{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:IOITODY3FCCELK7G3RWYIHZZJK","short_pith_number":"pith:IOITODY3","schema_version":"1.0","canonical_sha256":"4391370f1b288445abe6dc6d841f394a89929ed83fef4fd4bf18ffe965e3759d","source":{"kind":"arxiv","id":"1403.3414","version":1},"attestation_state":"computed","paper":{"title":"Predicting discovery rates of genomic features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","q-bio.PE","stat.TH"],"primary_cat":"q-bio.GN","authors_text":"NHLBI GO Exome Sequencing Project, Simon Gravel","submitted_at":"2014-03-13T20:05:45Z","abstract_excerpt":"Successful sequencing experiments require judicious sample selection. However, this selection must often be performed on the basis of limited preliminary data. Predicting the statistical properties of the final sample based on preliminary data can be challenging, because numerous uncertain model assumptions may be involved. Here, we ask whether we can predict ``omics\" variation across many samples by sequencing only a fraction of them. In the infinite-genome limit, we find that a pilot study sequencing $5\\%$ of a population is sufficient to predict the number of genetic variants in the entire "},"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":"1403.3414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-03-13T20:05:45Z","cross_cats_sorted":["math.ST","q-bio.PE","stat.TH"],"title_canon_sha256":"01a1e5a3517bbcd42922e1a5dd6c911d5433c165e077e6426b8aef777e76dccd","abstract_canon_sha256":"68fa5184defc6b39e7cbc662875b5bd68ee336890a300eb670b4eca7d465a989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:20.523498Z","signature_b64":"plv3wMBIAXugxf/PpUGI1uuDyMyeErzMikgQErcbvarkQ6103x8/6+kUBjidI2rp2kIXq/8Tc0c9izeP63AuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4391370f1b288445abe6dc6d841f394a89929ed83fef4fd4bf18ffe965e3759d","last_reissued_at":"2026-05-18T02:56:20.522819Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:20.522819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting discovery rates of genomic features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","q-bio.PE","stat.TH"],"primary_cat":"q-bio.GN","authors_text":"NHLBI GO Exome Sequencing Project, Simon Gravel","submitted_at":"2014-03-13T20:05:45Z","abstract_excerpt":"Successful sequencing experiments require judicious sample selection. However, this selection must often be performed on the basis of limited preliminary data. Predicting the statistical properties of the final sample based on preliminary data can be challenging, because numerous uncertain model assumptions may be involved. Here, we ask whether we can predict ``omics\" variation across many samples by sequencing only a fraction of them. In the infinite-genome limit, we find that a pilot study sequencing $5\\%$ of a population is sufficient to predict the number of genetic variants in the entire "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.3414","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":""},"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":"1403.3414","created_at":"2026-05-18T02:56:20.522919+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.3414v1","created_at":"2026-05-18T02:56:20.522919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.3414","created_at":"2026-05-18T02:56:20.522919+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOITODY3FCCE","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOITODY3FCCELK7G","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOITODY3","created_at":"2026-05-18T12:28:33.132498+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/IOITODY3FCCELK7G3RWYIHZZJK","json":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK.json","graph_json":"https://pith.science/api/pith-number/IOITODY3FCCELK7G3RWYIHZZJK/graph.json","events_json":"https://pith.science/api/pith-number/IOITODY3FCCELK7G3RWYIHZZJK/events.json","paper":"https://pith.science/paper/IOITODY3"},"agent_actions":{"view_html":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK","download_json":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK.json","view_paper":"https://pith.science/paper/IOITODY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.3414&json=true","fetch_graph":"https://pith.science/api/pith-number/IOITODY3FCCELK7G3RWYIHZZJK/graph.json","fetch_events":"https://pith.science/api/pith-number/IOITODY3FCCELK7G3RWYIHZZJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK/action/storage_attestation","attest_author":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK/action/author_attestation","sign_citation":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK/action/citation_signature","submit_replication":"https://pith.science/pith/IOITODY3FCCELK7G3RWYIHZZJK/action/replication_record"}},"created_at":"2026-05-18T02:56:20.522919+00:00","updated_at":"2026-05-18T02:56:20.522919+00:00"}