{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C6JOTVGLEBMOHLZXBCDFNFBV3F","short_pith_number":"pith:C6JOTVGL","canonical_record":{"source":{"id":"2505.15024","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T02:13:24Z","cross_cats_sorted":[],"title_canon_sha256":"c7a6701c06f0b45b5979470e370e48c4e3509144aabfce9d04ad95f9d0319350","abstract_canon_sha256":"fa37185db7e0721e11e3d7d5de36a5a3a96e0920e6aef370b79c872586f05952"},"schema_version":"1.0"},"canonical_sha256":"1792e9d4cb2058e3af370886569435d975d66929699ffc8c92b1bb0f1c62b851","source":{"kind":"arxiv","id":"2505.15024","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15024","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15024v2","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15024","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"C6JOTVGLEBMO","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"C6JOTVGLEBMOHLZX","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"C6JOTVGL","created_at":"2026-07-05T11:08:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C6JOTVGLEBMOHLZXBCDFNFBV3F","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15024","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T02:13:24Z","cross_cats_sorted":[],"title_canon_sha256":"c7a6701c06f0b45b5979470e370e48c4e3509144aabfce9d04ad95f9d0319350","abstract_canon_sha256":"fa37185db7e0721e11e3d7d5de36a5a3a96e0920e6aef370b79c872586f05952"},"schema_version":"1.0"},"canonical_sha256":"1792e9d4cb2058e3af370886569435d975d66929699ffc8c92b1bb0f1c62b851","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:21.284226Z","signature_b64":"HTEph2tBetVyK+6VNU9ZXg7EIes6eDZerXVRrXi2ew15Jwm7yjwywgtvao5A3iMc7rX49hqEtyO0frlR8/9RAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1792e9d4cb2058e3af370886569435d975d66929699ffc8c92b1bb0f1c62b851","last_reissued_at":"2026-07-05T11:08:21.283810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:21.283810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15024","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":"2026-07-05T11:08:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OvIt6z680LhXfSuSjvG6CO0fUjcVcdJjNrv8qzVLiub5ko1unVDgdW5943yBx5yKTLIKJg0LWScsbIAlKuL2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:07:12.643956Z"},"content_sha256":"dc3f60220f883836e6915e1c1e9d4a6381022422d023cbb419e5acb438226e0d","schema_version":"1.0","event_id":"sha256:dc3f60220f883836e6915e1c1e9d4a6381022422d023cbb419e5acb438226e0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C6JOTVGLEBMOHLZXBCDFNFBV3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diagnosing our datasets: How does my language model learn clinical information?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Sontag, Furong Jia, Monica Agrawal","submitted_at":"2025-05-21T02:13:24Z","abstract_excerpt":"Large language models (LLMs) have performed well across various clinical natural language processing tasks, despite not being directly trained on electronic health record (EHR) data. In this work, we examine how popular open-source LLMs learn clinical information from large mined corpora through two crucial but understudied lenses: (1) their interpretation of clinical jargon, a foundational ability for understanding real-world clinical notes, and (2) their responses to unsupported medical claims. For both use cases, we investigate the frequency of relevant clinical information in their corresp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15024","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/2505.15024/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":"2026-07-05T11:08:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMsNnOK4mT7Zl7aQd+LIp3sogtUP7UAMavB9O1pTnMyXCqfqSZSZBzYI3Ux0vDaNmin4Js0IbZW32le5JKm6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:07:12.644452Z"},"content_sha256":"7d8213c53b6317797ee7de27fac9a7754aa7ab011c280f470ac4f9b0913a2f0a","schema_version":"1.0","event_id":"sha256:7d8213c53b6317797ee7de27fac9a7754aa7ab011c280f470ac4f9b0913a2f0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C6JOTVGLEBMOHLZXBCDFNFBV3F/bundle.json","state_url":"https://pith.science/pith/C6JOTVGLEBMOHLZXBCDFNFBV3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C6JOTVGLEBMOHLZXBCDFNFBV3F/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":"2026-08-08T00:07:12Z","links":{"resolver":"https://pith.science/pith/C6JOTVGLEBMOHLZXBCDFNFBV3F","bundle":"https://pith.science/pith/C6JOTVGLEBMOHLZXBCDFNFBV3F/bundle.json","state":"https://pith.science/pith/C6JOTVGLEBMOHLZXBCDFNFBV3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C6JOTVGLEBMOHLZXBCDFNFBV3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C6JOTVGLEBMOHLZXBCDFNFBV3F","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":"fa37185db7e0721e11e3d7d5de36a5a3a96e0920e6aef370b79c872586f05952","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T02:13:24Z","title_canon_sha256":"c7a6701c06f0b45b5979470e370e48c4e3509144aabfce9d04ad95f9d0319350"},"schema_version":"1.0","source":{"id":"2505.15024","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15024","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15024v2","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15024","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"C6JOTVGLEBMO","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"C6JOTVGLEBMOHLZX","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"C6JOTVGL","created_at":"2026-07-05T11:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:7d8213c53b6317797ee7de27fac9a7754aa7ab011c280f470ac4f9b0913a2f0a","target":"graph","created_at":"2026-07-05T11:08:21Z","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/2505.15024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have performed well across various clinical natural language processing tasks, despite not being directly trained on electronic health record (EHR) data. In this work, we examine how popular open-source LLMs learn clinical information from large mined corpora through two crucial but understudied lenses: (1) their interpretation of clinical jargon, a foundational ability for understanding real-world clinical notes, and (2) their responses to unsupported medical claims. For both use cases, we investigate the frequency of relevant clinical information in their corresp","authors_text":"David Sontag, Furong Jia, Monica Agrawal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T02:13:24Z","title":"Diagnosing our datasets: How does my language model learn clinical information?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15024","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:dc3f60220f883836e6915e1c1e9d4a6381022422d023cbb419e5acb438226e0d","target":"record","created_at":"2026-07-05T11:08:21Z","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":"fa37185db7e0721e11e3d7d5de36a5a3a96e0920e6aef370b79c872586f05952","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T02:13:24Z","title_canon_sha256":"c7a6701c06f0b45b5979470e370e48c4e3509144aabfce9d04ad95f9d0319350"},"schema_version":"1.0","source":{"id":"2505.15024","kind":"arxiv","version":2}},"canonical_sha256":"1792e9d4cb2058e3af370886569435d975d66929699ffc8c92b1bb0f1c62b851","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1792e9d4cb2058e3af370886569435d975d66929699ffc8c92b1bb0f1c62b851","first_computed_at":"2026-07-05T11:08:21.283810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:21.283810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HTEph2tBetVyK+6VNU9ZXg7EIes6eDZerXVRrXi2ew15Jwm7yjwywgtvao5A3iMc7rX49hqEtyO0frlR8/9RAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:21.284226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15024","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc3f60220f883836e6915e1c1e9d4a6381022422d023cbb419e5acb438226e0d","sha256:7d8213c53b6317797ee7de27fac9a7754aa7ab011c280f470ac4f9b0913a2f0a"],"state_sha256":"c210691f4dc5064f2b9b30e62b24f89a7c3ffb730fd3bf27d7c26a0d5335f3e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9YhqDgAQqBSgxWNaSXcewuCEAo68yEOM2Vdy1FkqiUfaKO7HuPZwjgBbQm6O+4O8NqIfmKgP81BQlrbQi0b3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:07:12.648333Z","bundle_sha256":"7fcf6167ae42e200db5211a76320a5f0ba7940d7f7a31911c13f10b14b7d2ad5"}}