{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:LY6K7G5CJVFL4XKS2BQRSRQSWM","short_pith_number":"pith:LY6K7G5C","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"},"canonical_sha256":"5e3caf9ba24d4abe5d52d061194612b337afc4361be950475c395e6763d2aca3","source":{"kind":"arxiv","id":"1012.5011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1012.5011","created_at":"2026-05-18T04:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"1012.5011v1","created_at":"2026-05-18T04:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1012.5011","created_at":"2026-05-18T04:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"LY6K7G5CJVFL","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_16","alias_value":"LY6K7G5CJVFL4XKS","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_8","alias_value":"LY6K7G5C","created_at":"2026-05-18T12:26:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:LY6K7G5CJVFL4XKS2BQRSRQSWM","target":"record","payload":{"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"},"canonical_sha256":"5e3caf9ba24d4abe5d52d061194612b337afc4361be950475c395e6763d2aca3","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"},"source_kind":"arxiv","source_id":"1012.5011","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7nwhrZd9tcM56A+OlRQOc1EuNQKMfjQSErYheYO+gzoGMrI+CVAhToDkQ3icYLjOzrbSRLYg2b89yzuDITIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T19:46:13.229619Z"},"content_sha256":"6c1015d74add2fac80bc007f55ce10dec14efe99bee42148c32868dc72a77817","schema_version":"1.0","event_id":"sha256:6c1015d74add2fac80bc007f55ce10dec14efe99bee42148c32868dc72a77817"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:LY6K7G5CJVFL4XKS2BQRSRQSWM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NI4vxdwYxLNSxeIZMluOXladnLh+TGbbFDVNF3Tk5tjWl3qF1s3RvVg+Ju0WY++UEGmNFzprZX+rQSWn3kDnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T19:46:13.230197Z"},"content_sha256":"4d056844a552b29e919ae2690128da59f62f4938062457e59762a2ee9dfdfc29","schema_version":"1.0","event_id":"sha256:4d056844a552b29e919ae2690128da59f62f4938062457e59762a2ee9dfdfc29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/bundle.json","state_url":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T19:46:13Z","links":{"resolver":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM","bundle":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/bundle.json","state":"https://pith.science/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LY6K7G5CJVFL4XKS2BQRSRQSWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:LY6K7G5CJVFL4XKS2BQRSRQSWM","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":"4932394dff1f09791b7da1f3c47882e10aaea91f435f1962b547dc0f4d8eb666","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2010-12-22T15:31:32Z","title_canon_sha256":"af7abc83d936aa75f59e00dc8893c439a0201c6809d3cac5296dc649b8ed9ec0"},"schema_version":"1.0","source":{"id":"1012.5011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1012.5011","created_at":"2026-05-18T04:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"1012.5011v1","created_at":"2026-05-18T04:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1012.5011","created_at":"2026-05-18T04:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"LY6K7G5CJVFL","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_16","alias_value":"LY6K7G5CJVFL4XKS","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_8","alias_value":"LY6K7G5C","created_at":"2026-05-18T12:26:10Z"}],"graph_snapshots":[{"event_id":"sha256:4d056844a552b29e919ae2690128da59f62f4938062457e59762a2ee9dfdfc29","target":"graph","created_at":"2026-05-18T04:32:44Z","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":"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","authors_text":"Alan M. Moses, Amin Zia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2010-12-22T15:31:32Z","title":"Towards a theoretical understanding of false positives in DNA motif finding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1012.5011","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":"sha256:6c1015d74add2fac80bc007f55ce10dec14efe99bee42148c32868dc72a77817","target":"record","created_at":"2026-05-18T04:32:44Z","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":"4932394dff1f09791b7da1f3c47882e10aaea91f435f1962b547dc0f4d8eb666","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2010-12-22T15:31:32Z","title_canon_sha256":"af7abc83d936aa75f59e00dc8893c439a0201c6809d3cac5296dc649b8ed9ec0"},"schema_version":"1.0","source":{"id":"1012.5011","kind":"arxiv","version":1}},"canonical_sha256":"5e3caf9ba24d4abe5d52d061194612b337afc4361be950475c395e6763d2aca3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e3caf9ba24d4abe5d52d061194612b337afc4361be950475c395e6763d2aca3","first_computed_at":"2026-05-18T04:32:44.686586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:32:44.686586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l7f+7tV6cJSL2UIAvwtcpWj73HW/H7se4oQs3tKpgDvGnx5ARmhggfIvZZSqk9q0V7UDEABhlIYQQL5uJKjYDw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:32:44.687284Z","signed_message":"canonical_sha256_bytes"},"source_id":"1012.5011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c1015d74add2fac80bc007f55ce10dec14efe99bee42148c32868dc72a77817","sha256:4d056844a552b29e919ae2690128da59f62f4938062457e59762a2ee9dfdfc29"],"state_sha256":"9256d7a9ce82df82a72de58a1873c85633a35bf8545bff22927c2c5b44b6cbe1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ks/KStuOrQEcUTnnf5cpBl0F00UCwGTThgNyYmvi31ZEg+6AtkYLFoTbDUW1YRPkk7d9hN8dFbaD0/ileXgNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T19:46:13.232542Z","bundle_sha256":"4be5e9b4b0bb318b92ae511440e120a9e5592bb3470fab135648248a6ec2f22f"}}