e4e81474049186b85f2a501cdf7b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:10.548047Z","signature_b64":"AEuuV0Qx5avuilDH4zPY41R0V9RDcnkWaA2dor6GwcOYRV0yiaRCm0gcTAjHHXacOzM5G7m+2ddLBFyui4kZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f61db83c92eea937b58be42a881d14ec0e6e4e81474049186b85f2a501cdf7b1","last_reissued_at":"2026-07-05T10:59:10.547516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:10.547516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02659","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":"2026-07-05T10:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dMnRCe8YbMX8u2Wfv0kBvSjXGNDD3Y0xmXJsiYLyvtwgl00uZLfS1OR0Sen6I801rFN7ogbrTfC1L8BpaWNGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:46:59.205700Z"},"content_sha256":"482349ff7f3d10e959b44688e7c2ba3452514c8f9093c89f99480b88ac3f5ce3","schema_version":"1.0","event_id":"sha256:482349ff7f3d10e959b44688e7c2ba3452514c8f9093c89f99480b88ac3f5ce3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6YO3QPES52UTPNML4QVIQHIU5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Note on Statistically Accurate Tabular Data Generation Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrey Sidorenko","submitted_at":"2025-05-05T14:05:15Z","abstract_excerpt":"Large language models (LLMs) have shown promise in synthetic tabular data generation, yet existing methods struggle to preserve complex feature dependencies, particularly among categorical variables. This work introduces a probability-driven prompting approach that leverages LLMs to estimate conditional distributions, enabling more accurate and scalable data synthesis. The results highlight the potential of prompting probability distributions to enhance the statistical fidelity of LLM-generated tabular data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02659","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/2505.02659/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":"2026-07-05T10:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rISn6bx54zcCv85xQZecGLA4CLsJZajGub2Lvu6cM7Nckj7hlZAyelpVS5I7TIPA796HrvUX88phTdyuTbOuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:46:59.206223Z"},"content_sha256":"e6e39896f02f32b905c2fbe049b206954180cdf680637a64704e93b793264c7a","schema_version":"1.0","event_id":"sha256:e6e39896f02f32b905c2fbe049b206954180cdf680637a64704e93b793264c7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YO3QPES52UTPNML4QVIQHIU5Q/bundle.json","state_url":"https://pith.science/pith/6YO3QPES52UTPNML4QVIQHIU5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YO3QPES52UTPNML4QVIQHIU5Q/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":"2026-08-16T14:46:59Z","links":{"resolver":"https://pith.science/pith/6YO3QPES52UTPNML4QVIQHIU5Q","bundle":"https://pith.science/pith/6YO3QPES52UTPNML4QVIQHIU5Q/bundle.json","state":"https://pith.science/pith/6YO3QPES52UTPNML4QVIQHIU5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YO3QPES52UTPNML4QVIQHIU5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6YO3QPES52UTPNML4QVIQHIU5Q","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":"25a3e2b108535d987f622dfd21019e7b182fe9e33a37543f6db7b3c07aecb891","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T14:05:15Z","title_canon_sha256":"49799db794d2e2e4e84f48b03112f038b8636d02046953a60800133d0e197e2c"},"schema_version":"1.0","source":{"id":"2505.02659","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02659","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02659v2","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02659","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"6YO3QPES52UT","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"6YO3QPES52UTPNML","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"6YO3QPES","created_at":"2026-07-05T10:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:e6e39896f02f32b905c2fbe049b206954180cdf680637a64704e93b793264c7a","target":"graph","created_at":"2026-07-05T10:59:10Z","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/2505.02659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown promise in synthetic tabular data generation, yet existing methods struggle to preserve complex feature dependencies, particularly among categorical variables. This work introduces a probability-driven prompting approach that leverages LLMs to estimate conditional distributions, enabling more accurate and scalable data synthesis. The results highlight the potential of prompting probability distributions to enhance the statistical fidelity of LLM-generated tabular data.","authors_text":"Andrey Sidorenko","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T14:05:15Z","title":"A Note on Statistically Accurate Tabular Data Generation Using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02659","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":"sha256:482349ff7f3d10e959b44688e7c2ba3452514c8f9093c89f99480b88ac3f5ce3","target":"record","created_at":"2026-07-05T10:59:10Z","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":"25a3e2b108535d987f622dfd21019e7b182fe9e33a37543f6db7b3c07aecb891","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T14:05:15Z","title_canon_sha256":"49799db794d2e2e4e84f48b03112f038b8636d02046953a60800133d0e197e2c"},"schema_version":"1.0","source":{"id":"2505.02659","kind":"arxiv","version":2}},"canonical_sha256":"f61db83c92eea937b58be42a881d14ec0e6e4e81474049186b85f2a501cdf7b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f61db83c92eea937b58be42a881d14ec0e6e4e81474049186b85f2a501cdf7b1","first_computed_at":"2026-07-05T10:59:10.547516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:10.547516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AEuuV0Qx5avuilDH4zPY41R0V9RDcnkWaA2dor6GwcOYRV0yiaRCm0gcTAjHHXacOzM5G7m+2ddLBFyui4kZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:10.548047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02659","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:482349ff7f3d10e959b44688e7c2ba3452514c8f9093c89f99480b88ac3f5ce3","sha256:e6e39896f02f32b905c2fbe049b206954180cdf680637a64704e93b793264c7a"],"state_sha256":"f3c37179b1cb2c996e1899a5b9bb101ac54beade02439d48c7335ca78f825722"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LpcDaZ4DzEjM4Cb2ozee1QDCk1tKpGNXM6Z6KxaxEa/2C+/5wztfcotKtEbvUQu7yCt9zddJzqMv562fO1+EDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T14:46:59.211209Z","bundle_sha256":"9fb809d7592b5d549ec79d6e76ab3ce006e9c1b42094b44a8872113e6851bdc8"}}