{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:UMBTOHTL63YOKJPGZ3FXONHKBI","short_pith_number":"pith:UMBTOHTL","schema_version":"1.0","canonical_sha256":"a303371e6bf6f0e525e6cecb7734ea0a34741a9243accfa2c9eae393b07275a4","source":{"kind":"arxiv","id":"1004.0902","version":2},"attestation_state":"computed","paper":{"title":"On building minimal automaton for subset matching queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.IR"],"primary_cat":"cs.FL","authors_text":"Kimmo Fredriksson","submitted_at":"2010-04-06T17:20:03Z","abstract_excerpt":"We address the problem of building an index for a set $D$ of $n$ strings, where each string location is a subset of some finite integer alphabet of size $\\sigma$, so that we can answer efficiently if a given simple query string (where each string location is a single symbol) $p$ occurs in the set. That is, we need to efficiently find a string $d \\in D$ such that $p[i] \\in d[i]$ for every $i$. We show how to build such index in $O(n^{\\log_{\\sigma/\\Delta}(\\sigma)}\\log(n))$ average time, where $\\Delta$ is the average size of the subsets. Our methods have applications e.g.\\ in computational biolog"},"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":"1004.0902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2010-04-06T17:20:03Z","cross_cats_sorted":["cs.DS","cs.IR"],"title_canon_sha256":"29cd78381a54c8a99b7dab0962f0077ae7b834522b5c0211b1ce007917bfb9c0","abstract_canon_sha256":"135a2b1b7efd48479ee766ec153f5c863cea1944883f06337667d623fc4a2152"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:40:00.608381Z","signature_b64":"4/sEQN04CiGyfb/ALK5VIZQu3YbgasIb2EEqYaatWYeRP5n8Drx9Vv1ML3tjpiFp27bn3KSi3Z9L67SC+eIHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a303371e6bf6f0e525e6cecb7734ea0a34741a9243accfa2c9eae393b07275a4","last_reissued_at":"2026-05-18T04:40:00.607979Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:40:00.607979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On building minimal automaton for subset matching queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.IR"],"primary_cat":"cs.FL","authors_text":"Kimmo Fredriksson","submitted_at":"2010-04-06T17:20:03Z","abstract_excerpt":"We address the problem of building an index for a set $D$ of $n$ strings, where each string location is a subset of some finite integer alphabet of size $\\sigma$, so that we can answer efficiently if a given simple query string (where each string location is a single symbol) $p$ occurs in the set. That is, we need to efficiently find a string $d \\in D$ such that $p[i] \\in d[i]$ for every $i$. We show how to build such index in $O(n^{\\log_{\\sigma/\\Delta}(\\sigma)}\\log(n))$ average time, where $\\Delta$ is the average size of the subsets. Our methods have applications e.g.\\ in computational biolog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.0902","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":"1004.0902","created_at":"2026-05-18T04:40:00.608039+00:00"},{"alias_kind":"arxiv_version","alias_value":"1004.0902v2","created_at":"2026-05-18T04:40:00.608039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.0902","created_at":"2026-05-18T04:40:00.608039+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMBTOHTL63YO","created_at":"2026-05-18T12:26:15.391820+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMBTOHTL63YOKJPG","created_at":"2026-05-18T12:26:15.391820+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMBTOHTL","created_at":"2026-05-18T12:26:15.391820+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/UMBTOHTL63YOKJPGZ3FXONHKBI","json":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI.json","graph_json":"https://pith.science/api/pith-number/UMBTOHTL63YOKJPGZ3FXONHKBI/graph.json","events_json":"https://pith.science/api/pith-number/UMBTOHTL63YOKJPGZ3FXONHKBI/events.json","paper":"https://pith.science/paper/UMBTOHTL"},"agent_actions":{"view_html":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI","download_json":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI.json","view_paper":"https://pith.science/paper/UMBTOHTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1004.0902&json=true","fetch_graph":"https://pith.science/api/pith-number/UMBTOHTL63YOKJPGZ3FXONHKBI/graph.json","fetch_events":"https://pith.science/api/pith-number/UMBTOHTL63YOKJPGZ3FXONHKBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI/action/storage_attestation","attest_author":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI/action/author_attestation","sign_citation":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI/action/citation_signature","submit_replication":"https://pith.science/pith/UMBTOHTL63YOKJPGZ3FXONHKBI/action/replication_record"}},"created_at":"2026-05-18T04:40:00.608039+00:00","updated_at":"2026-05-18T04:40:00.608039+00:00"}