{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:GOIIC6A5V52GUJWODYR74JZJJB","short_pith_number":"pith:GOIIC6A5","schema_version":"1.0","canonical_sha256":"339081781daf746a26ce1e23fe27294878b401c32dc28f6eb6bbc69929650809","source":{"kind":"arxiv","id":"1501.05546","version":1},"attestation_state":"computed","paper":{"title":"Using a Big Data Database to Identify Pathogens in Protein Data Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.DB","authors_text":"Ashley Mae Conard, Darrell Ricke, Jeremy Kepner, Stephanie Dodson","submitted_at":"2015-01-22T15:58:42Z","abstract_excerpt":"Current metagenomic analysis algorithms require significant computing resources, can report excessive false positives (type I errors), may miss organisms (type II errors / false negatives), or scale poorly on large datasets. This paper explores using big data database technologies to characterize very large metagenomic DNA sequences in protein space, with the ultimate goal of rapid pathogen identification in patient samples. Our approach uses the abilities of a big data databases to hold large sparse associative array representations of genetic data to extract statistical patterns about the da"},"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":"1501.05546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-01-22T15:58:42Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"7b5f0e1889eb332d0c8078c84dbb1b12d084a27bb4c30e15248bbdadba7385d0","abstract_canon_sha256":"01c3b3c8a9015f91b0078b2edc0184e19ce1e001160eda49a81398b4003e5181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:54.477249Z","signature_b64":"jwWalIgHWn5NzHJXqhAvFtYL9FVeiYydY5PHDCI580zezngE1zPzBGCjYuquz/OHo5wi9sX0je+DvuNWKxafDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"339081781daf746a26ce1e23fe27294878b401c32dc28f6eb6bbc69929650809","last_reissued_at":"2026-05-18T02:28:54.476907Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:54.476907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using a Big Data Database to Identify Pathogens in Protein Data Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.DB","authors_text":"Ashley Mae Conard, Darrell Ricke, Jeremy Kepner, Stephanie Dodson","submitted_at":"2015-01-22T15:58:42Z","abstract_excerpt":"Current metagenomic analysis algorithms require significant computing resources, can report excessive false positives (type I errors), may miss organisms (type II errors / false negatives), or scale poorly on large datasets. This paper explores using big data database technologies to characterize very large metagenomic DNA sequences in protein space, with the ultimate goal of rapid pathogen identification in patient samples. Our approach uses the abilities of a big data databases to hold large sparse associative array representations of genetic data to extract statistical patterns about the da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.05546","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":"1501.05546","created_at":"2026-05-18T02:28:54.476961+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.05546v1","created_at":"2026-05-18T02:28:54.476961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.05546","created_at":"2026-05-18T02:28:54.476961+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOIIC6A5V52G","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOIIC6A5V52GUJWO","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOIIC6A5","created_at":"2026-05-18T12:29:22.688609+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/GOIIC6A5V52GUJWODYR74JZJJB","json":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB.json","graph_json":"https://pith.science/api/pith-number/GOIIC6A5V52GUJWODYR74JZJJB/graph.json","events_json":"https://pith.science/api/pith-number/GOIIC6A5V52GUJWODYR74JZJJB/events.json","paper":"https://pith.science/paper/GOIIC6A5"},"agent_actions":{"view_html":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB","download_json":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB.json","view_paper":"https://pith.science/paper/GOIIC6A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.05546&json=true","fetch_graph":"https://pith.science/api/pith-number/GOIIC6A5V52GUJWODYR74JZJJB/graph.json","fetch_events":"https://pith.science/api/pith-number/GOIIC6A5V52GUJWODYR74JZJJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB/action/storage_attestation","attest_author":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB/action/author_attestation","sign_citation":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB/action/citation_signature","submit_replication":"https://pith.science/pith/GOIIC6A5V52GUJWODYR74JZJJB/action/replication_record"}},"created_at":"2026-05-18T02:28:54.476961+00:00","updated_at":"2026-05-18T02:28:54.476961+00:00"}