{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O6TY3QG3NJHM6GTVQH53HUQAVA","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":"0466a6da5a773950c3459e2c1a57012e2a17df2e9b709ea26507eb8f761dd325","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-21T21:04:01Z","title_canon_sha256":"8f4d0bc483b16a6ce50ceacc961a1affe48db096579006803737378533074866"},"schema_version":"1.0","source":{"id":"2504.16137","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16137","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16137v2","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16137","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"O6TY3QG3NJHM","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"pith_short_16","alias_value":"O6TY3QG3NJHM6GTV","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"pith_short_8","alias_value":"O6TY3QG3","created_at":"2026-07-05T10:55:34Z"}],"graph_snapshots":[{"event_id":"sha256:267af5a31fe6cbf6d6d89507f74a5cb9b065dddf0b54f801062fe697ebb23df4","target":"graph","created_at":"2026-07-05T10:55:34Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.16137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dan Hendrycks, Jasper G\\\"otting, Jon G Sanders, Karam Elabd, Lennart Justen, Long Phan, Nathaniel Li, Pedro Medeiros, Seth Donoughe","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-21T21:04:01Z","title":"Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16137","kind":"arxiv","version":2},"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:a09f360651cc62964cdc313b78791a5b33a47b3a22e20da5d1b5ce2768a32058","target":"record","created_at":"2026-07-05T10:55:34Z","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":"0466a6da5a773950c3459e2c1a57012e2a17df2e9b709ea26507eb8f761dd325","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-21T21:04:01Z","title_canon_sha256":"8f4d0bc483b16a6ce50ceacc961a1affe48db096579006803737378533074866"},"schema_version":"1.0","source":{"id":"2504.16137","kind":"arxiv","version":2}},"canonical_sha256":"77a78dc0db6a4ecf1a7581fbb3d200a824352b9a88ad39f11c41c92230c8c2cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77a78dc0db6a4ecf1a7581fbb3d200a824352b9a88ad39f11c41c92230c8c2cf","first_computed_at":"2026-07-05T10:55:34.876813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:34.876813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eBjpcPji7K0Dh1dUH4nVY6dARjRfykMe7Nz3IphXmv7rd1egF9TFI4A0WQZRoEJr5/Xydkybt6h7n88Qm9zeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:34.877284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16137","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a09f360651cc62964cdc313b78791a5b33a47b3a22e20da5d1b5ce2768a32058","sha256:267af5a31fe6cbf6d6d89507f74a5cb9b065dddf0b54f801062fe697ebb23df4"],"state_sha256":"1944e042536a891c8bd713316aa4eb5f7369fab69f390ac9540521fa6d72b70f"}