{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QWK6C7SSI6VOOAPMXVR4ZGYKRN","short_pith_number":"pith:QWK6C7SS","schema_version":"1.0","canonical_sha256":"8595e17e5247aae701ecbd63cc9b0a8b74291c40e736beafa2037d75801de63a","source":{"kind":"arxiv","id":"2403.02154","version":1},"attestation_state":"computed","paper":{"title":"Double trouble: Predicting new variant counts across two heterogeneous populations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"stat.ME","authors_text":"Joshua G. Schraiber, Lorenzo Masoero, Tamara Broderick, Yunyi Shen","submitted_at":"2024-03-04T16:03:21Z","abstract_excerpt":"Collecting genomics data across multiple heterogeneous populations (e.g., across different cancer types) has the potential to improve our understanding of disease. Despite sequencing advances, though, resources often remain a constraint when gathering data. So it would be useful for experimental design if experimenters with access to a pilot study could predict the number of new variants they might expect to find in a follow-up study: both the number of new variants shared between the populations and the total across the populations. While many authors have developed prediction methods for the"},"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":"2403.02154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2024-03-04T16:03:21Z","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"title_canon_sha256":"3c4b7276e6f06639d2362a3a1336b73e2fb0ed1a087e089b2e048eb0140bb768","abstract_canon_sha256":"3036fc844c81392d5512af9ced23063f62fde77c06866386b206d5c9df957b3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:57.163146Z","signature_b64":"bu/xUnC3/iXE8zLT2YENIw6/BhmulzN6NIRBV9k0GDxWioDPxORadxqITRVMIp6bBDU3TbHnmOIIknbH59NcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8595e17e5247aae701ecbd63cc9b0a8b74291c40e736beafa2037d75801de63a","last_reissued_at":"2026-07-05T07:51:57.162731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:57.162731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Double trouble: Predicting new variant counts across two heterogeneous populations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"stat.ME","authors_text":"Joshua G. Schraiber, Lorenzo Masoero, Tamara Broderick, Yunyi Shen","submitted_at":"2024-03-04T16:03:21Z","abstract_excerpt":"Collecting genomics data across multiple heterogeneous populations (e.g., across different cancer types) has the potential to improve our understanding of disease. Despite sequencing advances, though, resources often remain a constraint when gathering data. So it would be useful for experimental design if experimenters with access to a pilot study could predict the number of new variants they might expect to find in a follow-up study: both the number of new variants shared between the populations and the total across the populations. While many authors have developed prediction methods for the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02154","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/2403.02154/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":"2403.02154","created_at":"2026-07-05T07:51:57.162795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02154v1","created_at":"2026-07-05T07:51:57.162795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02154","created_at":"2026-07-05T07:51:57.162795+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWK6C7SSI6VO","created_at":"2026-07-05T07:51:57.162795+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWK6C7SSI6VOOAPM","created_at":"2026-07-05T07:51:57.162795+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWK6C7SS","created_at":"2026-07-05T07:51:57.162795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08992","citing_title":"When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN","json":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN.json","graph_json":"https://pith.science/api/pith-number/QWK6C7SSI6VOOAPMXVR4ZGYKRN/graph.json","events_json":"https://pith.science/api/pith-number/QWK6C7SSI6VOOAPMXVR4ZGYKRN/events.json","paper":"https://pith.science/paper/QWK6C7SS"},"agent_actions":{"view_html":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN","download_json":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN.json","view_paper":"https://pith.science/paper/QWK6C7SS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02154&json=true","fetch_graph":"https://pith.science/api/pith-number/QWK6C7SSI6VOOAPMXVR4ZGYKRN/graph.json","fetch_events":"https://pith.science/api/pith-number/QWK6C7SSI6VOOAPMXVR4ZGYKRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN/action/storage_attestation","attest_author":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN/action/author_attestation","sign_citation":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN/action/citation_signature","submit_replication":"https://pith.science/pith/QWK6C7SSI6VOOAPMXVR4ZGYKRN/action/replication_record"}},"created_at":"2026-07-05T07:51:57.162795+00:00","updated_at":"2026-07-05T07:51:57.162795+00:00"}