{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WUVDLOGMNX3XCDW6EEVM7ZHEPF","short_pith_number":"pith:WUVDLOGM","canonical_record":{"source":{"id":"2506.00612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T15:51:09Z","cross_cats_sorted":[],"title_canon_sha256":"570f7d2f5af253ff7bc1c09ab040881f2ceec8d5e43fb329d56889b2dd2d0696","abstract_canon_sha256":"8e1f0031ab198be163e01bc08c61b7915981d7648b0a1a52729fdf79402e4162"},"schema_version":"1.0"},"canonical_sha256":"b52a35b8cc6df7710ede212acfe4e4795439b57aca0ab72fe105ba2c9e22778b","source":{"kind":"arxiv","id":"2506.00612","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00612","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00612v3","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00612","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"WUVDLOGMNX3X","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"WUVDLOGMNX3XCDW6","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"WUVDLOGM","created_at":"2026-07-05T11:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WUVDLOGMNX3XCDW6EEVM7ZHEPF","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T15:51:09Z","cross_cats_sorted":[],"title_canon_sha256":"570f7d2f5af253ff7bc1c09ab040881f2ceec8d5e43fb329d56889b2dd2d0696","abstract_canon_sha256":"8e1f0031ab198be163e01bc08c61b7915981d7648b0a1a52729fdf79402e4162"},"schema_version":"1.0"},"canonical_sha256":"b52a35b8cc6df7710ede212acfe4e4795439b57aca0ab72fe105ba2c9e22778b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:28.262973Z","signature_b64":"ou8YdvCh/uuSOHkNWvjaVZqsN1yVEm4g7DQjffemyz9IXkE/0Ke/q/9rzsODh40RLOj52ZPcUQBCPs4jm5SYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b52a35b8cc6df7710ede212acfe4e4795439b57aca0ab72fe105ba2c9e22778b","last_reissued_at":"2026-07-05T11:31:28.262489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:28.262489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00612","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eb+gPrH/yclu7zJypYK1rc7oNmfec0ohUJB+RETESyEirJ6wkS//Jmxj45Pk1J3+7/N+TwSj12bJ/VRTt7tmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:52:38.874541Z"},"content_sha256":"80255e4decaafe03fd58a2838c6127aa1323949af01ed80d6af97fc88664a76c","schema_version":"1.0","event_id":"sha256:80255e4decaafe03fd58a2838c6127aa1323949af01ed80d6af97fc88664a76c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WUVDLOGMNX3XCDW6EEVM7ZHEPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Minghui Chen, Running Yang, Wenlong Deng, Xiaoxiao Li, Yuyin Zhou","submitted_at":"2025-05-31T15:51:09Z","abstract_excerpt":"Clinical tasks such as diagnosis and treatment require strong decision-making abilities, highlighting the importance of rigorous evaluation benchmarks to assess the reliability of large language models (LLMs). In this work, we introduce a knowledge-guided data augmentation framework that enhances the difficulty of clinical multiple-choice question (MCQ) datasets by generating distractors (i.e., incorrect choices that are similar to the correct one and may confuse existing LLMs). Using our KG-based pipeline, the generated choices are both clinically plausible and deliberately misleading. Our ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00612","kind":"arxiv","version":3},"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/2506.00612/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":"2026-07-05T11:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aEPKO9RUIzboLYkR6NmfP2tN7LOCCM6ZvnqleXmhPXzhxBbgdHCvBA8xWmJ4/FHSNMi6bScjXEnOgG4L+IG0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:52:38.875080Z"},"content_sha256":"e8eefb2a7f49f32b7e51eb738749f203e3b448f169e2b27f6f0aca01f8382e9b","schema_version":"1.0","event_id":"sha256:e8eefb2a7f49f32b7e51eb738749f203e3b448f169e2b27f6f0aca01f8382e9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/bundle.json","state_url":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/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":"2026-08-08T01:52:38Z","links":{"resolver":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF","bundle":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/bundle.json","state":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WUVDLOGMNX3XCDW6EEVM7ZHEPF","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":"8e1f0031ab198be163e01bc08c61b7915981d7648b0a1a52729fdf79402e4162","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T15:51:09Z","title_canon_sha256":"570f7d2f5af253ff7bc1c09ab040881f2ceec8d5e43fb329d56889b2dd2d0696"},"schema_version":"1.0","source":{"id":"2506.00612","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00612","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00612v3","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00612","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"WUVDLOGMNX3X","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"WUVDLOGMNX3XCDW6","created_at":"2026-07-05T11:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"WUVDLOGM","created_at":"2026-07-05T11:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:e8eefb2a7f49f32b7e51eb738749f203e3b448f169e2b27f6f0aca01f8382e9b","target":"graph","created_at":"2026-07-05T11:31:28Z","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/2506.00612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical tasks such as diagnosis and treatment require strong decision-making abilities, highlighting the importance of rigorous evaluation benchmarks to assess the reliability of large language models (LLMs). In this work, we introduce a knowledge-guided data augmentation framework that enhances the difficulty of clinical multiple-choice question (MCQ) datasets by generating distractors (i.e., incorrect choices that are similar to the correct one and may confuse existing LLMs). Using our KG-based pipeline, the generated choices are both clinically plausible and deliberately misleading. Our ap","authors_text":"Minghui Chen, Running Yang, Wenlong Deng, Xiaoxiao Li, Yuyin Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T15:51:09Z","title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00612","kind":"arxiv","version":3},"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":"sha256:80255e4decaafe03fd58a2838c6127aa1323949af01ed80d6af97fc88664a76c","target":"record","created_at":"2026-07-05T11:31:28Z","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":"8e1f0031ab198be163e01bc08c61b7915981d7648b0a1a52729fdf79402e4162","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T15:51:09Z","title_canon_sha256":"570f7d2f5af253ff7bc1c09ab040881f2ceec8d5e43fb329d56889b2dd2d0696"},"schema_version":"1.0","source":{"id":"2506.00612","kind":"arxiv","version":3}},"canonical_sha256":"b52a35b8cc6df7710ede212acfe4e4795439b57aca0ab72fe105ba2c9e22778b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b52a35b8cc6df7710ede212acfe4e4795439b57aca0ab72fe105ba2c9e22778b","first_computed_at":"2026-07-05T11:31:28.262489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:28.262489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ou8YdvCh/uuSOHkNWvjaVZqsN1yVEm4g7DQjffemyz9IXkE/0Ke/q/9rzsODh40RLOj52ZPcUQBCPs4jm5SYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:28.262973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00612","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80255e4decaafe03fd58a2838c6127aa1323949af01ed80d6af97fc88664a76c","sha256:e8eefb2a7f49f32b7e51eb738749f203e3b448f169e2b27f6f0aca01f8382e9b"],"state_sha256":"80f16ba8ed31e78656252baf52f691cd05499280bd4bbf529805502cf1d72008"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"suWHKlkSa7sNv94fvFvxhVtLtUZYobjkLJmCMwpRifPus13hibxZOcG6iVAWmExjgWA6ahZo0LoRFazYO+0ZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:52:38.915892Z","bundle_sha256":"2c9ee35b65e04054152812450e3b69b4fff875f50984e6efe271886d4df181f2"}}