{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:6N6JYBZ4EW37WVT47RMSLF7YLT","short_pith_number":"pith:6N6JYBZ4","schema_version":"1.0","canonical_sha256":"f37c9c073c25b7fb567cfc592597f85ccfc1d32d4afa4667f8547ddd407e33f6","source":{"kind":"arxiv","id":"1508.02968","version":1},"attestation_state":"computed","paper":{"title":"Space-efficient detection of unusual words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Djamal Belazzougui, Fabio Cunial","submitted_at":"2015-08-12T16:01:21Z","abstract_excerpt":"Detecting all the strings that occur in a text more frequently or less frequently than expected according to an IID or a Markov model is a basic problem in string mining, yet current algorithms are based on data structures that are either space-inefficient or incur large slowdowns, and current implementations cannot scale to genomes or metagenomes in practice. In this paper we engineer an algorithm based on the suffix tree of a string to use just a small data structure built on the Burrows-Wheeler transform, and a stack of $O(\\sigma^2\\log^2 n)$ bits, where $n$ is the length of the string and $"},"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":"1508.02968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-08-12T16:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"9a93cd6b18938efa0341dc595b06715266c8eeb619d7363b5282fd44f6144997","abstract_canon_sha256":"5843e3ccba505897227328b1c86c6f02e71848124dea69185879493101fb6271"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:23.293734Z","signature_b64":"tkE+ygsyMi/0ZkpFljGkS6yT5+ZHlixIMs6PrXEyCd18nPYHl8sosqxT6m0eGScmDSahP2WZk5JFXk4gH9g3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f37c9c073c25b7fb567cfc592597f85ccfc1d32d4afa4667f8547ddd407e33f6","last_reissued_at":"2026-05-18T01:35:23.293020Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:23.293020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Space-efficient detection of unusual words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Djamal Belazzougui, Fabio Cunial","submitted_at":"2015-08-12T16:01:21Z","abstract_excerpt":"Detecting all the strings that occur in a text more frequently or less frequently than expected according to an IID or a Markov model is a basic problem in string mining, yet current algorithms are based on data structures that are either space-inefficient or incur large slowdowns, and current implementations cannot scale to genomes or metagenomes in practice. In this paper we engineer an algorithm based on the suffix tree of a string to use just a small data structure built on the Burrows-Wheeler transform, and a stack of $O(\\sigma^2\\log^2 n)$ bits, where $n$ is the length of the string and $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02968","kind":"arxiv","version":1},"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":"1508.02968","created_at":"2026-05-18T01:35:23.293149+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.02968v1","created_at":"2026-05-18T01:35:23.293149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02968","created_at":"2026-05-18T01:35:23.293149+00:00"},{"alias_kind":"pith_short_12","alias_value":"6N6JYBZ4EW37","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"6N6JYBZ4EW37WVT4","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"6N6JYBZ4","created_at":"2026-05-18T12:29:07.941421+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/6N6JYBZ4EW37WVT47RMSLF7YLT","json":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT.json","graph_json":"https://pith.science/api/pith-number/6N6JYBZ4EW37WVT47RMSLF7YLT/graph.json","events_json":"https://pith.science/api/pith-number/6N6JYBZ4EW37WVT47RMSLF7YLT/events.json","paper":"https://pith.science/paper/6N6JYBZ4"},"agent_actions":{"view_html":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT","download_json":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT.json","view_paper":"https://pith.science/paper/6N6JYBZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.02968&json=true","fetch_graph":"https://pith.science/api/pith-number/6N6JYBZ4EW37WVT47RMSLF7YLT/graph.json","fetch_events":"https://pith.science/api/pith-number/6N6JYBZ4EW37WVT47RMSLF7YLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT/action/storage_attestation","attest_author":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT/action/author_attestation","sign_citation":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT/action/citation_signature","submit_replication":"https://pith.science/pith/6N6JYBZ4EW37WVT47RMSLF7YLT/action/replication_record"}},"created_at":"2026-05-18T01:35:23.293149+00:00","updated_at":"2026-05-18T01:35:23.293149+00:00"}