{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Z7UC7RN5LHBFHWP6PAD5IKK2BS","short_pith_number":"pith:Z7UC7RN5","schema_version":"1.0","canonical_sha256":"cfe82fc5bd59c253d9fe7807d4295a0c8278b2e0c4a9cdfa437c1d5b268cb39c","source":{"kind":"arxiv","id":"1604.08760","version":1},"attestation_state":"computed","paper":{"title":"Optimal Computation of Avoided Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Costas S. Iliopoulos, Dimitris Polychronopoulos, Jia Gao, Manal Mohamed, Panagiotis Charalampopoulos, Solon P. Pissis, Yannis Almirantis","submitted_at":"2016-04-29T10:12:06Z","abstract_excerpt":"The deviation of the observed frequency of a word $w$ from its expected frequency in a given sequence $x$ is used to determine whether or not the word is avoided. This concept is particularly useful in DNA linguistic analysis. The value of the standard deviation of $w$, denoted by $std(w)$, effectively characterises the extent of a word by its edge contrast in the context in which it occurs. A word $w$ of length $k>2$ is a $\\rho$-avoided word in $x$ if $std(w) \\leq \\rho$, for a given threshold $\\rho < 0$. Notice that such a word may be completely absent from $x$. Hence computing all such words"},"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":"1604.08760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2016-04-29T10:12:06Z","cross_cats_sorted":[],"title_canon_sha256":"bbda0d1d816e8aa9594af06f374080bd37fcd2d0f97145eca6d346587167c8aa","abstract_canon_sha256":"ead1f48aec89a585ae6d74cdf3884df09dace86c7e659ab38bbe5fca0007227e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:01.876220Z","signature_b64":"vcc3tgbjZ6gwDUl7O6/thyeoJWxHytd1ynIZWPvpLAhht0QSUCG/cY6rMBGS9xfHSw/9UYWCXWCWvUUrT0OtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfe82fc5bd59c253d9fe7807d4295a0c8278b2e0c4a9cdfa437c1d5b268cb39c","last_reissued_at":"2026-05-18T01:16:01.875470Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:01.875470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Computation of Avoided Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Costas S. Iliopoulos, Dimitris Polychronopoulos, Jia Gao, Manal Mohamed, Panagiotis Charalampopoulos, Solon P. Pissis, Yannis Almirantis","submitted_at":"2016-04-29T10:12:06Z","abstract_excerpt":"The deviation of the observed frequency of a word $w$ from its expected frequency in a given sequence $x$ is used to determine whether or not the word is avoided. This concept is particularly useful in DNA linguistic analysis. The value of the standard deviation of $w$, denoted by $std(w)$, effectively characterises the extent of a word by its edge contrast in the context in which it occurs. A word $w$ of length $k>2$ is a $\\rho$-avoided word in $x$ if $std(w) \\leq \\rho$, for a given threshold $\\rho < 0$. Notice that such a word may be completely absent from $x$. Hence computing all such words"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.08760","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":"1604.08760","created_at":"2026-05-18T01:16:01.875592+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.08760v1","created_at":"2026-05-18T01:16:01.875592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.08760","created_at":"2026-05-18T01:16:01.875592+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7UC7RN5LHBF","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7UC7RN5LHBFHWP6","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7UC7RN5","created_at":"2026-05-18T12:30:53.716459+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/Z7UC7RN5LHBFHWP6PAD5IKK2BS","json":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS.json","graph_json":"https://pith.science/api/pith-number/Z7UC7RN5LHBFHWP6PAD5IKK2BS/graph.json","events_json":"https://pith.science/api/pith-number/Z7UC7RN5LHBFHWP6PAD5IKK2BS/events.json","paper":"https://pith.science/paper/Z7UC7RN5"},"agent_actions":{"view_html":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS","download_json":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS.json","view_paper":"https://pith.science/paper/Z7UC7RN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.08760&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7UC7RN5LHBFHWP6PAD5IKK2BS/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7UC7RN5LHBFHWP6PAD5IKK2BS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS/action/storage_attestation","attest_author":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS/action/author_attestation","sign_citation":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS/action/citation_signature","submit_replication":"https://pith.science/pith/Z7UC7RN5LHBFHWP6PAD5IKK2BS/action/replication_record"}},"created_at":"2026-05-18T01:16:01.875592+00:00","updated_at":"2026-05-18T01:16:01.875592+00:00"}