{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:RM3SEMKMVPA5IK6YUKKPEYKGGI","short_pith_number":"pith:RM3SEMKM","schema_version":"1.0","canonical_sha256":"8b3722314cabc1d42bd8a294f26146320d295420b59bdcc016a8da1add782a11","source":{"kind":"arxiv","id":"1410.1608","version":3},"attestation_state":"computed","paper":{"title":"Clustering pipeline for determining consensus sequences in targeted next-generation sequencing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Daniel Elleder, David R Hunter, Le Bao, Mary Poss, Raj Acharya, Raunaq Malhotra","submitted_at":"2014-10-07T03:50:26Z","abstract_excerpt":"Analyses of targeted genomic sequencing data from next-generation-sequencing (NGS) technologies typically involves mapping reads to a reference sequence or clustering reads. For a number of species a reference genome is not available so the analyses of targeted sequencing data, for example polymorphic structural variation caused by mobile elements is difficult; clustering methods are preferred for such data analysis. Clustering of reads requires a clustering threshold parameter, which is used to compare and group reads. However, determining the optimal clustering threshold for a read dataset 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":"1410.1608","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-10-07T03:50:26Z","cross_cats_sorted":[],"title_canon_sha256":"480a95b413fc2456ddad37e9088e6d43536063ce67d04c25d9ba51fd00d7257b","abstract_canon_sha256":"f9221f0607610e2c0159933eafc81d17f4ece5e6bc855e83bbe6ddc8ff0f6fbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:54.011471Z","signature_b64":"u6JKjTdrKIUrTH6mYOGeQjslXCBsqzpcoqdwoggtLuk6/NcYy9Uii+/IqOiOkUfxZDW0HhDJ1stCR9OYqs9zAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3722314cabc1d42bd8a294f26146320d295420b59bdcc016a8da1add782a11","last_reissued_at":"2026-05-18T01:20:54.010852Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:54.010852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering pipeline for determining consensus sequences in targeted next-generation sequencing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Daniel Elleder, David R Hunter, Le Bao, Mary Poss, Raj Acharya, Raunaq Malhotra","submitted_at":"2014-10-07T03:50:26Z","abstract_excerpt":"Analyses of targeted genomic sequencing data from next-generation-sequencing (NGS) technologies typically involves mapping reads to a reference sequence or clustering reads. For a number of species a reference genome is not available so the analyses of targeted sequencing data, for example polymorphic structural variation caused by mobile elements is difficult; clustering methods are preferred for such data analysis. Clustering of reads requires a clustering threshold parameter, which is used to compare and group reads. However, determining the optimal clustering threshold for a read dataset i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.1608","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":""},"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":"1410.1608","created_at":"2026-05-18T01:20:54.010948+00:00"},{"alias_kind":"arxiv_version","alias_value":"1410.1608v3","created_at":"2026-05-18T01:20:54.010948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.1608","created_at":"2026-05-18T01:20:54.010948+00:00"},{"alias_kind":"pith_short_12","alias_value":"RM3SEMKMVPA5","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"RM3SEMKMVPA5IK6Y","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"RM3SEMKM","created_at":"2026-05-18T12:28:46.137349+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/RM3SEMKMVPA5IK6YUKKPEYKGGI","json":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI.json","graph_json":"https://pith.science/api/pith-number/RM3SEMKMVPA5IK6YUKKPEYKGGI/graph.json","events_json":"https://pith.science/api/pith-number/RM3SEMKMVPA5IK6YUKKPEYKGGI/events.json","paper":"https://pith.science/paper/RM3SEMKM"},"agent_actions":{"view_html":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI","download_json":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI.json","view_paper":"https://pith.science/paper/RM3SEMKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1410.1608&json=true","fetch_graph":"https://pith.science/api/pith-number/RM3SEMKMVPA5IK6YUKKPEYKGGI/graph.json","fetch_events":"https://pith.science/api/pith-number/RM3SEMKMVPA5IK6YUKKPEYKGGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI/action/storage_attestation","attest_author":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI/action/author_attestation","sign_citation":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI/action/citation_signature","submit_replication":"https://pith.science/pith/RM3SEMKMVPA5IK6YUKKPEYKGGI/action/replication_record"}},"created_at":"2026-05-18T01:20:54.010948+00:00","updated_at":"2026-05-18T01:20:54.010948+00:00"}