{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VYGLYHJGXW4PA2J5423DLEBJG6","short_pith_number":"pith:VYGLYHJG","schema_version":"1.0","canonical_sha256":"ae0cbc1d26bdb8f0693de6b6359029379e6ff91e9a558ae794960cf0e26baf3c","source":{"kind":"arxiv","id":"1811.06933","version":1},"attestation_state":"computed","paper":{"title":"Efficient Construction of a Complete Index for Pan-Genomics Read Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Alan Kuhnle, Ben Langmead, Christina Boucher, Giovanni Manzini, Taher Mun, Travis Gagie","submitted_at":"2018-11-16T17:33:22Z","abstract_excerpt":"While short read aligners, which predominantly use the FM-index, are able to easily index one or a few human genomes, they do not scale well to indexing databases containing thousands of genomes. To understand why, it helps to examine the main components of the FM-index in more detail, which is a rank data structure over the Burrows-Wheeler Transform (BWT) of the string that will allow us to find the interval in the string's suffix array (SA) containing pointers to starting positions of occurrences of a given pattern; second, a sample of the SA that --- when used with the rank data structure -"},"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":"1811.06933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-11-16T17:33:22Z","cross_cats_sorted":[],"title_canon_sha256":"17d2f5224c611e8476ff889c7948674254df36518335355f9c637f713dafb64e","abstract_canon_sha256":"7cbe37739d86c11ec35c8141f4849cca6fdcefa06da1b7bd5e1649c294a70c32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:33.417999Z","signature_b64":"Kjf74kOFd0eXkFseHuKxTswDUMkP6LlJsb/R8kS15odO/dUHXC5vsYBJP4IKMiBLFnH70GtLsrVYEP3FOuapDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae0cbc1d26bdb8f0693de6b6359029379e6ff91e9a558ae794960cf0e26baf3c","last_reissued_at":"2026-05-18T00:00:33.417550Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:33.417550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Construction of a Complete Index for Pan-Genomics Read Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Alan Kuhnle, Ben Langmead, Christina Boucher, Giovanni Manzini, Taher Mun, Travis Gagie","submitted_at":"2018-11-16T17:33:22Z","abstract_excerpt":"While short read aligners, which predominantly use the FM-index, are able to easily index one or a few human genomes, they do not scale well to indexing databases containing thousands of genomes. To understand why, it helps to examine the main components of the FM-index in more detail, which is a rank data structure over the Burrows-Wheeler Transform (BWT) of the string that will allow us to find the interval in the string's suffix array (SA) containing pointers to starting positions of occurrences of a given pattern; second, a sample of the SA that --- when used with the rank data structure -"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06933","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":"1811.06933","created_at":"2026-05-18T00:00:33.417630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.06933v1","created_at":"2026-05-18T00:00:33.417630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06933","created_at":"2026-05-18T00:00:33.417630+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYGLYHJGXW4P","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYGLYHJGXW4PA2J5","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYGLYHJG","created_at":"2026-05-18T12:32:59.047623+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/VYGLYHJGXW4PA2J5423DLEBJG6","json":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6.json","graph_json":"https://pith.science/api/pith-number/VYGLYHJGXW4PA2J5423DLEBJG6/graph.json","events_json":"https://pith.science/api/pith-number/VYGLYHJGXW4PA2J5423DLEBJG6/events.json","paper":"https://pith.science/paper/VYGLYHJG"},"agent_actions":{"view_html":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6","download_json":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6.json","view_paper":"https://pith.science/paper/VYGLYHJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.06933&json=true","fetch_graph":"https://pith.science/api/pith-number/VYGLYHJGXW4PA2J5423DLEBJG6/graph.json","fetch_events":"https://pith.science/api/pith-number/VYGLYHJGXW4PA2J5423DLEBJG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6/action/storage_attestation","attest_author":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6/action/author_attestation","sign_citation":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6/action/citation_signature","submit_replication":"https://pith.science/pith/VYGLYHJGXW4PA2J5423DLEBJG6/action/replication_record"}},"created_at":"2026-05-18T00:00:33.417630+00:00","updated_at":"2026-05-18T00:00:33.417630+00:00"}