{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WVAHSEHL7L5XY7UVPD76TSTU6T","short_pith_number":"pith:WVAHSEHL","schema_version":"1.0","canonical_sha256":"b5407910ebfafb7c7e9578ffe9ca74f4d518ee606461aa366c033c2d8e9d3683","source":{"kind":"arxiv","id":"1706.02380","version":4},"attestation_state":"computed","paper":{"title":"Multi-sample Estimation of Bacterial Composition Matrix in Metagenomics Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"stat.ME","authors_text":"Anru Zhang, Hongzhe Li, Yuanpei Cao","submitted_at":"2017-06-07T21:05:26Z","abstract_excerpt":"Metagenomics sequencing is routinely applied to quantify bacterial abundances in microbiome studies, where the bacterial composition is estimated based on the sequencing read counts. Due to limited sequencing depth and DNA dropouts, many rare bacterial taxa might not be captured in the final sequencing reads, which results in many zero counts. Naive composition estimation using count normalization leads to many zero proportions, which tend to result in inaccurate estimates of bacterial abundance and diversity. This paper takes a multi-sample approach to the estimation of bacterial abundances i"},"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":"1706.02380","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ME","submitted_at":"2017-06-07T21:05:26Z","cross_cats_sorted":["stat.AP","stat.CO"],"title_canon_sha256":"205e4aef00249f34f12525b0abd0ecb938d645d990f890be902859a39953073f","abstract_canon_sha256":"9fccdbad5a33903af8ba71b09262ebb50488d269ae87f5f30d671aebf4fbb294"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:49.288967Z","signature_b64":"30IgGJE2doejeEa4MBUAsq9NsC4Zy7fi0a3Sl6YWIFGmso1Ma7hdot2j+AiadJMsqlMaWq8fXQXO4m7xwSbrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5407910ebfafb7c7e9578ffe9ca74f4d518ee606461aa366c033c2d8e9d3683","last_reissued_at":"2026-05-17T23:47:49.288139Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:49.288139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-sample Estimation of Bacterial Composition Matrix in Metagenomics Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"stat.ME","authors_text":"Anru Zhang, Hongzhe Li, Yuanpei Cao","submitted_at":"2017-06-07T21:05:26Z","abstract_excerpt":"Metagenomics sequencing is routinely applied to quantify bacterial abundances in microbiome studies, where the bacterial composition is estimated based on the sequencing read counts. Due to limited sequencing depth and DNA dropouts, many rare bacterial taxa might not be captured in the final sequencing reads, which results in many zero counts. Naive composition estimation using count normalization leads to many zero proportions, which tend to result in inaccurate estimates of bacterial abundance and diversity. This paper takes a multi-sample approach to the estimation of bacterial abundances i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02380","kind":"arxiv","version":4},"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":"1706.02380","created_at":"2026-05-17T23:47:49.288280+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.02380v4","created_at":"2026-05-17T23:47:49.288280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02380","created_at":"2026-05-17T23:47:49.288280+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVAHSEHL7L5X","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVAHSEHL7L5XY7UV","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVAHSEHL","created_at":"2026-05-18T12:31:53.515858+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/WVAHSEHL7L5XY7UVPD76TSTU6T","json":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T.json","graph_json":"https://pith.science/api/pith-number/WVAHSEHL7L5XY7UVPD76TSTU6T/graph.json","events_json":"https://pith.science/api/pith-number/WVAHSEHL7L5XY7UVPD76TSTU6T/events.json","paper":"https://pith.science/paper/WVAHSEHL"},"agent_actions":{"view_html":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T","download_json":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T.json","view_paper":"https://pith.science/paper/WVAHSEHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.02380&json=true","fetch_graph":"https://pith.science/api/pith-number/WVAHSEHL7L5XY7UVPD76TSTU6T/graph.json","fetch_events":"https://pith.science/api/pith-number/WVAHSEHL7L5XY7UVPD76TSTU6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T/action/storage_attestation","attest_author":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T/action/author_attestation","sign_citation":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T/action/citation_signature","submit_replication":"https://pith.science/pith/WVAHSEHL7L5XY7UVPD76TSTU6T/action/replication_record"}},"created_at":"2026-05-17T23:47:49.288280+00:00","updated_at":"2026-05-17T23:47:49.288280+00:00"}