{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6N6JYBZ4EW37WVT47RMSLF7YLT","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":"5843e3ccba505897227328b1c86c6f02e71848124dea69185879493101fb6271","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-08-12T16:01:21Z","title_canon_sha256":"9a93cd6b18938efa0341dc595b06715266c8eeb619d7363b5282fd44f6144997"},"schema_version":"1.0","source":{"id":"1508.02968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.02968","created_at":"2026-05-18T01:35:23Z"},{"alias_kind":"arxiv_version","alias_value":"1508.02968v1","created_at":"2026-05-18T01:35:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02968","created_at":"2026-05-18T01:35:23Z"},{"alias_kind":"pith_short_12","alias_value":"6N6JYBZ4EW37","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6N6JYBZ4EW37WVT4","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6N6JYBZ4","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:bbefb708c2f84893501e5b579f2717cb28574b7d04e7d0e69065918a8855c744","target":"graph","created_at":"2026-05-18T01:35:23Z","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":"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 $","authors_text":"Djamal Belazzougui, Fabio Cunial","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-08-12T16:01:21Z","title":"Space-efficient detection of unusual words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02968","kind":"arxiv","version":1},"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:bcc5f23ec92e1100b11eefac3bd0148d2898b7b2d31775fb9896ddf973885f49","target":"record","created_at":"2026-05-18T01:35:23Z","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":"5843e3ccba505897227328b1c86c6f02e71848124dea69185879493101fb6271","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-08-12T16:01:21Z","title_canon_sha256":"9a93cd6b18938efa0341dc595b06715266c8eeb619d7363b5282fd44f6144997"},"schema_version":"1.0","source":{"id":"1508.02968","kind":"arxiv","version":1}},"canonical_sha256":"f37c9c073c25b7fb567cfc592597f85ccfc1d32d4afa4667f8547ddd407e33f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f37c9c073c25b7fb567cfc592597f85ccfc1d32d4afa4667f8547ddd407e33f6","first_computed_at":"2026-05-18T01:35:23.293020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:23.293020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tkE+ygsyMi/0ZkpFljGkS6yT5+ZHlixIMs6PrXEyCd18nPYHl8sosqxT6m0eGScmDSahP2WZk5JFXk4gH9g3BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:23.293734Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.02968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcc5f23ec92e1100b11eefac3bd0148d2898b7b2d31775fb9896ddf973885f49","sha256:bbefb708c2f84893501e5b579f2717cb28574b7d04e7d0e69065918a8855c744"],"state_sha256":"953e57e9a01de048b00fc3d29812599fc1e6d16084018346ae2d56bee4115197"}