{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:BALK2ZJ4AWMGAH2T2LVTD7IDJM","short_pith_number":"pith:BALK2ZJ4","schema_version":"1.0","canonical_sha256":"0816ad653c0598601f53d2eb31fd034b1558c2b35df2655c317e7a074b681f6a","source":{"kind":"arxiv","id":"1108.0554","version":2},"attestation_state":"computed","paper":{"title":"Towards an Optimal Space-and-Query-Time Index for Top-k Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Rahul Shah, Sharma V. Thankachan, Wing-Kai Hon","submitted_at":"2011-08-02T12:00:02Z","abstract_excerpt":"Let $\\D = $$ \\{d_1,d_2,...d_D\\}$ be a given set of $D$ string documents of total length $n$, our task is to index $\\D$, such that the $k$ most relevant documents for an online query pattern $P$ of length $p$ can be retrieved efficiently. We propose an index of size $|CSA|+n\\log D(2+o(1))$ bits and $O(t_{s}(p)+k\\log\\log n+poly\\log\\log n)$ query time for the basic relevance metric \\emph{term-frequency}, where $|CSA|$ is the size (in bits) of a compressed full text index of $\\D$, with $O(t_s(p))$ time for searching a pattern of length $p$ . We further reduce the space to $|CSA|+n\\log D(1+o(1))$ b"},"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":"1108.0554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-08-02T12:00:02Z","cross_cats_sorted":[],"title_canon_sha256":"a75ea51f4d819e2e24e2a1838b504bbad0ba40e3fc081cd505762d2964d2f31f","abstract_canon_sha256":"9ab3f8de6e3a8e5a74398c159dcadc2ff20aa00e1e46a8044045f8f8849e75d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:58:51.296180Z","signature_b64":"1kPUzy2BYfXvO2Nskz/w8hdGtldV/m1k3a1GDKARF9wApnBBksWuDNi94/rSI67fCORpxUKcb4mqZtz1GJK3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0816ad653c0598601f53d2eb31fd034b1558c2b35df2655c317e7a074b681f6a","last_reissued_at":"2026-05-18T03:58:51.295568Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:58:51.295568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards an Optimal Space-and-Query-Time Index for Top-k Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Rahul Shah, Sharma V. Thankachan, Wing-Kai Hon","submitted_at":"2011-08-02T12:00:02Z","abstract_excerpt":"Let $\\D = $$ \\{d_1,d_2,...d_D\\}$ be a given set of $D$ string documents of total length $n$, our task is to index $\\D$, such that the $k$ most relevant documents for an online query pattern $P$ of length $p$ can be retrieved efficiently. We propose an index of size $|CSA|+n\\log D(2+o(1))$ bits and $O(t_{s}(p)+k\\log\\log n+poly\\log\\log n)$ query time for the basic relevance metric \\emph{term-frequency}, where $|CSA|$ is the size (in bits) of a compressed full text index of $\\D$, with $O(t_s(p))$ time for searching a pattern of length $p$ . We further reduce the space to $|CSA|+n\\log D(1+o(1))$ b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.0554","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":"1108.0554","created_at":"2026-05-18T03:58:51.295653+00:00"},{"alias_kind":"arxiv_version","alias_value":"1108.0554v2","created_at":"2026-05-18T03:58:51.295653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.0554","created_at":"2026-05-18T03:58:51.295653+00:00"},{"alias_kind":"pith_short_12","alias_value":"BALK2ZJ4AWMG","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BALK2ZJ4AWMGAH2T","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BALK2ZJ4","created_at":"2026-05-18T12:26:24.575870+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/BALK2ZJ4AWMGAH2T2LVTD7IDJM","json":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM.json","graph_json":"https://pith.science/api/pith-number/BALK2ZJ4AWMGAH2T2LVTD7IDJM/graph.json","events_json":"https://pith.science/api/pith-number/BALK2ZJ4AWMGAH2T2LVTD7IDJM/events.json","paper":"https://pith.science/paper/BALK2ZJ4"},"agent_actions":{"view_html":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM","download_json":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM.json","view_paper":"https://pith.science/paper/BALK2ZJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1108.0554&json=true","fetch_graph":"https://pith.science/api/pith-number/BALK2ZJ4AWMGAH2T2LVTD7IDJM/graph.json","fetch_events":"https://pith.science/api/pith-number/BALK2ZJ4AWMGAH2T2LVTD7IDJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM/action/storage_attestation","attest_author":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM/action/author_attestation","sign_citation":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM/action/citation_signature","submit_replication":"https://pith.science/pith/BALK2ZJ4AWMGAH2T2LVTD7IDJM/action/replication_record"}},"created_at":"2026-05-18T03:58:51.295653+00:00","updated_at":"2026-05-18T03:58:51.295653+00:00"}