{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:OD5H76V32JJEKIDISKO4PREJBY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ceffcfa804f9861f8fd74d01b58aa04486c2f52f9c544f55b4db9832b9d0fef7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-03-16T07:16:10Z","title_canon_sha256":"abefabe9d71c26304e011307235fd768eae39e33988133eb7bbe51196707e229"},"schema_version":"1.0","source":{"id":"1103.3114","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1103.3114","created_at":"2026-05-18T04:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"1103.3114v2","created_at":"2026-05-18T04:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1103.3114","created_at":"2026-05-18T04:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"OD5H76V32JJE","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"OD5H76V32JJEKIDI","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"OD5H76V3","created_at":"2026-05-18T12:26:37Z"}],"graph_snapshots":[{"event_id":"sha256:bea49b15f54d5209d7ecd44d783e0f2a7dcbc41e104c65bb555e67e6610d8cf2","target":"graph","created_at":"2026-05-18T04:18:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Hideo Bannai, Keisuke Goto, Masayuki Takeda, Shunsuke Inenaga","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-03-16T07:16:10Z","title":"Fast $q$-gram Mining on SLP Compressed Strings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1103.3114","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6f805ae1a1b7f432cffff6d503364e166a8fbce101c1710276463b71449fe985","target":"record","created_at":"2026-05-18T04:18:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ceffcfa804f9861f8fd74d01b58aa04486c2f52f9c544f55b4db9832b9d0fef7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2011-03-16T07:16:10Z","title_canon_sha256":"abefabe9d71c26304e011307235fd768eae39e33988133eb7bbe51196707e229"},"schema_version":"1.0","source":{"id":"1103.3114","kind":"arxiv","version":2}},"canonical_sha256":"70fa7ffabbd252452068929dc7c4890e0395cf0556cb858fa54902b7e3a09440","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70fa7ffabbd252452068929dc7c4890e0395cf0556cb858fa54902b7e3a09440","first_computed_at":"2026-05-18T04:18:23.253687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:18:23.253687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DoZeAwh7gUaO11bBdCgnowjafbNATwna+7eoN9BA1MT2Ilj1q+jY45Isy1gA5s+HKDCi7ZyyAfgaWgCdoitkCA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:18:23.254206Z","signed_message":"canonical_sha256_bytes"},"source_id":"1103.3114","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f805ae1a1b7f432cffff6d503364e166a8fbce101c1710276463b71449fe985","sha256:bea49b15f54d5209d7ecd44d783e0f2a7dcbc41e104c65bb555e67e6610d8cf2"],"state_sha256":"7ee9d5e02ee905818819e801646061426833f3724ad154afb259b2b678b0d122"}