{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:LY6K7G5CJVFL4XKS2BQRSRQSWM","short_pith_number":"pith:LY6K7G5C","schema_version":"1.0","canonical_sha256":"5e3caf9ba24d4abe5d52d061194612b337afc4361be950475c395e6763d2aca3","source":{"kind":"arxiv","id":"1012.5011","version":1},"attestation_state":"computed","paper":{"title":"Towards a theoretical understanding of false positives in DNA motif finding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Alan M. Moses, Amin Zia","submitted_at":"2010-12-22T15:31:32Z","abstract_excerpt":"Detection of false-positive motifs is one of the main causes of low performance in motif finding methods. It is generally assumed that false-positives are mostly due to algorithmic weakness of motif-finders. Here, however, we derive the theoretical dependence of false positives on dataset size and find that false positives can arise as a result of large dataset size, irrespective of the algorithm used. Interestingly, the false-positive strength depends more on the number of sequences in the dataset than it does on the sequence length. As expected, false-positives can be reduced by decreasing t"},"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":"1012.5011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2010-12-22T15:31:32Z","cross_cats_sorted":[],"title_canon_sha256":"af7abc83d936aa75f59e00dc8893c439a0201c6809d3cac5296dc649b8ed9ec0","abstract_canon_sha256":"4932394dff1f09791b7da1f3c47882e10aaea91f435f1962b547dc0f4d8eb666"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:32:44.687284Z","signature_b64":"l7f+7tV6cJSL2UIAvwtcpWj73HW/H7se4oQs3tKpgDvGnx5ARmhggfIvZZSqk9q0V7UDEABhlIYQQL5uJKjYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e3caf9ba24d4abe5d52d061194612b337afc4361be950475c395e6763d2aca3","last_reissued_at":"2026-05-18T04:32:44.686586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:32:44.686586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a theoretical understanding of false positives in DNA motif finding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Alan M. Moses, Amin Zia","submitted_at":"2010-12-22T15:31:32Z","abstract_excerpt":"Detection of false-positive motifs is one of the main causes of low performance in motif finding methods. It is generally assumed that false-positives are mostly due to algorithmic weakness of motif-finders. Here, however, we derive the theoretical dependence of false positives on dataset size and find that false positives can arise as a result of large dataset size, irrespective of the algorithm used. Interestingly, the false-positive strength depends more on the number of sequences in the dataset than it does on the sequence length. As expected, false-positives can be reduced by decreasing t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1012.5011","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":"1012.5011","created_at":"2026-05-18T04:32:44.686697+00:00"},{"alias_kind":"arxiv_version","alias_value":"1012.5011v1","created_at":"2026-05-18T04:32:44.686697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1012.5011","created_at":"2026-05-18T04:32:44.686697+00:00"},{"alias_kind":"pith_short_12","alias_value":"LY6K7G5CJVFL","created_at":"2026-05-18T12:26:10.704358+00:00"},{"alias_kind":"pith_short_16","alias_value":"LY6K7G5CJVFL4XKS","created_at":"2026-05-18T12:26:10.704358+00:00"},{"alias_kind":"pith_short_8","alias_value":"LY6K7G5C","created_at":"2026-05-18T12:26:10.704358+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/LY6K7G5CJVFL4XKS2BQRSRQSWM","json":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM.json","graph_json":"https://pith.science/api/pith-number/LY6K7G5CJVFL4XKS2BQRSRQSWM/graph.json","events_json":"https://pith.science/api/pith-number/LY6K7G5CJVFL4XKS2BQRSRQSWM/events.json","paper":"https://pith.science/paper/LY6K7G5C"},"agent_actions":{"view_html":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM","download_json":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM.json","view_paper":"https://pith.science/paper/LY6K7G5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1012.5011&json=true","fetch_graph":"https://pith.science/api/pith-number/LY6K7G5CJVFL4XKS2BQRSRQSWM/graph.json","fetch_events":"https://pith.science/api/pith-number/LY6K7G5CJVFL4XKS2BQRSRQSWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/action/storage_attestation","attest_author":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/action/author_attestation","sign_citation":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/action/citation_signature","submit_replication":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/action/replication_record"}},"created_at":"2026-05-18T04:32:44.686697+00:00","updated_at":"2026-05-18T04:32:44.686697+00:00"}