{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:DP6D5EC3MTA6MOEQ4BKND26EBX","short_pith_number":"pith:DP6D5EC3","schema_version":"1.0","canonical_sha256":"1bfc3e905b64c1e63890e054d1ebc40dff55311e274a586bf067c25b3550c00c","source":{"kind":"arxiv","id":"1112.4193","version":3},"attestation_state":"computed","paper":{"title":"Scaling metagenome sequence assembly with probabilistic de Bruijn graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Adina Howe, Arend Hintze, C. Titus Brown, James M. Tiedje, Jason Pell, Rosangela Canino-Koning","submitted_at":"2011-12-18T21:49:46Z","abstract_excerpt":"Deep sequencing has enabled the investigation of a wide range of environmental microbial ecosystems, but the high memory requirements for {\\em de novo} assembly of short-read shotgun sequencing data from these complex populations are an increasingly large practical barrier. Here we introduce a memory-efficient graph representation with which we can analyze the k-mer connectivity of metagenomic samples. The graph representation is based on a probabilistic data structure, a Bloom filter, that allows us to efficiently store assembly graphs in as little as 4 bits per k-mer, albeit inexactly. We sh"},"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":"1112.4193","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2011-12-18T21:49:46Z","cross_cats_sorted":[],"title_canon_sha256":"0320df93e51de73dad90b51627b1bdd306f553173bacd53e6d0d51e67b753187","abstract_canon_sha256":"fbbd1506a4b863850af9d7e953698178b12d462542cc673f11da16e1a41f04b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:59:05.991717Z","signature_b64":"bBNjl9S9ztV4OvlSOzhbsHuuuO5J0NKPkL0Jvls6PLWaSmOD5TyV+YZHtVEVigd9W8kmOrc5f08Puu+hkGEHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bfc3e905b64c1e63890e054d1ebc40dff55311e274a586bf067c25b3550c00c","last_reissued_at":"2026-05-18T01:59:05.991097Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:59:05.991097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling metagenome sequence assembly with probabilistic de Bruijn graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Adina Howe, Arend Hintze, C. Titus Brown, James M. Tiedje, Jason Pell, Rosangela Canino-Koning","submitted_at":"2011-12-18T21:49:46Z","abstract_excerpt":"Deep sequencing has enabled the investigation of a wide range of environmental microbial ecosystems, but the high memory requirements for {\\em de novo} assembly of short-read shotgun sequencing data from these complex populations are an increasingly large practical barrier. Here we introduce a memory-efficient graph representation with which we can analyze the k-mer connectivity of metagenomic samples. The graph representation is based on a probabilistic data structure, a Bloom filter, that allows us to efficiently store assembly graphs in as little as 4 bits per k-mer, albeit inexactly. We sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1112.4193","kind":"arxiv","version":3},"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":"1112.4193","created_at":"2026-05-18T01:59:05.991183+00:00"},{"alias_kind":"arxiv_version","alias_value":"1112.4193v3","created_at":"2026-05-18T01:59:05.991183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1112.4193","created_at":"2026-05-18T01:59:05.991183+00:00"},{"alias_kind":"pith_short_12","alias_value":"DP6D5EC3MTA6","created_at":"2026-05-18T12:26:26.731475+00:00"},{"alias_kind":"pith_short_16","alias_value":"DP6D5EC3MTA6MOEQ","created_at":"2026-05-18T12:26:26.731475+00:00"},{"alias_kind":"pith_short_8","alias_value":"DP6D5EC3","created_at":"2026-05-18T12:26:26.731475+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/DP6D5EC3MTA6MOEQ4BKND26EBX","json":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX.json","graph_json":"https://pith.science/api/pith-number/DP6D5EC3MTA6MOEQ4BKND26EBX/graph.json","events_json":"https://pith.science/api/pith-number/DP6D5EC3MTA6MOEQ4BKND26EBX/events.json","paper":"https://pith.science/paper/DP6D5EC3"},"agent_actions":{"view_html":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX","download_json":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX.json","view_paper":"https://pith.science/paper/DP6D5EC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1112.4193&json=true","fetch_graph":"https://pith.science/api/pith-number/DP6D5EC3MTA6MOEQ4BKND26EBX/graph.json","fetch_events":"https://pith.science/api/pith-number/DP6D5EC3MTA6MOEQ4BKND26EBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX/action/storage_attestation","attest_author":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX/action/author_attestation","sign_citation":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX/action/citation_signature","submit_replication":"https://pith.science/pith/DP6D5EC3MTA6MOEQ4BKND26EBX/action/replication_record"}},"created_at":"2026-05-18T01:59:05.991183+00:00","updated_at":"2026-05-18T01:59:05.991183+00:00"}