{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RY53GOTEC6L24RBXCVN6D2QU5H","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":"7a393126dc4b254f60c0b5ad98a11939cc6a7205617b1e9fb39d40903244a2e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T22:42:33Z","title_canon_sha256":"9f704fde3ee58d346fc0604b2d0e293aafd786bb80eb6759e710818ee07b958b"},"schema_version":"1.0","source":{"id":"2505.14963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14963","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14963v1","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14963","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_12","alias_value":"RY53GOTEC6L2","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_16","alias_value":"RY53GOTEC6L24RBX","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_8","alias_value":"RY53GOTE","created_at":"2026-07-05T11:06:38Z"}],"graph_snapshots":[{"event_id":"sha256:bad4c57b244a53ac7b060271ecee96b15981800295a2ce35dfd0c2f65b03f666","target":"graph","created_at":"2026-07-05T11:06:38Z","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/2505.14963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly envisioned as decision-support tools in clinical practice, yet safe clinical reasoning demands integrating heterogeneous knowledge bases -- trials, primary studies, regulatory documents, and cost data -- under strict accuracy constraints. Existing evaluations often rely on synthetic prompts, reduce the task to single-hop factoid queries, or conflate reasoning with open-ended generation, leaving their real-world utility unclear. To close this gap, we present MedBrowseComp, the first benchmark that systematically tests an agent's ability to reliably ","authors_text":"Danielle S. Bitterman, Hugo Aerts, Jack Gallifant, Jeremy Warner, Pedro Moreira, Sam Schmidgall, Shan Chen, Thomas Hartvigsen, Yuxin Xiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T22:42:33Z","title":"MedBrowseComp: Benchmarking Medical Deep Research and Computer Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14963","kind":"arxiv","version":1},"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":"sha256:4112ef33c94e044b156b81ad7538cc6f679c5819acb4ec970cb62ab50484934c","target":"record","created_at":"2026-07-05T11:06:38Z","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":"7a393126dc4b254f60c0b5ad98a11939cc6a7205617b1e9fb39d40903244a2e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T22:42:33Z","title_canon_sha256":"9f704fde3ee58d346fc0604b2d0e293aafd786bb80eb6759e710818ee07b958b"},"schema_version":"1.0","source":{"id":"2505.14963","kind":"arxiv","version":1}},"canonical_sha256":"8e3bb33a641797ae4437155be1ea14e9ef68c1fb264b3715823e52b814087921","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e3bb33a641797ae4437155be1ea14e9ef68c1fb264b3715823e52b814087921","first_computed_at":"2026-07-05T11:06:38.411908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:38.411908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZSry6zr93gXd+9hDIkEzgrALeTv9izSn19/Fg8mSYBWz7stL6ss9m+B4gaPpUbG3pmEu/QnpHFPVDwO1ouECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:38.412402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4112ef33c94e044b156b81ad7538cc6f679c5819acb4ec970cb62ab50484934c","sha256:bad4c57b244a53ac7b060271ecee96b15981800295a2ce35dfd0c2f65b03f666"],"state_sha256":"2acc8bbb34716a7345642f5a875e3a855fd3d24333cd9a743fd81ba9efd3da3f"}