{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VCFIEOJGVVPO6PFYN7CYUVPWEF","short_pith_number":"pith:VCFIEOJG","canonical_record":{"source":{"id":"2308.14089","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-27T12:24:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"db66e3ebe70b28105cbd46bc5ef761c304e699078c32807f18ac83aa61444d09","abstract_canon_sha256":"7403efc35b4d03c121e76b97218a53b9a3df1edfcad0a820ea1a9f45749303ad"},"schema_version":"1.0"},"canonical_sha256":"a88a823926ad5eef3cb86fc58a55f62174cafc363dddd019391a4bd1d21f3459","source":{"kind":"arxiv","id":"2308.14089","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14089","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14089v2","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14089","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"pith_short_12","alias_value":"VCFIEOJGVVPO","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"pith_short_16","alias_value":"VCFIEOJGVVPO6PFY","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"pith_short_8","alias_value":"VCFIEOJG","created_at":"2026-07-05T07:27:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VCFIEOJGVVPO6PFYN7CYUVPWEF","target":"record","payload":{"canonical_record":{"source":{"id":"2308.14089","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-27T12:24:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"db66e3ebe70b28105cbd46bc5ef761c304e699078c32807f18ac83aa61444d09","abstract_canon_sha256":"7403efc35b4d03c121e76b97218a53b9a3df1edfcad0a820ea1a9f45749303ad"},"schema_version":"1.0"},"canonical_sha256":"a88a823926ad5eef3cb86fc58a55f62174cafc363dddd019391a4bd1d21f3459","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:49.806678Z","signature_b64":"gW8OyVuvnq2YMTqGb3MtqYaidQ3wycyNw+YMjW7jJEMJ4KhJ3VTD8m+7bEPlJLjUqXrE02e/cbdgrkAjDVkSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a88a823926ad5eef3cb86fc58a55f62174cafc363dddd019391a4bd1d21f3459","last_reissued_at":"2026-07-05T07:27:49.806138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:49.806138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.14089","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":"2026-07-05T07:27:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBgCZx7LSsdnTYvFwcqi7s37iILno6dC33e47QNZxHKq5GsA6GRC/vauwYP5KubNR6L9+nt1tE3M7SqThGERAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:31:13.400413Z"},"content_sha256":"b4ad55495f954b2183e31515993981a1931e16c49663e5e37b5b6f3cb8445c68","schema_version":"1.0","event_id":"sha256:b4ad55495f954b2183e31515993981a1931e16c49663e5e37b5b6f3cb8445c68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VCFIEOJGVVPO6PFYN7CYUVPWEF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshay S. Chaudhari, Alejandro Lozano, Alison Callahan, Ashwin Nayak, Birju S. Patel, Chia-Chun Chiang, Christopher Sharp, Eduardo P. Reis, Emma P. Brunskill, Ethan Goh, Ethan Steinberg, Jason A. Fries, Jenelle A. Jindal, Jonathan H. Chen, Julian Z. Genkins, Keith E. Morse, Louis Blankemeier, Michael A. Pfeffer, Nigam H. Shah, Nima Aghaeepour, Oluseyi Fayanju, Percy Liang, Rahul Thapa, Scott J. Adams, Scott L. Fleming, Sergios Gatidis, Shreya J. Shah, Thomas Savage, William J. Haberkorn, Zepeng Huo","submitted_at":"2023-08-27T12:24:39Z","abstract_excerpt":"The ability of large language models (LLMs) to follow natural language instructions with human-level fluency suggests many opportunities in healthcare to reduce administrative burden and improve quality of care. However, evaluating LLMs on realistic text generation tasks for healthcare remains challenging. Existing question answering datasets for electronic health record (EHR) data fail to capture the complexity of information needs and documentation burdens experienced by clinicians. To address these challenges, we introduce MedAlign, a benchmark dataset of 983 natural language instructions f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14089","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/2308.14089/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":"2026-07-05T07:27:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5fFGVhY0pT6/xWzH/YBxpXao/1oJMVAVdbbYojtYVMFADx2vSiauol3GWOXmR0Z2voOHDiae8p/s7GsPSvlPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:31:13.400793Z"},"content_sha256":"da9186c1e88b0a31f2af29082db65eb7b12e5295a1adf45326e81e50e4e9cd1b","schema_version":"1.0","event_id":"sha256:da9186c1e88b0a31f2af29082db65eb7b12e5295a1adf45326e81e50e4e9cd1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VCFIEOJGVVPO6PFYN7CYUVPWEF/bundle.json","state_url":"https://pith.science/pith/VCFIEOJGVVPO6PFYN7CYUVPWEF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VCFIEOJGVVPO6PFYN7CYUVPWEF/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":"2026-07-06T10:31:13Z","links":{"resolver":"https://pith.science/pith/VCFIEOJGVVPO6PFYN7CYUVPWEF","bundle":"https://pith.science/pith/VCFIEOJGVVPO6PFYN7CYUVPWEF/bundle.json","state":"https://pith.science/pith/VCFIEOJGVVPO6PFYN7CYUVPWEF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VCFIEOJGVVPO6PFYN7CYUVPWEF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VCFIEOJGVVPO6PFYN7CYUVPWEF","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":"7403efc35b4d03c121e76b97218a53b9a3df1edfcad0a820ea1a9f45749303ad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-27T12:24:39Z","title_canon_sha256":"db66e3ebe70b28105cbd46bc5ef761c304e699078c32807f18ac83aa61444d09"},"schema_version":"1.0","source":{"id":"2308.14089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14089","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14089v2","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14089","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"pith_short_12","alias_value":"VCFIEOJGVVPO","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"pith_short_16","alias_value":"VCFIEOJGVVPO6PFY","created_at":"2026-07-05T07:27:49Z"},{"alias_kind":"pith_short_8","alias_value":"VCFIEOJG","created_at":"2026-07-05T07:27:49Z"}],"graph_snapshots":[{"event_id":"sha256:da9186c1e88b0a31f2af29082db65eb7b12e5295a1adf45326e81e50e4e9cd1b","target":"graph","created_at":"2026-07-05T07:27:49Z","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/2308.14089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability of large language models (LLMs) to follow natural language instructions with human-level fluency suggests many opportunities in healthcare to reduce administrative burden and improve quality of care. However, evaluating LLMs on realistic text generation tasks for healthcare remains challenging. Existing question answering datasets for electronic health record (EHR) data fail to capture the complexity of information needs and documentation burdens experienced by clinicians. To address these challenges, we introduce MedAlign, a benchmark dataset of 983 natural language instructions f","authors_text":"Akshay S. Chaudhari, Alejandro Lozano, Alison Callahan, Ashwin Nayak, Birju S. Patel, Chia-Chun Chiang, Christopher Sharp, Eduardo P. Reis, Emma P. Brunskill, Ethan Goh, Ethan Steinberg, Jason A. Fries, Jenelle A. Jindal, Jonathan H. Chen, Julian Z. Genkins, Keith E. Morse, Louis Blankemeier, Michael A. Pfeffer, Nigam H. Shah, Nima Aghaeepour, Oluseyi Fayanju, Percy Liang, Rahul Thapa, Scott J. Adams, Scott L. Fleming, Sergios Gatidis, Shreya J. Shah, Thomas Savage, William J. Haberkorn, Zepeng Huo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-27T12:24:39Z","title":"MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14089","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:b4ad55495f954b2183e31515993981a1931e16c49663e5e37b5b6f3cb8445c68","target":"record","created_at":"2026-07-05T07:27:49Z","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":"7403efc35b4d03c121e76b97218a53b9a3df1edfcad0a820ea1a9f45749303ad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-27T12:24:39Z","title_canon_sha256":"db66e3ebe70b28105cbd46bc5ef761c304e699078c32807f18ac83aa61444d09"},"schema_version":"1.0","source":{"id":"2308.14089","kind":"arxiv","version":2}},"canonical_sha256":"a88a823926ad5eef3cb86fc58a55f62174cafc363dddd019391a4bd1d21f3459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a88a823926ad5eef3cb86fc58a55f62174cafc363dddd019391a4bd1d21f3459","first_computed_at":"2026-07-05T07:27:49.806138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:49.806138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gW8OyVuvnq2YMTqGb3MtqYaidQ3wycyNw+YMjW7jJEMJ4KhJ3VTD8m+7bEPlJLjUqXrE02e/cbdgrkAjDVkSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:49.806678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.14089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4ad55495f954b2183e31515993981a1931e16c49663e5e37b5b6f3cb8445c68","sha256:da9186c1e88b0a31f2af29082db65eb7b12e5295a1adf45326e81e50e4e9cd1b"],"state_sha256":"8401ca1a94f0a73b156aaf2c4485cd62c95bb50b3af5d07f1780f2f4a69d1a7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8p+y1j977Sd5w3Mvh/qfJxJMDCDVnBrwiNENZ4w7yYFH2mxeCV7G74kqj736wa/rSBdgWdhOWMlQKj6JBa4yDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:31:13.402827Z","bundle_sha256":"5cc0205327f85a57d8ee1a0e4ec2255d08a9ef7328c781b9e32d67003517780b"}}