{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EALESCFRHJGHCO2B3A6TLSPXYY","short_pith_number":"pith:EALESCFR","schema_version":"1.0","canonical_sha256":"20164908b13a4c713b41d83d35c9f7c605d70e5790ceedbf6626f910efcd2748","source":{"kind":"arxiv","id":"2412.03278","version":3},"attestation_state":"computed","paper":{"title":"Generating Synthetic Genotypes using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Alexander Sch\\\"onhuth, Barbara Hammer, Philip Kenneweg, Raghuram Dandinasivara, Xiao Luo","submitted_at":"2024-12-04T12:37:59Z","abstract_excerpt":"In this paper, we introduce the first diffusion model designed to generate complete synthetic human genotypes, which, by standard protocols, one can straightforwardly expand into full-length, DNA-level genomes. The synthetic genotypes mimic real human genotypes without just reproducing known genotypes, in terms of approved metrics. When training biomedically relevant classifiers with synthetic genotypes, accuracy is near-identical to the accuracy achieved when training classifiers with real data. We further demonstrate that augmenting small amounts of real with synthetically generated genotype"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.03278","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CE","submitted_at":"2024-12-04T12:37:59Z","cross_cats_sorted":[],"title_canon_sha256":"725a4d69b5a6f3b138bb1e30de814ac60838a87e228f6d0eebb95dde8d91c143","abstract_canon_sha256":"8dad0272ddb595739123c1eb4e776ba05b646e66b1b584693eba93e3b5fee3de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:28.706069Z","signature_b64":"VXw+qan7RElFv3X34ff7dRGvXqy489inImdMSyPq27xVD2WKOGqQ/itJfey3gDcdM49F9uoGPUFB14VToVZ8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20164908b13a4c713b41d83d35c9f7c605d70e5790ceedbf6626f910efcd2748","last_reissued_at":"2026-07-05T10:07:28.705592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:28.705592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Synthetic Genotypes using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Alexander Sch\\\"onhuth, Barbara Hammer, Philip Kenneweg, Raghuram Dandinasivara, Xiao Luo","submitted_at":"2024-12-04T12:37:59Z","abstract_excerpt":"In this paper, we introduce the first diffusion model designed to generate complete synthetic human genotypes, which, by standard protocols, one can straightforwardly expand into full-length, DNA-level genomes. The synthetic genotypes mimic real human genotypes without just reproducing known genotypes, in terms of approved metrics. When training biomedically relevant classifiers with synthetic genotypes, accuracy is near-identical to the accuracy achieved when training classifiers with real data. We further demonstrate that augmenting small amounts of real with synthetically generated genotype"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03278","kind":"arxiv","version":3},"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/2412.03278/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.03278","created_at":"2026-07-05T10:07:28.705651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03278v3","created_at":"2026-07-05T10:07:28.705651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03278","created_at":"2026-07-05T10:07:28.705651+00:00"},{"alias_kind":"pith_short_12","alias_value":"EALESCFRHJGH","created_at":"2026-07-05T10:07:28.705651+00:00"},{"alias_kind":"pith_short_16","alias_value":"EALESCFRHJGHCO2B","created_at":"2026-07-05T10:07:28.705651+00:00"},{"alias_kind":"pith_short_8","alias_value":"EALESCFR","created_at":"2026-07-05T10:07:28.705651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY","json":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY.json","graph_json":"https://pith.science/api/pith-number/EALESCFRHJGHCO2B3A6TLSPXYY/graph.json","events_json":"https://pith.science/api/pith-number/EALESCFRHJGHCO2B3A6TLSPXYY/events.json","paper":"https://pith.science/paper/EALESCFR"},"agent_actions":{"view_html":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY","download_json":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY.json","view_paper":"https://pith.science/paper/EALESCFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03278&json=true","fetch_graph":"https://pith.science/api/pith-number/EALESCFRHJGHCO2B3A6TLSPXYY/graph.json","fetch_events":"https://pith.science/api/pith-number/EALESCFRHJGHCO2B3A6TLSPXYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY/action/storage_attestation","attest_author":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY/action/author_attestation","sign_citation":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY/action/citation_signature","submit_replication":"https://pith.science/pith/EALESCFRHJGHCO2B3A6TLSPXYY/action/replication_record"}},"created_at":"2026-07-05T10:07:28.705651+00:00","updated_at":"2026-07-05T10:07:28.705651+00:00"}