{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:U2HMLJEHAFILQVSN522XFVUUTL","short_pith_number":"pith:U2HMLJEH","schema_version":"1.0","canonical_sha256":"a68ec5a4870150b8564deeb572d6949ad958c94ca3f5167d8995316765b74e06","source":{"kind":"arxiv","id":"1205.0192","version":2},"attestation_state":"computed","paper":{"title":"Large-scale compression of genomic sequence databases with the Burrows-Wheeler transform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.DS","authors_text":"Anthony J. Cox, Giovanna Rosone, Markus J. Bauer, Tobias Jakobi","submitted_at":"2012-05-01T15:39:50Z","abstract_excerpt":"Motivation\n  The Burrows-Wheeler transform (BWT) is the foundation of many algorithms for compression and indexing of text data, but the cost of computing the BWT of very large string collections has prevented these techniques from being widely applied to the large sets of sequences often encountered as the outcome of DNA sequencing experiments. In previous work, we presented a novel algorithm that allows the BWT of human genome scale data to be computed on very moderate hardware, thus enabling us to investigate the BWT as a tool for the compression of such datasets.\n  Results\n  We first used "},"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":"1205.0192","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2012-05-01T15:39:50Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"e138c5a7c6c876059f66836551b4846531a2cb89dcc4661d6468ee543d611eac","abstract_canon_sha256":"52fe7048c1b382a53f2665a5a86177877ee36ab559cbd69aa75def65db39bc94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:15.814260Z","signature_b64":"sw5SDY/N+NSg5Q/W0ztkczo4Lf+xe13te/kgVrmlwk2U60JTqFTaFjHsN70UQya/+MgWZHD0Hz9pC++ExiWsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a68ec5a4870150b8564deeb572d6949ad958c94ca3f5167d8995316765b74e06","last_reissued_at":"2026-05-18T02:21:15.813658Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:15.813658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-scale compression of genomic sequence databases with the Burrows-Wheeler transform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.DS","authors_text":"Anthony J. Cox, Giovanna Rosone, Markus J. Bauer, Tobias Jakobi","submitted_at":"2012-05-01T15:39:50Z","abstract_excerpt":"Motivation\n  The Burrows-Wheeler transform (BWT) is the foundation of many algorithms for compression and indexing of text data, but the cost of computing the BWT of very large string collections has prevented these techniques from being widely applied to the large sets of sequences often encountered as the outcome of DNA sequencing experiments. In previous work, we presented a novel algorithm that allows the BWT of human genome scale data to be computed on very moderate hardware, thus enabling us to investigate the BWT as a tool for the compression of such datasets.\n  Results\n  We first used "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.0192","kind":"arxiv","version":2},"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":"1205.0192","created_at":"2026-05-18T02:21:15.813742+00:00"},{"alias_kind":"arxiv_version","alias_value":"1205.0192v2","created_at":"2026-05-18T02:21:15.813742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.0192","created_at":"2026-05-18T02:21:15.813742+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2HMLJEHAFIL","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2HMLJEHAFILQVSN","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2HMLJEH","created_at":"2026-05-18T12:27:23.164592+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/U2HMLJEHAFILQVSN522XFVUUTL","json":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL.json","graph_json":"https://pith.science/api/pith-number/U2HMLJEHAFILQVSN522XFVUUTL/graph.json","events_json":"https://pith.science/api/pith-number/U2HMLJEHAFILQVSN522XFVUUTL/events.json","paper":"https://pith.science/paper/U2HMLJEH"},"agent_actions":{"view_html":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL","download_json":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL.json","view_paper":"https://pith.science/paper/U2HMLJEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1205.0192&json=true","fetch_graph":"https://pith.science/api/pith-number/U2HMLJEHAFILQVSN522XFVUUTL/graph.json","fetch_events":"https://pith.science/api/pith-number/U2HMLJEHAFILQVSN522XFVUUTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL/action/storage_attestation","attest_author":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL/action/author_attestation","sign_citation":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL/action/citation_signature","submit_replication":"https://pith.science/pith/U2HMLJEHAFILQVSN522XFVUUTL/action/replication_record"}},"created_at":"2026-05-18T02:21:15.813742+00:00","updated_at":"2026-05-18T02:21:15.813742+00:00"}