{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:OD5H76V32JJEKIDISKO4PREJBY","short_pith_number":"pith:OD5H76V3","schema_version":"1.0","canonical_sha256":"70fa7ffabbd252452068929dc7c4890e0395cf0556cb858fa54902b7e3a09440","source":{"kind":"arxiv","id":"1103.3114","version":2},"attestation_state":"computed","paper":{"title":"Fast $q$-gram Mining on SLP Compressed Strings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Hideo Bannai, Keisuke Goto, Masayuki Takeda, Shunsuke Inenaga","submitted_at":"2011-03-16T07:16:10Z","abstract_excerpt":"We present simple and efficient algorithms for calculating $q$-gram frequencies on strings represented in compressed form, namely, as a straight line program (SLP). Given an SLP of size $n$ that represents string $T$, we present an $O(qn)$ time and space algorithm that computes the occurrence frequencies of $q$-grams in $T$. Computational experiments show that our algorithm and its variation are practical for small $q$, actually running faster on various real string data, compared to algorithms that work on the uncompressed text. We also discuss applications in data mining and classification o"},"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":"1103.3114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-03-16T07:16:10Z","cross_cats_sorted":[],"title_canon_sha256":"abefabe9d71c26304e011307235fd768eae39e33988133eb7bbe51196707e229","abstract_canon_sha256":"ceffcfa804f9861f8fd74d01b58aa04486c2f52f9c544f55b4db9832b9d0fef7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:18:23.254206Z","signature_b64":"DoZeAwh7gUaO11bBdCgnowjafbNATwna+7eoN9BA1MT2Ilj1q+jY45Isy1gA5s+HKDCi7ZyyAfgaWgCdoitkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70fa7ffabbd252452068929dc7c4890e0395cf0556cb858fa54902b7e3a09440","last_reissued_at":"2026-05-18T04:18:23.253687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:18:23.253687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast $q$-gram Mining on SLP Compressed Strings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Hideo Bannai, Keisuke Goto, Masayuki Takeda, Shunsuke Inenaga","submitted_at":"2011-03-16T07:16:10Z","abstract_excerpt":"We present simple and efficient algorithms for calculating $q$-gram frequencies on strings represented in compressed form, namely, as a straight line program (SLP). Given an SLP of size $n$ that represents string $T$, we present an $O(qn)$ time and space algorithm that computes the occurrence frequencies of $q$-grams in $T$. Computational experiments show that our algorithm and its variation are practical for small $q$, actually running faster on various real string data, compared to algorithms that work on the uncompressed text. We also discuss applications in data mining and classification o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1103.3114","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":"1103.3114","created_at":"2026-05-18T04:18:23.253772+00:00"},{"alias_kind":"arxiv_version","alias_value":"1103.3114v2","created_at":"2026-05-18T04:18:23.253772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1103.3114","created_at":"2026-05-18T04:18:23.253772+00:00"},{"alias_kind":"pith_short_12","alias_value":"OD5H76V32JJE","created_at":"2026-05-18T12:26:37.096874+00:00"},{"alias_kind":"pith_short_16","alias_value":"OD5H76V32JJEKIDI","created_at":"2026-05-18T12:26:37.096874+00:00"},{"alias_kind":"pith_short_8","alias_value":"OD5H76V3","created_at":"2026-05-18T12:26:37.096874+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/OD5H76V32JJEKIDISKO4PREJBY","json":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY.json","graph_json":"https://pith.science/api/pith-number/OD5H76V32JJEKIDISKO4PREJBY/graph.json","events_json":"https://pith.science/api/pith-number/OD5H76V32JJEKIDISKO4PREJBY/events.json","paper":"https://pith.science/paper/OD5H76V3"},"agent_actions":{"view_html":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY","download_json":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY.json","view_paper":"https://pith.science/paper/OD5H76V3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1103.3114&json=true","fetch_graph":"https://pith.science/api/pith-number/OD5H76V32JJEKIDISKO4PREJBY/graph.json","fetch_events":"https://pith.science/api/pith-number/OD5H76V32JJEKIDISKO4PREJBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY/action/storage_attestation","attest_author":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY/action/author_attestation","sign_citation":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY/action/citation_signature","submit_replication":"https://pith.science/pith/OD5H76V32JJEKIDISKO4PREJBY/action/replication_record"}},"created_at":"2026-05-18T04:18:23.253772+00:00","updated_at":"2026-05-18T04:18:23.253772+00:00"}