{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WLQWGTK6VB7RLVZ4YTCMXJ5TWC","short_pith_number":"pith:WLQWGTK6","schema_version":"1.0","canonical_sha256":"b2e1634d5ea87f15d73cc4c4cba7b3b09fd618309c7062059470d7cd1a0ae01f","source":{"kind":"arxiv","id":"2506.03294","version":2},"attestation_state":"computed","paper":{"title":"Prefix-free parsing for merging big BWTs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Ben Langmead, Diego Diaz-Dominguez, Francesco Masillo, Giovanni Manzini, Travis Gagie, Veronica Guerrini, Vikram Shivakumar, Zsuzsanna Liptak","submitted_at":"2025-06-03T18:34:01Z","abstract_excerpt":"When building Burrows-Wheeler Transforms (BWTs) of truly huge datasets, prefix-free parsing (PFP) can use an unreasonable amount of memory. In this paper we show how if a dataset can be broken down into small datasets that are not very similar to each other -- such as collections of many copies of genomes of each of several species, or collections of many copies of each of the human chromosomes -- then we can drastically reduce PFP's memory footprint by building the BWTs of the small datasets and then merging them into the BWT of the whole dataset."},"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":"2506.03294","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2025-06-03T18:34:01Z","cross_cats_sorted":[],"title_canon_sha256":"a7d34f7aced22bc617c732f04729f683fcd2a9ba2c3f7b0bde633826e0605bfe","abstract_canon_sha256":"903e65f70a4e63015b1124eb5ea725d201b0e52dbfd21483328e4cc4fef41030"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:00.257527Z","signature_b64":"5OQ9IHeNF7RffApCRA1IRHQXiEKLHH1HfEoOfLWpAXC5wljhe3yr3djpErHRp4iBBBf+EyuMXzexBdGY4ofhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2e1634d5ea87f15d73cc4c4cba7b3b09fd618309c7062059470d7cd1a0ae01f","last_reissued_at":"2026-07-05T11:17:00.256965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:00.256965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prefix-free parsing for merging big BWTs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Ben Langmead, Diego Diaz-Dominguez, Francesco Masillo, Giovanni Manzini, Travis Gagie, Veronica Guerrini, Vikram Shivakumar, Zsuzsanna Liptak","submitted_at":"2025-06-03T18:34:01Z","abstract_excerpt":"When building Burrows-Wheeler Transforms (BWTs) of truly huge datasets, prefix-free parsing (PFP) can use an unreasonable amount of memory. In this paper we show how if a dataset can be broken down into small datasets that are not very similar to each other -- such as collections of many copies of genomes of each of several species, or collections of many copies of each of the human chromosomes -- then we can drastically reduce PFP's memory footprint by building the BWTs of the small datasets and then merging them into the BWT of the whole dataset."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03294","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.03294/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2506.03294","created_at":"2026-07-05T11:17:00.257023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03294v2","created_at":"2026-07-05T11:17:00.257023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03294","created_at":"2026-07-05T11:17:00.257023+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLQWGTK6VB7R","created_at":"2026-07-05T11:17:00.257023+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLQWGTK6VB7RLVZ4","created_at":"2026-07-05T11:17:00.257023+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLQWGTK6","created_at":"2026-07-05T11:17:00.257023+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/WLQWGTK6VB7RLVZ4YTCMXJ5TWC","json":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC.json","graph_json":"https://pith.science/api/pith-number/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/graph.json","events_json":"https://pith.science/api/pith-number/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/events.json","paper":"https://pith.science/paper/WLQWGTK6"},"agent_actions":{"view_html":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC","download_json":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC.json","view_paper":"https://pith.science/paper/WLQWGTK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03294&json=true","fetch_graph":"https://pith.science/api/pith-number/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/graph.json","fetch_events":"https://pith.science/api/pith-number/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/action/storage_attestation","attest_author":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/action/author_attestation","sign_citation":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/action/citation_signature","submit_replication":"https://pith.science/pith/WLQWGTK6VB7RLVZ4YTCMXJ5TWC/action/replication_record"}},"created_at":"2026-07-05T11:17:00.257023+00:00","updated_at":"2026-07-05T11:17:00.257023+00:00"}