{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O6TY3QG3NJHM6GTVQH53HUQAVA","short_pith_number":"pith:O6TY3QG3","schema_version":"1.0","canonical_sha256":"77a78dc0db6a4ecf1a7581fbb3d200a824352b9a88ad39f11c41c92230c8c2cf","source":{"kind":"arxiv","id":"2504.16137","version":2},"attestation_state":"computed","paper":{"title":"Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CY","authors_text":"Dan Hendrycks, Jasper G\\\"otting, Jon G Sanders, Karam Elabd, Lennart Justen, Long Phan, Nathaniel Li, Pedro Medeiros, Seth Donoughe","submitted_at":"2025-04-21T21:04:01Z","abstract_excerpt":"We present the Virology Capabilities Test (VCT), a large language model (LLM) benchmark that measures the capability to troubleshoot complex virology laboratory protocols. Constructed from the inputs of dozens of PhD-level expert virologists, VCT consists of $322$ multimodal questions covering fundamental, tacit, and visual knowledge that is essential for practical work in virology laboratories. VCT is difficult: expert virologists with access to the internet score an average of $22.1\\%$ on questions specifically in their sub-areas of expertise. However, the most performant LLM, OpenAI's o3, r"},"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":"2504.16137","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-21T21:04:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f4d0bc483b16a6ce50ceacc961a1affe48db096579006803737378533074866","abstract_canon_sha256":"0466a6da5a773950c3459e2c1a57012e2a17df2e9b709ea26507eb8f761dd325"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:34.877284Z","signature_b64":"eBjpcPji7K0Dh1dUH4nVY6dARjRfykMe7Nz3IphXmv7rd1egF9TFI4A0WQZRoEJr5/Xydkybt6h7n88Qm9zeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77a78dc0db6a4ecf1a7581fbb3d200a824352b9a88ad39f11c41c92230c8c2cf","last_reissued_at":"2026-07-05T10:55:34.876813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:34.876813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CY","authors_text":"Dan Hendrycks, Jasper G\\\"otting, Jon G Sanders, Karam Elabd, Lennart Justen, Long Phan, Nathaniel Li, Pedro Medeiros, Seth Donoughe","submitted_at":"2025-04-21T21:04:01Z","abstract_excerpt":"We present the Virology Capabilities Test (VCT), a large language model (LLM) benchmark that measures the capability to troubleshoot complex virology laboratory protocols. Constructed from the inputs of dozens of PhD-level expert virologists, VCT consists of $322$ multimodal questions covering fundamental, tacit, and visual knowledge that is essential for practical work in virology laboratories. VCT is difficult: expert virologists with access to the internet score an average of $22.1\\%$ on questions specifically in their sub-areas of expertise. However, the most performant LLM, OpenAI's o3, r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16137","kind":"arxiv","version":2},"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/2504.16137/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":"2504.16137","created_at":"2026-07-05T10:55:34.876864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16137v2","created_at":"2026-07-05T10:55:34.876864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16137","created_at":"2026-07-05T10:55:34.876864+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6TY3QG3NJHM","created_at":"2026-07-05T10:55:34.876864+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6TY3QG3NJHM6GTV","created_at":"2026-07-05T10:55:34.876864+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6TY3QG3","created_at":"2026-07-05T10:55:34.876864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12429","citing_title":"Muse Spark Safety & Preparedness Report","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21545","citing_title":"RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03121","citing_title":"An Independent Safety Evaluation of Kimi K2.5","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24966","citing_title":"Risk Reporting for Developers' Internal AI Model Use","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00927","citing_title":"BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA","json":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA.json","graph_json":"https://pith.science/api/pith-number/O6TY3QG3NJHM6GTVQH53HUQAVA/graph.json","events_json":"https://pith.science/api/pith-number/O6TY3QG3NJHM6GTVQH53HUQAVA/events.json","paper":"https://pith.science/paper/O6TY3QG3"},"agent_actions":{"view_html":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA","download_json":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA.json","view_paper":"https://pith.science/paper/O6TY3QG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16137&json=true","fetch_graph":"https://pith.science/api/pith-number/O6TY3QG3NJHM6GTVQH53HUQAVA/graph.json","fetch_events":"https://pith.science/api/pith-number/O6TY3QG3NJHM6GTVQH53HUQAVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA/action/storage_attestation","attest_author":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA/action/author_attestation","sign_citation":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA/action/citation_signature","submit_replication":"https://pith.science/pith/O6TY3QG3NJHM6GTVQH53HUQAVA/action/replication_record"}},"created_at":"2026-07-05T10:55:34.876864+00:00","updated_at":"2026-07-05T10:55:34.876864+00:00"}