{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5XQIQFE5LUPKJPF6WCDYEO724I","short_pith_number":"pith:5XQIQFE5","schema_version":"1.0","canonical_sha256":"ede088149d5d1ea4bcbeb087823bfae2278d5e47111e4a6f4315fa43f5abe98e","source":{"kind":"arxiv","id":"2606.06749","version":1},"attestation_state":"computed","paper":{"title":"Deterministic access to global viral sequence data enables robust agentic scientific discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Bernhard Y. Renard, Ferdous Nasri, Jonah Cool, Krithik Ramesh, Laura Luebbert, Nuala A. O'Leary, Pardis C. Sabeti, Patrick Varilly, Sarah Gurev","submitted_at":"2026-06-04T22:19:42Z","abstract_excerpt":"Public viral genome resources such as the National Center for Biotechnology Information (NCBI) Virus database are central to outbreak response, evolutionary analysis, vaccine design, and genomic surveillance. Yet many high-value retrieval workflows remain optimized for interactive use rather than deterministic, reproducible programmatic interfaces. This creates a challenge for Large Language Model (LLM)-based scientific agents, where errors in metadata interpretation, filtering logic, or retrieval can propagate into incorrect datasets. To evaluate agentic viral data retrieval, we built VirBenc"},"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":"2606.06749","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-06-04T22:19:42Z","cross_cats_sorted":[],"title_canon_sha256":"0cb4c05690e39a0c8f5e53084a784843e4ad641f5453bcafa15bb4156a781c5f","abstract_canon_sha256":"749194581637eddc1fdda2dcefc9842578375c76be75bd6a31ce9850a7320d2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:26.417300Z","signature_b64":"CVXpiISJFLyoKWGYc3CCSqaRePeZje1ey2A/lUS+qMijYj9OKAYQoXlB5gRdVLpdQtlmZM4QcvxHswHZKcmiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ede088149d5d1ea4bcbeb087823bfae2278d5e47111e4a6f4315fa43f5abe98e","last_reissued_at":"2026-06-08T01:04:26.416555Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:26.416555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deterministic access to global viral sequence data enables robust agentic scientific discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Bernhard Y. Renard, Ferdous Nasri, Jonah Cool, Krithik Ramesh, Laura Luebbert, Nuala A. O'Leary, Pardis C. Sabeti, Patrick Varilly, Sarah Gurev","submitted_at":"2026-06-04T22:19:42Z","abstract_excerpt":"Public viral genome resources such as the National Center for Biotechnology Information (NCBI) Virus database are central to outbreak response, evolutionary analysis, vaccine design, and genomic surveillance. Yet many high-value retrieval workflows remain optimized for interactive use rather than deterministic, reproducible programmatic interfaces. This creates a challenge for Large Language Model (LLM)-based scientific agents, where errors in metadata interpretation, filtering logic, or retrieval can propagate into incorrect datasets. To evaluate agentic viral data retrieval, we built VirBenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06749","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.06749/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2606.06749","created_at":"2026-06-08T01:04:26.416677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06749v1","created_at":"2026-06-08T01:04:26.416677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06749","created_at":"2026-06-08T01:04:26.416677+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XQIQFE5LUPK","created_at":"2026-06-08T01:04:26.416677+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XQIQFE5LUPKJPF6","created_at":"2026-06-08T01:04:26.416677+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XQIQFE5","created_at":"2026-06-08T01:04:26.416677+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/5XQIQFE5LUPKJPF6WCDYEO724I","json":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I.json","graph_json":"https://pith.science/api/pith-number/5XQIQFE5LUPKJPF6WCDYEO724I/graph.json","events_json":"https://pith.science/api/pith-number/5XQIQFE5LUPKJPF6WCDYEO724I/events.json","paper":"https://pith.science/paper/5XQIQFE5"},"agent_actions":{"view_html":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I","download_json":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I.json","view_paper":"https://pith.science/paper/5XQIQFE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06749&json=true","fetch_graph":"https://pith.science/api/pith-number/5XQIQFE5LUPKJPF6WCDYEO724I/graph.json","fetch_events":"https://pith.science/api/pith-number/5XQIQFE5LUPKJPF6WCDYEO724I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I/action/storage_attestation","attest_author":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I/action/author_attestation","sign_citation":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I/action/citation_signature","submit_replication":"https://pith.science/pith/5XQIQFE5LUPKJPF6WCDYEO724I/action/replication_record"}},"created_at":"2026-06-08T01:04:26.416677+00:00","updated_at":"2026-06-08T01:04:26.416677+00:00"}