{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:SCZSTIUMO3F6NFEOTY4CCPUBW6","short_pith_number":"pith:SCZSTIUM","schema_version":"1.0","canonical_sha256":"90b329a28c76cbe6948e9e38213e81b78151e38d1730636d3bf71f32a0e50c9e","source":{"kind":"arxiv","id":"1308.6240","version":1},"attestation_state":"computed","paper":{"title":"Diminishing Return for Increased Mappability with Longer Sequencing Reads: Implications of the k-mer Distributions in the Human Genome","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Jan Freudenberg, Pedro Miramontes, Wentian Li","submitted_at":"2013-08-28T18:14:47Z","abstract_excerpt":"The amount of non-unique sequence (non-singletons) in a genome directly affects the difficulty of read alignment to a reference assembly for high throughput-sequencing data. Although a greater length increases the chance for reads being uniquely mapped to the reference genome, a quantitative analysis of the influence of read lengths on mappability has been lacking. To address this question, we evaluate the k-mer distribution of the human reference genome. The k-mer frequency is determined for k ranging from 20 to 1000 basepairs. We use the proportion of non-singleton k-mers to evaluate the map"},"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":"1308.6240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2013-08-28T18:14:47Z","cross_cats_sorted":[],"title_canon_sha256":"e40ee5e25930b9982586c4c32e88fa1e9c9fe7e1cc076d9bf9d0d1fa432f16fc","abstract_canon_sha256":"5af21708073a21e729ace34cac01acb5fa6f064def9a56cbd21ea0a6235fbc2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:42.940717Z","signature_b64":"tJEE5CyasFH2JPDTFvYcb7RG0v98eL5S/j+8sWKQUT8+Jlwf2N8D4OcWVFmqnQoDMCPAEpaavvZmvam6hFo+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90b329a28c76cbe6948e9e38213e81b78151e38d1730636d3bf71f32a0e50c9e","last_reissued_at":"2026-05-18T00:49:42.940010Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:42.940010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diminishing Return for Increased Mappability with Longer Sequencing Reads: Implications of the k-mer Distributions in the Human Genome","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Jan Freudenberg, Pedro Miramontes, Wentian Li","submitted_at":"2013-08-28T18:14:47Z","abstract_excerpt":"The amount of non-unique sequence (non-singletons) in a genome directly affects the difficulty of read alignment to a reference assembly for high throughput-sequencing data. Although a greater length increases the chance for reads being uniquely mapped to the reference genome, a quantitative analysis of the influence of read lengths on mappability has been lacking. To address this question, we evaluate the k-mer distribution of the human reference genome. The k-mer frequency is determined for k ranging from 20 to 1000 basepairs. We use the proportion of non-singleton k-mers to evaluate the map"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1308.6240","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":"1308.6240","created_at":"2026-05-18T00:49:42.940131+00:00"},{"alias_kind":"arxiv_version","alias_value":"1308.6240v1","created_at":"2026-05-18T00:49:42.940131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1308.6240","created_at":"2026-05-18T00:49:42.940131+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCZSTIUMO3F6","created_at":"2026-05-18T12:27:59.945178+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCZSTIUMO3F6NFEO","created_at":"2026-05-18T12:27:59.945178+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCZSTIUM","created_at":"2026-05-18T12:27:59.945178+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/SCZSTIUMO3F6NFEOTY4CCPUBW6","json":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6.json","graph_json":"https://pith.science/api/pith-number/SCZSTIUMO3F6NFEOTY4CCPUBW6/graph.json","events_json":"https://pith.science/api/pith-number/SCZSTIUMO3F6NFEOTY4CCPUBW6/events.json","paper":"https://pith.science/paper/SCZSTIUM"},"agent_actions":{"view_html":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6","download_json":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6.json","view_paper":"https://pith.science/paper/SCZSTIUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1308.6240&json=true","fetch_graph":"https://pith.science/api/pith-number/SCZSTIUMO3F6NFEOTY4CCPUBW6/graph.json","fetch_events":"https://pith.science/api/pith-number/SCZSTIUMO3F6NFEOTY4CCPUBW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6/action/storage_attestation","attest_author":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6/action/author_attestation","sign_citation":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6/action/citation_signature","submit_replication":"https://pith.science/pith/SCZSTIUMO3F6NFEOTY4CCPUBW6/action/replication_record"}},"created_at":"2026-05-18T00:49:42.940131+00:00","updated_at":"2026-05-18T00:49:42.940131+00:00"}