{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4E3QJ3Q3FGYJYYPQC5CT3DCGKE","short_pith_number":"pith:4E3QJ3Q3","canonical_record":{"source":{"id":"2406.06331","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T14:47:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4fb4ed0a71537786925f34290cf274f57dc61ead5120e6cc2b1c0f872613bd28","abstract_canon_sha256":"699f766724c2fe42d46f1b310a9db6374d65f54db844e39efe6eebb26ff05674"},"schema_version":"1.0"},"canonical_sha256":"e13704ee1b29b09c61f017453d8c46510d812ea5875cb5933268535baa8e92ed","source":{"kind":"arxiv","id":"2406.06331","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06331","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06331v2","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06331","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"4E3QJ3Q3FGYJ","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"pith_short_16","alias_value":"4E3QJ3Q3FGYJYYPQ","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"pith_short_8","alias_value":"4E3QJ3Q3","created_at":"2026-07-05T08:39:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4E3QJ3Q3FGYJYYPQC5CT3DCGKE","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06331","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T14:47:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4fb4ed0a71537786925f34290cf274f57dc61ead5120e6cc2b1c0f872613bd28","abstract_canon_sha256":"699f766724c2fe42d46f1b310a9db6374d65f54db844e39efe6eebb26ff05674"},"schema_version":"1.0"},"canonical_sha256":"e13704ee1b29b09c61f017453d8c46510d812ea5875cb5933268535baa8e92ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:34.912264Z","signature_b64":"QTzreFY4+7VxsTqUXNcUt3NT+nOzS+6hUNxEcSPBAUeBlMjUYeIC5avvx7ivZ2k35YaUjObCpyhpmW6z1pS8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e13704ee1b29b09c61f017453d8c46510d812ea5875cb5933268535baa8e92ed","last_reissued_at":"2026-07-05T08:39:34.911833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:34.911833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06331","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66UDeiYooMWwlZVbMi/VEGDicwFM9cTElb7gOe+xUpulKnquD/2V6oVuSrGInMI6bffVIVVL70/8p6LWch9VDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:33.856614Z"},"content_sha256":"0a3d7829a91c521fc75c47bdb1742fcf50a0173afaf62e71ae4a849ecd90ac5c","schema_version":"1.0","event_id":"sha256:0a3d7829a91c521fc75c47bdb1742fcf50a0173afaf62e71ae4a849ecd90ac5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4E3QJ3Q3FGYJYYPQC5CT3DCGKE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedExQA: Medical Question Answering Benchmark with Multiple Explanations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Honghan Wu, Jinge Wu, Yunsoo Kim, Yusuf Abdulle","submitted_at":"2024-06-10T14:47:04Z","abstract_excerpt":"This paper introduces MedExQA, a novel benchmark in medical question-answering, to evaluate large language models' (LLMs) understanding of medical knowledge through explanations. By constructing datasets across five distinct medical specialties that are underrepresented in current datasets and further incorporating multiple explanations for each question-answer pair, we address a major gap in current medical QA benchmarks which is the absence of comprehensive assessments of LLMs' ability to generate nuanced medical explanations. Our work highlights the importance of explainability in medical L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06331","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/2406.06331/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":"2026-07-05T08:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbsvHnsKq/DZzCeuk/1xEP3HOFKegmvVVawZd6BdYaMgoWv9RvA2oNA+yScY82JAD74mfdvM22qeHOxq47OADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:33.857129Z"},"content_sha256":"932daefed8bd6a1803d8dfb2d81c29e2f7a2d4b22b15f9f8d36d0426f638a219","schema_version":"1.0","event_id":"sha256:932daefed8bd6a1803d8dfb2d81c29e2f7a2d4b22b15f9f8d36d0426f638a219"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4E3QJ3Q3FGYJYYPQC5CT3DCGKE/bundle.json","state_url":"https://pith.science/pith/4E3QJ3Q3FGYJYYPQC5CT3DCGKE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4E3QJ3Q3FGYJYYPQC5CT3DCGKE/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":"2026-08-08T13:12:33Z","links":{"resolver":"https://pith.science/pith/4E3QJ3Q3FGYJYYPQC5CT3DCGKE","bundle":"https://pith.science/pith/4E3QJ3Q3FGYJYYPQC5CT3DCGKE/bundle.json","state":"https://pith.science/pith/4E3QJ3Q3FGYJYYPQC5CT3DCGKE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4E3QJ3Q3FGYJYYPQC5CT3DCGKE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4E3QJ3Q3FGYJYYPQC5CT3DCGKE","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":"699f766724c2fe42d46f1b310a9db6374d65f54db844e39efe6eebb26ff05674","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T14:47:04Z","title_canon_sha256":"4fb4ed0a71537786925f34290cf274f57dc61ead5120e6cc2b1c0f872613bd28"},"schema_version":"1.0","source":{"id":"2406.06331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06331","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06331v2","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06331","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"4E3QJ3Q3FGYJ","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"pith_short_16","alias_value":"4E3QJ3Q3FGYJYYPQ","created_at":"2026-07-05T08:39:34Z"},{"alias_kind":"pith_short_8","alias_value":"4E3QJ3Q3","created_at":"2026-07-05T08:39:34Z"}],"graph_snapshots":[{"event_id":"sha256:932daefed8bd6a1803d8dfb2d81c29e2f7a2d4b22b15f9f8d36d0426f638a219","target":"graph","created_at":"2026-07-05T08:39:34Z","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/2406.06331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces MedExQA, a novel benchmark in medical question-answering, to evaluate large language models' (LLMs) understanding of medical knowledge through explanations. By constructing datasets across five distinct medical specialties that are underrepresented in current datasets and further incorporating multiple explanations for each question-answer pair, we address a major gap in current medical QA benchmarks which is the absence of comprehensive assessments of LLMs' ability to generate nuanced medical explanations. Our work highlights the importance of explainability in medical L","authors_text":"Honghan Wu, Jinge Wu, Yunsoo Kim, Yusuf Abdulle","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T14:47:04Z","title":"MedExQA: Medical Question Answering Benchmark with Multiple Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06331","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":"sha256:0a3d7829a91c521fc75c47bdb1742fcf50a0173afaf62e71ae4a849ecd90ac5c","target":"record","created_at":"2026-07-05T08:39:34Z","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":"699f766724c2fe42d46f1b310a9db6374d65f54db844e39efe6eebb26ff05674","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T14:47:04Z","title_canon_sha256":"4fb4ed0a71537786925f34290cf274f57dc61ead5120e6cc2b1c0f872613bd28"},"schema_version":"1.0","source":{"id":"2406.06331","kind":"arxiv","version":2}},"canonical_sha256":"e13704ee1b29b09c61f017453d8c46510d812ea5875cb5933268535baa8e92ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e13704ee1b29b09c61f017453d8c46510d812ea5875cb5933268535baa8e92ed","first_computed_at":"2026-07-05T08:39:34.911833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:34.911833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QTzreFY4+7VxsTqUXNcUt3NT+nOzS+6hUNxEcSPBAUeBlMjUYeIC5avvx7ivZ2k35YaUjObCpyhpmW6z1pS8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:34.912264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a3d7829a91c521fc75c47bdb1742fcf50a0173afaf62e71ae4a849ecd90ac5c","sha256:932daefed8bd6a1803d8dfb2d81c29e2f7a2d4b22b15f9f8d36d0426f638a219"],"state_sha256":"0347e513026afb5675f011c77fb75f1c32cbd35c00deb0584035933f2ecb3061"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4n5rKjhE2GiLn73+2CMq4CuATusZ6L8I3JWySKXHA9+s2cQHEKUri8V1QTmO0isOoMuMNNRcgfdvUz2dBvOYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:12:33.860934Z","bundle_sha256":"23dc02e6ad7e469c552dbd85c7cb323b154a108cba1d777701c3c662231f18eb"}}