{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:2JKB2CFX5JO6TNJ2JVIQJKSOT7","short_pith_number":"pith:2JKB2CFX","schema_version":"1.0","canonical_sha256":"d2541d08b7ea5de9b53a4d5104aa4e9fee2a45bd790ace00ad74ebf7e90075da","source":{"kind":"arxiv","id":"1111.1355","version":1},"attestation_state":"computed","paper":{"title":"A Compressed Self-Index for Genomic Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Juha K\\\"arkk\\\"ainen, Simon J. Puglisi, Travis Gagie, Yakov Nekrich","submitted_at":"2011-11-05T21:53:33Z","abstract_excerpt":"Advances in DNA sequencing technology will soon result in databases of thousands of genomes. Within a species, individuals' genomes are almost exact copies of each other; e.g., any two human genomes are 99.9% the same. Relative Lempel-Ziv (RLZ) compression takes advantage of this property: it stores the first genome uncompressed or as an FM-index, then compresses the other genomes with a variant of LZ77 that copies phrases only from the first genome. RLZ achieves good compression and supports fast random access; in this paper we show how to support fast search as well, thus obtaining an effici"},"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":"1111.1355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-11-05T21:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"96671ff86526d0c3af97eda1cf3eb31578a20066ca4f579c064b1407296d8b9f","abstract_canon_sha256":"6c506caf68a53f988e6fb4a406908c721e90cc2cc9a33b01ea92af0cdeb99720"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:09:26.402225Z","signature_b64":"IoXtKPQyaGObWDoP+OC/reIdwA1eImg8qIXAKwDCvpnfkuzrExh+osMRez1TyXsi6ky27Jt6ntSZzC9aCMv1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2541d08b7ea5de9b53a4d5104aa4e9fee2a45bd790ace00ad74ebf7e90075da","last_reissued_at":"2026-05-18T04:09:26.401753Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:09:26.401753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Compressed Self-Index for Genomic Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Juha K\\\"arkk\\\"ainen, Simon J. Puglisi, Travis Gagie, Yakov Nekrich","submitted_at":"2011-11-05T21:53:33Z","abstract_excerpt":"Advances in DNA sequencing technology will soon result in databases of thousands of genomes. Within a species, individuals' genomes are almost exact copies of each other; e.g., any two human genomes are 99.9% the same. Relative Lempel-Ziv (RLZ) compression takes advantage of this property: it stores the first genome uncompressed or as an FM-index, then compresses the other genomes with a variant of LZ77 that copies phrases only from the first genome. RLZ achieves good compression and supports fast random access; in this paper we show how to support fast search as well, thus obtaining an effici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1111.1355","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":"1111.1355","created_at":"2026-05-18T04:09:26.401824+00:00"},{"alias_kind":"arxiv_version","alias_value":"1111.1355v1","created_at":"2026-05-18T04:09:26.401824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1111.1355","created_at":"2026-05-18T04:09:26.401824+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JKB2CFX5JO6","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JKB2CFX5JO6TNJ2","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JKB2CFX","created_at":"2026-05-18T12:26:18.847500+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/2JKB2CFX5JO6TNJ2JVIQJKSOT7","json":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7.json","graph_json":"https://pith.science/api/pith-number/2JKB2CFX5JO6TNJ2JVIQJKSOT7/graph.json","events_json":"https://pith.science/api/pith-number/2JKB2CFX5JO6TNJ2JVIQJKSOT7/events.json","paper":"https://pith.science/paper/2JKB2CFX"},"agent_actions":{"view_html":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7","download_json":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7.json","view_paper":"https://pith.science/paper/2JKB2CFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1111.1355&json=true","fetch_graph":"https://pith.science/api/pith-number/2JKB2CFX5JO6TNJ2JVIQJKSOT7/graph.json","fetch_events":"https://pith.science/api/pith-number/2JKB2CFX5JO6TNJ2JVIQJKSOT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7/action/storage_attestation","attest_author":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7/action/author_attestation","sign_citation":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7/action/citation_signature","submit_replication":"https://pith.science/pith/2JKB2CFX5JO6TNJ2JVIQJKSOT7/action/replication_record"}},"created_at":"2026-05-18T04:09:26.401824+00:00","updated_at":"2026-05-18T04:09:26.401824+00:00"}