{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VAEMR37CTYWXWTUA3B2BG4LA4K","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":"fd28f2f0b07c1bff8ec5a418772ee5fb93c6e65aab39e0361af95d65e1a08301","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-30T05:52:49Z","title_canon_sha256":"197796b4d71e8ac70b021351adb52f01e33d6788564b2c70a9d54ed8412b298e"},"schema_version":"1.0","source":{"id":"2604.27456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27456","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27456v2","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27456","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"VAEMR37CTYWX","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"VAEMR37CTYWXWTUA","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"VAEMR37C","created_at":"2026-06-09T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:63768fdcd84674cf7652fb1582d5474835a544051f186b83304330c86a89039d","target":"graph","created_at":"2026-06-09T01:04:43Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our approach combines secure multiparty computation (MPC) to ensure input privacy, so that no party ever discloses its data in unencrypted form, with differential privacy (DP) to provide output privacy by mitigating information leakage from the released synthetic data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the utility of the synthetic data remains high enough for downstream AI tasks after applying both MPC and DP, even when data distributions differ across sites."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A combination of MPC and DP enables federated training of synthetic genomic data generators across institutions while preserving input and output privacy."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Secure multiparty computation and differential privacy let multiple sites jointly train synthetic genomic data generators without exposing raw inputs."}],"snapshot_sha256":"ea368f0af5a960f527390a245618b0cd49d76f869dab96bc227eca52ce7d3ca5"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T22:36:02.353919Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:15:19.865081Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.27456/integrity.json","findings":[],"snapshot_sha256":"f7b45fce5f01a07b8a521b44e602fe33ec27c1dadbc7fdd83e6944c889f30a8f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Access to genomic data is highly regulated due to its sensitive nature. While safeguards are essential, cumbersome data access processes pose a significant barrier to the development of AI methods for genomics. Synthetic data generation can mitigate this tension by enabling broader data sharing without exposing sensitive information. Synthetic genomic data are produced by training generative models on real data and subsequently sampling artificial data that preserves relevant statistics while limiting disclosures about the underlying individuals. In some settings, a single data holder may have","authors_text":"Daniil Filienko, Martine De Cock, Sikha Pentyala","cross_cats":[],"headline":"Secure multiparty computation and differential privacy let multiple sites jointly train synthetic genomic data generators without exposing raw inputs.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-30T05:52:49Z","title":"Secure Cross-Silo Synthetic Genomic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27456","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T10:19:40.679515Z","id":"7dd97f11-1782-489b-be64-644adcb3168a","model_set":{"reader":"grok-4.3"},"one_line_summary":"A combination of MPC and DP enables federated training of synthetic genomic data generators across institutions while preserving input and output privacy.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Secure multiparty computation and differential privacy let multiple sites jointly train synthetic genomic data generators without exposing raw inputs.","strongest_claim":"Our approach combines secure multiparty computation (MPC) to ensure input privacy, so that no party ever discloses its data in unencrypted form, with differential privacy (DP) to provide output privacy by mitigating information leakage from the released synthetic data.","weakest_assumption":"That the utility of the synthetic data remains high enough for downstream AI tasks after applying both MPC and DP, even when data distributions differ across sites."}},"verdict_id":"7dd97f11-1782-489b-be64-644adcb3168a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d3e6b6b600f69709213d572b51607e5be620ab36be73f95db31a4ee1ad9bd37a","target":"record","created_at":"2026-06-09T01:04:43Z","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":"fd28f2f0b07c1bff8ec5a418772ee5fb93c6e65aab39e0361af95d65e1a08301","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-30T05:52:49Z","title_canon_sha256":"197796b4d71e8ac70b021351adb52f01e33d6788564b2c70a9d54ed8412b298e"},"schema_version":"1.0","source":{"id":"2604.27456","kind":"arxiv","version":2}},"canonical_sha256":"a808c8efe29e2d7b4e80d874137160e2955dcf168b52420335fc29a5f086c5ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a808c8efe29e2d7b4e80d874137160e2955dcf168b52420335fc29a5f086c5ff","first_computed_at":"2026-06-09T01:04:43.195999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:43.195999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EVSSwEN3RRrZmF2syBXdqJof58mTO4rJy+IiKwGrbBrqGGKzomCxpQyNWVedDEkdIvrpIHBqIXhZiYptiLriCw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:43.196540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3e6b6b600f69709213d572b51607e5be620ab36be73f95db31a4ee1ad9bd37a","sha256:63768fdcd84674cf7652fb1582d5474835a544051f186b83304330c86a89039d"],"state_sha256":"03ace711592de358b1783b4e2d70cbf073e3c727a3e7d44cd1021bc4450fb30f"}