{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:OPFK5BGJXAX42SS2STSXEJBNHK","short_pith_number":"pith:OPFK5BGJ","schema_version":"1.0","canonical_sha256":"73caae84c9b82fcd4a5a94e572242d3a8c0e1370076d171c40ecdb0f4635c826","source":{"kind":"arxiv","id":"1511.04944","version":2},"attestation_state":"computed","paper":{"title":"NASCUP: Nucleic Acid Sequence Classification by Universal Probability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"q-bio.GN","authors_text":"Byunghan Lee, Gyuwan Kim, Jongsik Chun, Sungroh Yoon, Sunyoung Kwon, Young-Han Kim","submitted_at":"2015-11-16T13:04:03Z","abstract_excerpt":"Motivated by the need for fast and accurate classification of unlabeled nucleotide sequences on a large scale, we developed NASCUP, a new classification method that captures statistical structures of nucleotide sequences by compact context-tree models and universal probability from information theory. NASCUP achieved BLAST-like classification accuracy consistently for several large-scale databases in orders-of-magnitude reduced runtime, and was applied to other bioinformatics tasks such as outlier detection and synthetic sequence generation."},"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":"1511.04944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2015-11-16T13:04:03Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"fa42b31f9035154360d1839e3f47b3c6b19bd209c1b00351d2a6f3e66245bc15","abstract_canon_sha256":"118232ff19d15f31e9750fdbf11b879eec1bb92ea8ac973541b7c7406477573e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:39.843913Z","signature_b64":"hu0FXf6K3F1f5ePx5pjvY2s1djVbe47+0bfdzFBNZYD3qfE9BwBKzKdSrR749+QuLwS/90+sZdTHFUSMyplsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73caae84c9b82fcd4a5a94e572242d3a8c0e1370076d171c40ecdb0f4635c826","last_reissued_at":"2026-05-17T23:59:39.843237Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:39.843237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NASCUP: Nucleic Acid Sequence Classification by Universal Probability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"q-bio.GN","authors_text":"Byunghan Lee, Gyuwan Kim, Jongsik Chun, Sungroh Yoon, Sunyoung Kwon, Young-Han Kim","submitted_at":"2015-11-16T13:04:03Z","abstract_excerpt":"Motivated by the need for fast and accurate classification of unlabeled nucleotide sequences on a large scale, we developed NASCUP, a new classification method that captures statistical structures of nucleotide sequences by compact context-tree models and universal probability from information theory. NASCUP achieved BLAST-like classification accuracy consistently for several large-scale databases in orders-of-magnitude reduced runtime, and was applied to other bioinformatics tasks such as outlier detection and synthetic sequence generation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04944","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":"1511.04944","created_at":"2026-05-17T23:59:39.843355+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.04944v2","created_at":"2026-05-17T23:59:39.843355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04944","created_at":"2026-05-17T23:59:39.843355+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPFK5BGJXAX4","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPFK5BGJXAX42SS2","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPFK5BGJ","created_at":"2026-05-18T12:29:34.919912+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/OPFK5BGJXAX42SS2STSXEJBNHK","json":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK.json","graph_json":"https://pith.science/api/pith-number/OPFK5BGJXAX42SS2STSXEJBNHK/graph.json","events_json":"https://pith.science/api/pith-number/OPFK5BGJXAX42SS2STSXEJBNHK/events.json","paper":"https://pith.science/paper/OPFK5BGJ"},"agent_actions":{"view_html":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK","download_json":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK.json","view_paper":"https://pith.science/paper/OPFK5BGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.04944&json=true","fetch_graph":"https://pith.science/api/pith-number/OPFK5BGJXAX42SS2STSXEJBNHK/graph.json","fetch_events":"https://pith.science/api/pith-number/OPFK5BGJXAX42SS2STSXEJBNHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK/action/storage_attestation","attest_author":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK/action/author_attestation","sign_citation":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK/action/citation_signature","submit_replication":"https://pith.science/pith/OPFK5BGJXAX42SS2STSXEJBNHK/action/replication_record"}},"created_at":"2026-05-17T23:59:39.843355+00:00","updated_at":"2026-05-17T23:59:39.843355+00:00"}