{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MI5D6E77N4CI7GGG6U2CRU6OVW","short_pith_number":"pith:MI5D6E77","canonical_record":{"source":{"id":"2412.05153","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T16:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"c67454bcb7c7c552a0ab6db91a8779e3bbed2281003b6f502e5d0bb6dc88141a","abstract_canon_sha256":"80f30209d7590ee350ec55226fe8879bcb78cac2371b898df4d39d739ab5e7e0"},"schema_version":"1.0"},"canonical_sha256":"623a3f13ff6f048f98c6f53428d3cead8134fe4994c1a60474956ebf1a30d05e","source":{"kind":"arxiv","id":"2412.05153","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05153","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05153v2","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05153","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"MI5D6E77N4CI","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"pith_short_16","alias_value":"MI5D6E77N4CI7GGG","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"pith_short_8","alias_value":"MI5D6E77","created_at":"2026-07-05T11:26:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MI5D6E77N4CI7GGG6U2CRU6OVW","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05153","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T16:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"c67454bcb7c7c552a0ab6db91a8779e3bbed2281003b6f502e5d0bb6dc88141a","abstract_canon_sha256":"80f30209d7590ee350ec55226fe8879bcb78cac2371b898df4d39d739ab5e7e0"},"schema_version":"1.0"},"canonical_sha256":"623a3f13ff6f048f98c6f53428d3cead8134fe4994c1a60474956ebf1a30d05e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:25.031821Z","signature_b64":"AxIDEOoTrphq5VGKfj2kwuHKvjxEO2C+4PyX1jSR1SUh06fdGq2j6I9xPacvDGXVI1Y/Lcb8jcuVOP6UeQ74Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"623a3f13ff6f048f98c6f53428d3cead8134fe4994c1a60474956ebf1a30d05e","last_reissued_at":"2026-07-05T11:26:25.031381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:25.031381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05153","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":"2026-07-05T11:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1r274zOa0JCr+vMpHklwg7uFkdhJdcRE6S9G3+d0peON8jAJzw74FppzSNUSOlk7uD5uvk2ocRnHrrOAm3sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:01:10.266659Z"},"content_sha256":"4bb0221955d4f02c42a7f6fe0f66cc9d5af27e9de2f4b268bafe8e9e056fef73","schema_version":"1.0","event_id":"sha256:4bb0221955d4f02c42a7f6fe0f66cc9d5af27e9de2f4b268bafe8e9e056fef73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MI5D6E77N4CI7GGG6U2CRU6OVW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A text-to-tabular approach to generate synthetic patient data using LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine Movschin, Jean-Daniel Zucker, Margaux Tornqvist, Mathilde Berthelot, Nicolas Lambert, Tristan Fauvel","submitted_at":"2024-12-06T16:10:40Z","abstract_excerpt":"Access to large-scale high-quality healthcare databases is key to accelerate medical research and make insightful discoveries about diseases. However, access to such data is often limited by patient privacy concerns, data sharing restrictions and high costs. To overcome these limitations, synthetic patient data has emerged as an alternative. However, synthetic data generation (SDG) methods typically rely on machine learning (ML) models trained on original data, leading back to the data scarcity problem. We propose an approach to generate synthetic tabular patient data that does not require acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05153","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/2412.05153/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":"2026-07-05T11:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7W11qvivVdun0QZW7CK7t1TXpEMaLyECkmECBKURcJHIo5AK5ACRE9NGY0pi8bWTsTtarAct3twmrOztxrS5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:01:10.267005Z"},"content_sha256":"f18431a94316b1493bc4498508a60b044f360584b96325f5a739df6da478fbf9","schema_version":"1.0","event_id":"sha256:f18431a94316b1493bc4498508a60b044f360584b96325f5a739df6da478fbf9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MI5D6E77N4CI7GGG6U2CRU6OVW/bundle.json","state_url":"https://pith.science/pith/MI5D6E77N4CI7GGG6U2CRU6OVW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MI5D6E77N4CI7GGG6U2CRU6OVW/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":"2026-08-13T21:01:10Z","links":{"resolver":"https://pith.science/pith/MI5D6E77N4CI7GGG6U2CRU6OVW","bundle":"https://pith.science/pith/MI5D6E77N4CI7GGG6U2CRU6OVW/bundle.json","state":"https://pith.science/pith/MI5D6E77N4CI7GGG6U2CRU6OVW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MI5D6E77N4CI7GGG6U2CRU6OVW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MI5D6E77N4CI7GGG6U2CRU6OVW","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":"80f30209d7590ee350ec55226fe8879bcb78cac2371b898df4d39d739ab5e7e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T16:10:40Z","title_canon_sha256":"c67454bcb7c7c552a0ab6db91a8779e3bbed2281003b6f502e5d0bb6dc88141a"},"schema_version":"1.0","source":{"id":"2412.05153","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05153","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05153v2","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05153","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"MI5D6E77N4CI","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"pith_short_16","alias_value":"MI5D6E77N4CI7GGG","created_at":"2026-07-05T11:26:25Z"},{"alias_kind":"pith_short_8","alias_value":"MI5D6E77","created_at":"2026-07-05T11:26:25Z"}],"graph_snapshots":[{"event_id":"sha256:f18431a94316b1493bc4498508a60b044f360584b96325f5a739df6da478fbf9","target":"graph","created_at":"2026-07-05T11:26:25Z","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/2412.05153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Access to large-scale high-quality healthcare databases is key to accelerate medical research and make insightful discoveries about diseases. However, access to such data is often limited by patient privacy concerns, data sharing restrictions and high costs. To overcome these limitations, synthetic patient data has emerged as an alternative. However, synthetic data generation (SDG) methods typically rely on machine learning (ML) models trained on original data, leading back to the data scarcity problem. We propose an approach to generate synthetic tabular patient data that does not require acc","authors_text":"Antoine Movschin, Jean-Daniel Zucker, Margaux Tornqvist, Mathilde Berthelot, Nicolas Lambert, Tristan Fauvel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T16:10:40Z","title":"A text-to-tabular approach to generate synthetic patient data using LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05153","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":"sha256:4bb0221955d4f02c42a7f6fe0f66cc9d5af27e9de2f4b268bafe8e9e056fef73","target":"record","created_at":"2026-07-05T11:26:25Z","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":"80f30209d7590ee350ec55226fe8879bcb78cac2371b898df4d39d739ab5e7e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T16:10:40Z","title_canon_sha256":"c67454bcb7c7c552a0ab6db91a8779e3bbed2281003b6f502e5d0bb6dc88141a"},"schema_version":"1.0","source":{"id":"2412.05153","kind":"arxiv","version":2}},"canonical_sha256":"623a3f13ff6f048f98c6f53428d3cead8134fe4994c1a60474956ebf1a30d05e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"623a3f13ff6f048f98c6f53428d3cead8134fe4994c1a60474956ebf1a30d05e","first_computed_at":"2026-07-05T11:26:25.031381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:25.031381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AxIDEOoTrphq5VGKfj2kwuHKvjxEO2C+4PyX1jSR1SUh06fdGq2j6I9xPacvDGXVI1Y/Lcb8jcuVOP6UeQ74Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:25.031821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05153","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bb0221955d4f02c42a7f6fe0f66cc9d5af27e9de2f4b268bafe8e9e056fef73","sha256:f18431a94316b1493bc4498508a60b044f360584b96325f5a739df6da478fbf9"],"state_sha256":"e00c372107a92bc3ceacf6b6b2d4de891a4c54cff2a1af69795b55c532f5a724"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3QhnNvQo2Ob6T5d0l7jURmlHZnuBbWxf5QBYo4dmJbBlqWlwMDu4ARD5zW18mOxGCspMYgCYlOHgTx84tGJUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T21:01:10.298796Z","bundle_sha256":"1725dd9490ff42a168f0e94d61c6a386f6c841305c1f033a4a2a6c42dc40d26b"}}