{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SXYTBC4DY7JXLK7FELVMTP7UGN","short_pith_number":"pith:SXYTBC4D","canonical_record":{"source":{"id":"2411.09834","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T22:54:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df3d141f5bb2d1d58b4222d69e5217827834019c0bc7e1d861ac36dc9bcfec0a","abstract_canon_sha256":"13d9c9a534509473c377035f551569168639e870c1dde85b3eab999a2cb9f2b9"},"schema_version":"1.0"},"canonical_sha256":"95f1308b83c7d375abe522eac9bff43356b5ee015de3589d63ff441af9599c7f","source":{"kind":"arxiv","id":"2411.09834","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09834","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09834v2","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09834","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"SXYTBC4DY7JX","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"SXYTBC4DY7JXLK7F","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"SXYTBC4D","created_at":"2026-07-05T09:37:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SXYTBC4DY7JXLK7FELVMTP7UGN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.09834","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T22:54:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df3d141f5bb2d1d58b4222d69e5217827834019c0bc7e1d861ac36dc9bcfec0a","abstract_canon_sha256":"13d9c9a534509473c377035f551569168639e870c1dde85b3eab999a2cb9f2b9"},"schema_version":"1.0"},"canonical_sha256":"95f1308b83c7d375abe522eac9bff43356b5ee015de3589d63ff441af9599c7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:58.297199Z","signature_b64":"FOlj1I63nlO7V0Me5xhSyUw9SxEkMjiBTGeEo6h80b/rKSGwHFMbT6+VW+CW1it9sphP3nwy6ccIi/Xp/qLZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f1308b83c7d375abe522eac9bff43356b5ee015de3589d63ff441af9599c7f","last_reissued_at":"2026-07-05T09:37:58.296651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:58.296651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.09834","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":"2026-07-05T09:37:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HVMVTzrRRdWU3S8x3EBLcBXMxh/jfMB7Wq9GDxQHCeCJegak3h8iZ3rOlTz+n0LufARMuG1oguPwZt3fYDSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:12:17.123368Z"},"content_sha256":"f3f2d5851e4ef7ffba084c350ee6348689b18c5c2b89ea5977fa778bd39611a1","schema_version":"1.0","event_id":"sha256:f3f2d5851e4ef7ffba084c350ee6348689b18c5c2b89ea5977fa778bd39611a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SXYTBC4DY7JXLK7FELVMTP7UGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Benchmark for Long-Form Medical Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Farahanchi, Bing Ren, Bryceton G. Thomas, Elnaz Nouri, Jessica M. Sin, Pedram Hosseini, Saeed Hassanpour","submitted_at":"2024-11-14T22:54:38Z","abstract_excerpt":"There is a lack of benchmarks for evaluating large language models (LLMs) in long-form medical question answering (QA). Most existing medical QA evaluation benchmarks focus on automatic metrics and multiple-choice questions. While valuable, these benchmarks fail to fully capture or assess the complexities of real-world clinical applications where LLMs are being deployed. Furthermore, existing studies on evaluating long-form answer generation in medical QA are primarily closed-source, lacking access to human medical expert annotations, which makes it difficult to reproduce results and enhance e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09834","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/2411.09834/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":"2026-07-05T09:37:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xZJf5JOu6XwLeOy5NKPdUPyqEj+syXPczmB/a77xx9W+6ehTecOw9JPFzs+onU3chSHFa6jUYNgUkuy88WaNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:12:17.124021Z"},"content_sha256":"961e5d766936ccacae1075236dabf9480b2dfb93c79e74c5443416c35c2e6f92","schema_version":"1.0","event_id":"sha256:961e5d766936ccacae1075236dabf9480b2dfb93c79e74c5443416c35c2e6f92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXYTBC4DY7JXLK7FELVMTP7UGN/bundle.json","state_url":"https://pith.science/pith/SXYTBC4DY7JXLK7FELVMTP7UGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXYTBC4DY7JXLK7FELVMTP7UGN/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":"2026-07-07T05:12:17Z","links":{"resolver":"https://pith.science/pith/SXYTBC4DY7JXLK7FELVMTP7UGN","bundle":"https://pith.science/pith/SXYTBC4DY7JXLK7FELVMTP7UGN/bundle.json","state":"https://pith.science/pith/SXYTBC4DY7JXLK7FELVMTP7UGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXYTBC4DY7JXLK7FELVMTP7UGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SXYTBC4DY7JXLK7FELVMTP7UGN","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":"13d9c9a534509473c377035f551569168639e870c1dde85b3eab999a2cb9f2b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T22:54:38Z","title_canon_sha256":"df3d141f5bb2d1d58b4222d69e5217827834019c0bc7e1d861ac36dc9bcfec0a"},"schema_version":"1.0","source":{"id":"2411.09834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09834","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09834v2","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09834","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"SXYTBC4DY7JX","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"SXYTBC4DY7JXLK7F","created_at":"2026-07-05T09:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"SXYTBC4D","created_at":"2026-07-05T09:37:58Z"}],"graph_snapshots":[{"event_id":"sha256:961e5d766936ccacae1075236dabf9480b2dfb93c79e74c5443416c35c2e6f92","target":"graph","created_at":"2026-07-05T09:37:58Z","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/2411.09834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a lack of benchmarks for evaluating large language models (LLMs) in long-form medical question answering (QA). Most existing medical QA evaluation benchmarks focus on automatic metrics and multiple-choice questions. While valuable, these benchmarks fail to fully capture or assess the complexities of real-world clinical applications where LLMs are being deployed. Furthermore, existing studies on evaluating long-form answer generation in medical QA are primarily closed-source, lacking access to human medical expert annotations, which makes it difficult to reproduce results and enhance e","authors_text":"Ali Farahanchi, Bing Ren, Bryceton G. Thomas, Elnaz Nouri, Jessica M. Sin, Pedram Hosseini, Saeed Hassanpour","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T22:54:38Z","title":"A Benchmark for Long-Form Medical Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09834","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:f3f2d5851e4ef7ffba084c350ee6348689b18c5c2b89ea5977fa778bd39611a1","target":"record","created_at":"2026-07-05T09:37:58Z","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":"13d9c9a534509473c377035f551569168639e870c1dde85b3eab999a2cb9f2b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T22:54:38Z","title_canon_sha256":"df3d141f5bb2d1d58b4222d69e5217827834019c0bc7e1d861ac36dc9bcfec0a"},"schema_version":"1.0","source":{"id":"2411.09834","kind":"arxiv","version":2}},"canonical_sha256":"95f1308b83c7d375abe522eac9bff43356b5ee015de3589d63ff441af9599c7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95f1308b83c7d375abe522eac9bff43356b5ee015de3589d63ff441af9599c7f","first_computed_at":"2026-07-05T09:37:58.296651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:58.296651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FOlj1I63nlO7V0Me5xhSyUw9SxEkMjiBTGeEo6h80b/rKSGwHFMbT6+VW+CW1it9sphP3nwy6ccIi/Xp/qLZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:58.297199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3f2d5851e4ef7ffba084c350ee6348689b18c5c2b89ea5977fa778bd39611a1","sha256:961e5d766936ccacae1075236dabf9480b2dfb93c79e74c5443416c35c2e6f92"],"state_sha256":"568a1a90c98fe50944687c9d75a5de02055782e9bd6d2b2cccf188b198147f97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1V2R8V5t6q4MTRUcGpHkP8zFvdBGLTOZY+1Awnx9AJOhlJN1ZPWBorqrwkJUmi25IpQ4FJyapEssCN4sSNsSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:12:17.128581Z","bundle_sha256":"83a85bd6238f0d5817452dc19bf4a79bbfc2bb727fedb49bbfa8d4528df1173c"}}