{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SSAT73WNFAMZXPVATVMQRVJFXP","short_pith_number":"pith:SSAT73WN","schema_version":"1.0","canonical_sha256":"94813feecd28199bbea09d5908d525bbdccd74e85f6374f95d67f208ec4d8673","source":{"kind":"arxiv","id":"2004.02781","version":10},"attestation_state":"computed","paper":{"title":"Indexing Highly Repetitive String Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Gonzalo Navarro","submitted_at":"2020-04-06T16:16:26Z","abstract_excerpt":"Two decades ago, a breakthrough in indexing string collections made it possible to represent them within their compressed space while at the same time offering indexed search functionalities. As this new technology permeated through applications like bioinformatics, the string collections experienced a growth that outperforms Moore's Law and challenges our ability of handling them even in compressed form. It turns out, fortunately, that many of these rapidly growing string collections are highly repetitive, so that their information content is orders of magnitude lower than their plain size. T"},"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":"2004.02781","kind":"arxiv","version":10},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-04-06T16:16:26Z","cross_cats_sorted":[],"title_canon_sha256":"7a9fe35b10f6b4b4c58fd732311245745255d86fa657621433de72af16ee809a","abstract_canon_sha256":"143c1addbe3c6cd06428152b43ed488b69f71dd78a3261816896a21bb29735ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:59.820291Z","signature_b64":"HrT6W54LmdyIGOa9QzPJu5vR7WlBgi8yyFayUocglUnIUgdjl2v9Z1m6ttR6FWIFc7ls6R3KDoXnnLwt+dkMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94813feecd28199bbea09d5908d525bbdccd74e85f6374f95d67f208ec4d8673","last_reissued_at":"2026-07-05T05:18:59.819905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:59.819905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Indexing Highly Repetitive String Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Gonzalo Navarro","submitted_at":"2020-04-06T16:16:26Z","abstract_excerpt":"Two decades ago, a breakthrough in indexing string collections made it possible to represent them within their compressed space while at the same time offering indexed search functionalities. As this new technology permeated through applications like bioinformatics, the string collections experienced a growth that outperforms Moore's Law and challenges our ability of handling them even in compressed form. It turns out, fortunately, that many of these rapidly growing string collections are highly repetitive, so that their information content is orders of magnitude lower than their plain size. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02781","kind":"arxiv","version":10},"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/2004.02781/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":"2004.02781","created_at":"2026-07-05T05:18:59.819961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02781v10","created_at":"2026-07-05T05:18:59.819961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02781","created_at":"2026-07-05T05:18:59.819961+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSAT73WNFAMZ","created_at":"2026-07-05T05:18:59.819961+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSAT73WNFAMZXPVA","created_at":"2026-07-05T05:18:59.819961+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSAT73WN","created_at":"2026-07-05T05:18:59.819961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.05638","citing_title":"Smallest Suffixient Sets: Effectiveness, Resilience, and Calculation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04244","citing_title":"Faster Iterative $\\phi$ Queries on the Positional BWT","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP","json":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP.json","graph_json":"https://pith.science/api/pith-number/SSAT73WNFAMZXPVATVMQRVJFXP/graph.json","events_json":"https://pith.science/api/pith-number/SSAT73WNFAMZXPVATVMQRVJFXP/events.json","paper":"https://pith.science/paper/SSAT73WN"},"agent_actions":{"view_html":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP","download_json":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP.json","view_paper":"https://pith.science/paper/SSAT73WN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02781&json=true","fetch_graph":"https://pith.science/api/pith-number/SSAT73WNFAMZXPVATVMQRVJFXP/graph.json","fetch_events":"https://pith.science/api/pith-number/SSAT73WNFAMZXPVATVMQRVJFXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP/action/storage_attestation","attest_author":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP/action/author_attestation","sign_citation":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP/action/citation_signature","submit_replication":"https://pith.science/pith/SSAT73WNFAMZXPVATVMQRVJFXP/action/replication_record"}},"created_at":"2026-07-05T05:18:59.819961+00:00","updated_at":"2026-07-05T05:18:59.819961+00:00"}