{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ROHMJNBL6QW2CZRD6SNOXZ7NA4","short_pith_number":"pith:ROHMJNBL","canonical_record":{"source":{"id":"2607.09404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T13:35:37Z","cross_cats_sorted":[],"title_canon_sha256":"26167125fea133caad82a9c2718744c886c808ea54ec6e1f3e3cdbf6b5fd32c7","abstract_canon_sha256":"d5795e666c3bd9cd0627bb3b4a6c6bb99285518599410cf116d1b6aec052edc6"},"schema_version":"1.0"},"canonical_sha256":"8b8ec4b42bf42da16623f49aebe7ed070fe0474124f737997020b84420f0d4cd","source":{"kind":"arxiv","id":"2607.09404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09404","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09404v1","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09404","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"ROHMJNBL6QW2","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"ROHMJNBL6QW2CZRD","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"ROHMJNBL","created_at":"2026-07-13T01:19:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ROHMJNBL6QW2CZRD6SNOXZ7NA4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.09404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T13:35:37Z","cross_cats_sorted":[],"title_canon_sha256":"26167125fea133caad82a9c2718744c886c808ea54ec6e1f3e3cdbf6b5fd32c7","abstract_canon_sha256":"d5795e666c3bd9cd0627bb3b4a6c6bb99285518599410cf116d1b6aec052edc6"},"schema_version":"1.0"},"canonical_sha256":"8b8ec4b42bf42da16623f49aebe7ed070fe0474124f737997020b84420f0d4cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:10.425628Z","signature_b64":"AsDwd9orJ8hUSDy1ETy4UnuQ8DmtUwRZ1VudE8BAN2ZMHwBPkQprrpPrZRNB8dC8J+murVNy2+61guLWEFq7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b8ec4b42bf42da16623f49aebe7ed070fe0474124f737997020b84420f0d4cd","last_reissued_at":"2026-07-13T01:19:10.424458Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:10.424458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.09404","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T01:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GifWQe4WKVOYHVoxLi6DLRNDKNJDSMYvpjQv0nVaUAW29MqnpBEdzFPHC4vPq1tGZrcM0C0z/DsxR68/yVZSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:06:52.643144Z"},"content_sha256":"38c10b4db40c07fb0921063512d57aff6a2ca548f59873221a9584fdfe7f40d5","schema_version":"1.0","event_id":"sha256:38c10b4db40c07fb0921063512d57aff6a2ca548f59873221a9584fdfe7f40d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ROHMJNBL6QW2CZRD6SNOXZ7NA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SYNRARE: Synthetic Rare Disease EHR Generation for ML Benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nicolai Dinh Khang Truong, Richard R\\\"ottger","submitted_at":"2026-07-10T13:35:37Z","abstract_excerpt":"Motivation: Rare disease (RD) diagnosis is frequently delayed due to the similarities in symptoms to common disease variants. Machine Learning Algorithms applied to Electronic Health Records show promise for accelerating the diagnosis; however, legal and privacy concerns pose significant barriers. To address these issues, Synthetic Data Generation is an alternative method for obtaining Electronic Health Records and can be applied with any Machine Learning algorithm for benchmarking and development purposes. Despite the availability of Synthetic Data Generation algorithms, support for generatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09404","kind":"arxiv","version":1},"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/2607.09404/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":"2026-07-13T01:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WeZABcnPtRQUOL401l7+T12gWL67QBWV1+GcgWfzIFc7t0A+r2KHftln0i3vPgKH6fBB9l11/V6g/S61RFExAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:06:52.644076Z"},"content_sha256":"282d3894177e09261e0a7a9f707e7fabffff1ae73a1c8954dbff5dc0ba3f6641","schema_version":"1.0","event_id":"sha256:282d3894177e09261e0a7a9f707e7fabffff1ae73a1c8954dbff5dc0ba3f6641"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROHMJNBL6QW2CZRD6SNOXZ7NA4/bundle.json","state_url":"https://pith.science/pith/ROHMJNBL6QW2CZRD6SNOXZ7NA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROHMJNBL6QW2CZRD6SNOXZ7NA4/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":"2026-08-14T07:06:52Z","links":{"resolver":"https://pith.science/pith/ROHMJNBL6QW2CZRD6SNOXZ7NA4","bundle":"https://pith.science/pith/ROHMJNBL6QW2CZRD6SNOXZ7NA4/bundle.json","state":"https://pith.science/pith/ROHMJNBL6QW2CZRD6SNOXZ7NA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROHMJNBL6QW2CZRD6SNOXZ7NA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ROHMJNBL6QW2CZRD6SNOXZ7NA4","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":"d5795e666c3bd9cd0627bb3b4a6c6bb99285518599410cf116d1b6aec052edc6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T13:35:37Z","title_canon_sha256":"26167125fea133caad82a9c2718744c886c808ea54ec6e1f3e3cdbf6b5fd32c7"},"schema_version":"1.0","source":{"id":"2607.09404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09404","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09404v1","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09404","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"ROHMJNBL6QW2","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"ROHMJNBL6QW2CZRD","created_at":"2026-07-13T01:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"ROHMJNBL","created_at":"2026-07-13T01:19:10Z"}],"graph_snapshots":[{"event_id":"sha256:282d3894177e09261e0a7a9f707e7fabffff1ae73a1c8954dbff5dc0ba3f6641","target":"graph","created_at":"2026-07-13T01:19:10Z","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/2607.09404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivation: Rare disease (RD) diagnosis is frequently delayed due to the similarities in symptoms to common disease variants. Machine Learning Algorithms applied to Electronic Health Records show promise for accelerating the diagnosis; however, legal and privacy concerns pose significant barriers. To address these issues, Synthetic Data Generation is an alternative method for obtaining Electronic Health Records and can be applied with any Machine Learning algorithm for benchmarking and development purposes. Despite the availability of Synthetic Data Generation algorithms, support for generatin","authors_text":"Nicolai Dinh Khang Truong, Richard R\\\"ottger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T13:35:37Z","title":"SYNRARE: Synthetic Rare Disease EHR Generation for ML Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09404","kind":"arxiv","version":1},"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":"sha256:38c10b4db40c07fb0921063512d57aff6a2ca548f59873221a9584fdfe7f40d5","target":"record","created_at":"2026-07-13T01:19:10Z","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":"d5795e666c3bd9cd0627bb3b4a6c6bb99285518599410cf116d1b6aec052edc6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T13:35:37Z","title_canon_sha256":"26167125fea133caad82a9c2718744c886c808ea54ec6e1f3e3cdbf6b5fd32c7"},"schema_version":"1.0","source":{"id":"2607.09404","kind":"arxiv","version":1}},"canonical_sha256":"8b8ec4b42bf42da16623f49aebe7ed070fe0474124f737997020b84420f0d4cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b8ec4b42bf42da16623f49aebe7ed070fe0474124f737997020b84420f0d4cd","first_computed_at":"2026-07-13T01:19:10.424458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:19:10.424458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AsDwd9orJ8hUSDy1ETy4UnuQ8DmtUwRZ1VudE8BAN2ZMHwBPkQprrpPrZRNB8dC8J+murVNy2+61guLWEFq7DQ==","signature_status":"signed_v1","signed_at":"2026-07-13T01:19:10.425628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38c10b4db40c07fb0921063512d57aff6a2ca548f59873221a9584fdfe7f40d5","sha256:282d3894177e09261e0a7a9f707e7fabffff1ae73a1c8954dbff5dc0ba3f6641"],"state_sha256":"b70cf1e9cd3f12da5e655588bcf22f32fadf44b1e64e951fe87f590d3f9ce558"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEGDHU/VgptIXg4MU7/mRbI9zVWMmgcUnzVXXUtPadZO+SEXNqnfrB5vHOFNCZmZw8AAhnatRdcOz7YgUvFTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:06:52.652977Z","bundle_sha256":"7e6e0bc2baac2fea82212316ca6b4ac370661d16a62a68c0bc1c3dccd0cc732b"}}