{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VY3YVO65MYDQ6QPGPV6XOQMJZI","short_pith_number":"pith:VY3YVO65","canonical_record":{"source":{"id":"2404.15894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T14:32:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b43e0c7a87d79232b52e2fec4e7a7baee725a78f19be92f98444f60b7f3fca","abstract_canon_sha256":"48bd64be88250ced11632a3cf18af7b83349d473c1a78f49bd369fc47a10e8a7"},"schema_version":"1.0"},"canonical_sha256":"ae378abbdd66070f41e67d7d774189ca1de9da516619529b0e3e87970aa55d49","source":{"kind":"arxiv","id":"2404.15894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15894","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15894v1","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15894","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"pith_short_12","alias_value":"VY3YVO65MYDQ","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"pith_short_16","alias_value":"VY3YVO65MYDQ6QPG","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"pith_short_8","alias_value":"VY3YVO65","created_at":"2026-07-05T08:11:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VY3YVO65MYDQ6QPGPV6XOQMJZI","target":"record","payload":{"canonical_record":{"source":{"id":"2404.15894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T14:32:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b43e0c7a87d79232b52e2fec4e7a7baee725a78f19be92f98444f60b7f3fca","abstract_canon_sha256":"48bd64be88250ced11632a3cf18af7b83349d473c1a78f49bd369fc47a10e8a7"},"schema_version":"1.0"},"canonical_sha256":"ae378abbdd66070f41e67d7d774189ca1de9da516619529b0e3e87970aa55d49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:47.041001Z","signature_b64":"yj5P/tWheOPyI/VqVIhQWpPMYagWIYUEG5jNrcGtjCCanMDDflWZJAo8lmNeNbXYyB0aY72XLGZqIdgY6TwmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae378abbdd66070f41e67d7d774189ca1de9da516619529b0e3e87970aa55d49","last_reissued_at":"2026-07-05T08:11:47.040621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:47.040621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.15894","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":"2026-07-05T08:11:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+68fcHLP51WxIzT2CQRkAguExYiiVJJattWf8fHKG++k7y73w21TDhawD+JE+Bk239xmFVkdhsguI7mtpuBBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:11:12.976785Z"},"content_sha256":"981e7bd426f6111effeb4cd8fa3ef3318ecc3e981276bd62fd4e58c9c5711c21","schema_version":"1.0","event_id":"sha256:981e7bd426f6111effeb4cd8fa3ef3318ecc3e981276bd62fd4e58c9c5711c21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VY3YVO65MYDQ6QPGPV6XOQMJZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing The Potential Of Mid-Sized Language Models For Clinical QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Betty Xiong, Christopher D. Manning, Elliot Bolton, Joel Schamroth, Roxana Daneshjou, Vijaytha Muralidharan, Vivek Muralidharan","submitted_at":"2024-04-24T14:32:34Z","abstract_excerpt":"Large language models, such as GPT-4 and Med-PaLM, have shown impressive performance on clinical tasks; however, they require access to compute, are closed-source, and cannot be deployed on device. Mid-size models such as BioGPT-large, BioMedLM, LLaMA 2, and Mistral 7B avoid these drawbacks, but their capacity for clinical tasks has been understudied. To help assess their potential for clinical use and help researchers decide which model they should use, we compare their performance on two clinical question-answering (QA) tasks: MedQA and consumer query answering. We find that Mistral 7B is th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15894","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/2404.15894/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":"2026-07-05T08:11:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BatB7FTGVQzdSApCZG7M93x67tHgZ+fWK3G8n+PepWfjhfYAYama12mV1gi5kInI9LEDfMA/UY+F/Amoq/5iBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:11:12.977275Z"},"content_sha256":"f26aa7316f15ce1d8a83c2c5cca962ecae2e44a3d970d0fcca52f55126e5941d","schema_version":"1.0","event_id":"sha256:f26aa7316f15ce1d8a83c2c5cca962ecae2e44a3d970d0fcca52f55126e5941d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VY3YVO65MYDQ6QPGPV6XOQMJZI/bundle.json","state_url":"https://pith.science/pith/VY3YVO65MYDQ6QPGPV6XOQMJZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VY3YVO65MYDQ6QPGPV6XOQMJZI/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":"2026-08-22T22:11:12Z","links":{"resolver":"https://pith.science/pith/VY3YVO65MYDQ6QPGPV6XOQMJZI","bundle":"https://pith.science/pith/VY3YVO65MYDQ6QPGPV6XOQMJZI/bundle.json","state":"https://pith.science/pith/VY3YVO65MYDQ6QPGPV6XOQMJZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VY3YVO65MYDQ6QPGPV6XOQMJZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VY3YVO65MYDQ6QPGPV6XOQMJZI","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":"48bd64be88250ced11632a3cf18af7b83349d473c1a78f49bd369fc47a10e8a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T14:32:34Z","title_canon_sha256":"84b43e0c7a87d79232b52e2fec4e7a7baee725a78f19be92f98444f60b7f3fca"},"schema_version":"1.0","source":{"id":"2404.15894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15894","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15894v1","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15894","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"pith_short_12","alias_value":"VY3YVO65MYDQ","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"pith_short_16","alias_value":"VY3YVO65MYDQ6QPG","created_at":"2026-07-05T08:11:47Z"},{"alias_kind":"pith_short_8","alias_value":"VY3YVO65","created_at":"2026-07-05T08:11:47Z"}],"graph_snapshots":[{"event_id":"sha256:f26aa7316f15ce1d8a83c2c5cca962ecae2e44a3d970d0fcca52f55126e5941d","target":"graph","created_at":"2026-07-05T08:11:47Z","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/2404.15894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models, such as GPT-4 and Med-PaLM, have shown impressive performance on clinical tasks; however, they require access to compute, are closed-source, and cannot be deployed on device. Mid-size models such as BioGPT-large, BioMedLM, LLaMA 2, and Mistral 7B avoid these drawbacks, but their capacity for clinical tasks has been understudied. To help assess their potential for clinical use and help researchers decide which model they should use, we compare their performance on two clinical question-answering (QA) tasks: MedQA and consumer query answering. We find that Mistral 7B is th","authors_text":"Betty Xiong, Christopher D. Manning, Elliot Bolton, Joel Schamroth, Roxana Daneshjou, Vijaytha Muralidharan, Vivek Muralidharan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T14:32:34Z","title":"Assessing The Potential Of Mid-Sized Language Models For Clinical QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15894","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":"sha256:981e7bd426f6111effeb4cd8fa3ef3318ecc3e981276bd62fd4e58c9c5711c21","target":"record","created_at":"2026-07-05T08:11:47Z","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":"48bd64be88250ced11632a3cf18af7b83349d473c1a78f49bd369fc47a10e8a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T14:32:34Z","title_canon_sha256":"84b43e0c7a87d79232b52e2fec4e7a7baee725a78f19be92f98444f60b7f3fca"},"schema_version":"1.0","source":{"id":"2404.15894","kind":"arxiv","version":1}},"canonical_sha256":"ae378abbdd66070f41e67d7d774189ca1de9da516619529b0e3e87970aa55d49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae378abbdd66070f41e67d7d774189ca1de9da516619529b0e3e87970aa55d49","first_computed_at":"2026-07-05T08:11:47.040621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:47.040621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yj5P/tWheOPyI/VqVIhQWpPMYagWIYUEG5jNrcGtjCCanMDDflWZJAo8lmNeNbXYyB0aY72XLGZqIdgY6TwmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:47.041001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:981e7bd426f6111effeb4cd8fa3ef3318ecc3e981276bd62fd4e58c9c5711c21","sha256:f26aa7316f15ce1d8a83c2c5cca962ecae2e44a3d970d0fcca52f55126e5941d"],"state_sha256":"71460772adf9f3036be49014009b0eb4758c2d009a66ccf4e64552b8d2986314"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2xpS15zRG+DTecYE7CaJwKoIamrNOeRzXAqY+aKMl4LHL6bpEakOhm7nERX37S3DX7FoFr1zMGupyeyApWpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:11:12.982232Z","bundle_sha256":"182765940f274d8fb1845e9ec44c581b748da316343e5d88ae48f837c8d8b5dc"}}