{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:Y5IIPTPPGOWLFY5E72HVLLPEHT","short_pith_number":"pith:Y5IIPTPP","schema_version":"1.0","canonical_sha256":"c75087cdef33acb2e3a4fe8f55ade43cfa1f22d37eabdeac01f351fdcb5c0094","source":{"kind":"arxiv","id":"1207.2632","version":2},"attestation_state":"computed","paper":{"title":"On Optimal Top-K String Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Cheng Sheng, Jeffrey Scott Vitter, Rahul Shah, Sharma V. Thankachan","submitted_at":"2012-07-11T13:30:06Z","abstract_excerpt":"Let ${\\cal{D}}$ = $\\{d_1, d_2, d_3, ..., d_D\\}$ be a given set of $D$ (string) documents of total length $n$. The top-$k$ document retrieval problem is to index $\\cal{D}$ such that when a pattern $P$ of length $p$, and a parameter $k$ come as a query, the index returns the $k$ most relevant documents to the pattern $P$. Hon et. al. \\cite{HSV09} gave the first linear space framework to solve this problem in $O(p + k\\log k)$ time. This was improved by Navarro and Nekrich \\cite{NN12} to $O(p + k)$. These results are powerful enough to support arbitrary relevance functions like frequency, proximit"},"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":"1207.2632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2012-07-11T13:30:06Z","cross_cats_sorted":[],"title_canon_sha256":"5b7d8794a12c295d00a68e1add9c09b09ef90f90b07ea4946925965b03e4e3f5","abstract_canon_sha256":"72b9982d893ae492871a52e332fff0e18492e6d3d61c5f162c0597f1a5d7c2ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:40:36.071594Z","signature_b64":"bQfXBBQivniBbKLGPgp8cA+8ZZecbclb2OBLg3iutvxr/CeA65LJECv14N2Cj6fm/j7sYjMJOyzjo1N9DJmrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c75087cdef33acb2e3a4fe8f55ade43cfa1f22d37eabdeac01f351fdcb5c0094","last_reissued_at":"2026-05-18T03:40:36.070718Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:40:36.070718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Optimal Top-K String Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Cheng Sheng, Jeffrey Scott Vitter, Rahul Shah, Sharma V. Thankachan","submitted_at":"2012-07-11T13:30:06Z","abstract_excerpt":"Let ${\\cal{D}}$ = $\\{d_1, d_2, d_3, ..., d_D\\}$ be a given set of $D$ (string) documents of total length $n$. The top-$k$ document retrieval problem is to index $\\cal{D}$ such that when a pattern $P$ of length $p$, and a parameter $k$ come as a query, the index returns the $k$ most relevant documents to the pattern $P$. Hon et. al. \\cite{HSV09} gave the first linear space framework to solve this problem in $O(p + k\\log k)$ time. This was improved by Navarro and Nekrich \\cite{NN12} to $O(p + k)$. These results are powerful enough to support arbitrary relevance functions like frequency, proximit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.2632","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":"1207.2632","created_at":"2026-05-18T03:40:36.070879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.2632v2","created_at":"2026-05-18T03:40:36.070879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.2632","created_at":"2026-05-18T03:40:36.070879+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5IIPTPPGOWL","created_at":"2026-05-18T12:27:27.928770+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5IIPTPPGOWLFY5E","created_at":"2026-05-18T12:27:27.928770+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5IIPTPP","created_at":"2026-05-18T12:27:27.928770+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/Y5IIPTPPGOWLFY5E72HVLLPEHT","json":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT.json","graph_json":"https://pith.science/api/pith-number/Y5IIPTPPGOWLFY5E72HVLLPEHT/graph.json","events_json":"https://pith.science/api/pith-number/Y5IIPTPPGOWLFY5E72HVLLPEHT/events.json","paper":"https://pith.science/paper/Y5IIPTPP"},"agent_actions":{"view_html":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT","download_json":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT.json","view_paper":"https://pith.science/paper/Y5IIPTPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.2632&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5IIPTPPGOWLFY5E72HVLLPEHT/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5IIPTPPGOWLFY5E72HVLLPEHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT/action/storage_attestation","attest_author":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT/action/author_attestation","sign_citation":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT/action/citation_signature","submit_replication":"https://pith.science/pith/Y5IIPTPPGOWLFY5E72HVLLPEHT/action/replication_record"}},"created_at":"2026-05-18T03:40:36.070879+00:00","updated_at":"2026-05-18T03:40:36.070879+00:00"}