{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U2LRXCCDH7K4O5BXQZKVTOCNZ2","short_pith_number":"pith:U2LRXCCD","canonical_record":{"source":{"id":"2505.11613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:21:52Z","cross_cats_sorted":[],"title_canon_sha256":"d23063d3e69f10cfc20ef3fa3883c6f126a07ded3bd4c2f7c4dd9bc0ddb4399b","abstract_canon_sha256":"4eb54a5f7b4e5573099e67676602c702e373b0aac32bb39e24caac3e06012565"},"schema_version":"1.0"},"canonical_sha256":"a6971b88433fd5c77437865559b84dcea405d9b8114149c3f2eff368e689f72e","source":{"kind":"arxiv","id":"2505.11613","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11613","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11613v1","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11613","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"U2LRXCCDH7K4","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"U2LRXCCDH7K4O5BX","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"U2LRXCCD","created_at":"2026-07-05T11:04:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U2LRXCCDH7K4O5BXQZKVTOCNZ2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:21:52Z","cross_cats_sorted":[],"title_canon_sha256":"d23063d3e69f10cfc20ef3fa3883c6f126a07ded3bd4c2f7c4dd9bc0ddb4399b","abstract_canon_sha256":"4eb54a5f7b4e5573099e67676602c702e373b0aac32bb39e24caac3e06012565"},"schema_version":"1.0"},"canonical_sha256":"a6971b88433fd5c77437865559b84dcea405d9b8114149c3f2eff368e689f72e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:24.432536Z","signature_b64":"3SF4f4cfYE4SVX3f4w7Dd80+9evfsz/YOeRe9bcjcl9oVHvdfVkkyVq3SIcU5sxb/SVryKZaXUy3iR74ylCjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6971b88433fd5c77437865559b84dcea405d9b8114149c3f2eff368e689f72e","last_reissued_at":"2026-07-05T11:04:24.431993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:24.431993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11613","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f5eyl72hMWi2ucf6B+Lz7DZHoG5/wQtkdQmM6e7eouPT/sorE2D7yvMPU9o+VIMYxF5LkJwmlMVQOUjuM810DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:15:04.738965Z"},"content_sha256":"b62f17c2b871274dba1f06c9709b29c40a4c7dc197ff2f532f7ff62131a1fa63","schema_version":"1.0","event_id":"sha256:b62f17c2b871274dba1f06c9709b29c40a4c7dc197ff2f532f7ff62131a1fa63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U2LRXCCDH7K4O5BXQZKVTOCNZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangya Wan, Mingye Gao, Taoran Li, Xiaomin Li, Yijun Wang, Yuexing Hao, Zihan Wang","submitted_at":"2025-05-16T18:21:52Z","abstract_excerpt":"Clinical guidelines, typically structured as decision trees, are central to evidence-based medical practice and critical for ensuring safe and accurate diagnostic decision-making. However, it remains unclear whether Large Language Models (LLMs) can reliably follow such structured protocols. In this work, we introduce MedGUIDE, a new benchmark for evaluating LLMs on their ability to make guideline-consistent clinical decisions. MedGUIDE is constructed from 55 curated NCCN decision trees across 17 cancer types and uses clinical scenarios generated by LLMs to create a large pool of multiple-choic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11613","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/2505.11613/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYH6NtDjmSbJzB8IHrkKksGu0hLu0ITqWMWXB5v9bfkWgoXmtC2yLrP6SOaq193p4fVa4tuQ9yfowcQ3mE0BAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:15:04.739486Z"},"content_sha256":"6823a5507cce418869438eb4b3ae89d2cf682d40f41437cd577f079454ed34a5","schema_version":"1.0","event_id":"sha256:6823a5507cce418869438eb4b3ae89d2cf682d40f41437cd577f079454ed34a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U2LRXCCDH7K4O5BXQZKVTOCNZ2/bundle.json","state_url":"https://pith.science/pith/U2LRXCCDH7K4O5BXQZKVTOCNZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U2LRXCCDH7K4O5BXQZKVTOCNZ2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T03:15:04Z","links":{"resolver":"https://pith.science/pith/U2LRXCCDH7K4O5BXQZKVTOCNZ2","bundle":"https://pith.science/pith/U2LRXCCDH7K4O5BXQZKVTOCNZ2/bundle.json","state":"https://pith.science/pith/U2LRXCCDH7K4O5BXQZKVTOCNZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U2LRXCCDH7K4O5BXQZKVTOCNZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U2LRXCCDH7K4O5BXQZKVTOCNZ2","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":"4eb54a5f7b4e5573099e67676602c702e373b0aac32bb39e24caac3e06012565","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:21:52Z","title_canon_sha256":"d23063d3e69f10cfc20ef3fa3883c6f126a07ded3bd4c2f7c4dd9bc0ddb4399b"},"schema_version":"1.0","source":{"id":"2505.11613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11613","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11613v1","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11613","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"U2LRXCCDH7K4","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"U2LRXCCDH7K4O5BX","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"U2LRXCCD","created_at":"2026-07-05T11:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:6823a5507cce418869438eb4b3ae89d2cf682d40f41437cd577f079454ed34a5","target":"graph","created_at":"2026-07-05T11:04:24Z","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/2505.11613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical guidelines, typically structured as decision trees, are central to evidence-based medical practice and critical for ensuring safe and accurate diagnostic decision-making. However, it remains unclear whether Large Language Models (LLMs) can reliably follow such structured protocols. In this work, we introduce MedGUIDE, a new benchmark for evaluating LLMs on their ability to make guideline-consistent clinical decisions. MedGUIDE is constructed from 55 curated NCCN decision trees across 17 cancer types and uses clinical scenarios generated by LLMs to create a large pool of multiple-choic","authors_text":"Guangya Wan, Mingye Gao, Taoran Li, Xiaomin Li, Yijun Wang, Yuexing Hao, Zihan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:21:52Z","title":"MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11613","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:b62f17c2b871274dba1f06c9709b29c40a4c7dc197ff2f532f7ff62131a1fa63","target":"record","created_at":"2026-07-05T11:04:24Z","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":"4eb54a5f7b4e5573099e67676602c702e373b0aac32bb39e24caac3e06012565","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:21:52Z","title_canon_sha256":"d23063d3e69f10cfc20ef3fa3883c6f126a07ded3bd4c2f7c4dd9bc0ddb4399b"},"schema_version":"1.0","source":{"id":"2505.11613","kind":"arxiv","version":1}},"canonical_sha256":"a6971b88433fd5c77437865559b84dcea405d9b8114149c3f2eff368e689f72e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6971b88433fd5c77437865559b84dcea405d9b8114149c3f2eff368e689f72e","first_computed_at":"2026-07-05T11:04:24.431993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:24.431993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3SF4f4cfYE4SVX3f4w7Dd80+9evfsz/YOeRe9bcjcl9oVHvdfVkkyVq3SIcU5sxb/SVryKZaXUy3iR74ylCjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:24.432536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b62f17c2b871274dba1f06c9709b29c40a4c7dc197ff2f532f7ff62131a1fa63","sha256:6823a5507cce418869438eb4b3ae89d2cf682d40f41437cd577f079454ed34a5"],"state_sha256":"078b2c29e96fee8d3687d94cfd26d53c42ca944963129c878ac25c3c39f5b337"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kAxHMLNUDz+cPlZIaR4CZoe0Vg9BTYRYO9X2gmjV+AmD1cCJsUtohTlqbhJMnfGDAPUlz9sUwxGpj89i58zBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:15:04.744806Z","bundle_sha256":"644d909be143e8066290431ab0432a44125dc8feb00b639c605e06ccca18437c"}}