{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2BZZC3NPBE3V57SJDFF3ZLFOSL","short_pith_number":"pith:2BZZC3NP","canonical_record":{"source":{"id":"2312.06457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T15:45:27Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"0a62a5c960cda8a241196227c6665e143e7afba4be321d2aa9958e45f453519a","abstract_canon_sha256":"db291c73f0dc81318be33ebbbbb7536a760e06a279cfa0c34d38a2b69145046c"},"schema_version":"1.0"},"canonical_sha256":"d073916daf09375efe49194bbcacae92ed7e941538f06d60aa582cbbc60efa97","source":{"kind":"arxiv","id":"2312.06457","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06457","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06457v1","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06457","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"2BZZC3NPBE3V","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"2BZZC3NPBE3V57SJ","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"2BZZC3NP","created_at":"2026-07-05T07:22:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2BZZC3NPBE3V57SJDFF3ZLFOSL","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T15:45:27Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"0a62a5c960cda8a241196227c6665e143e7afba4be321d2aa9958e45f453519a","abstract_canon_sha256":"db291c73f0dc81318be33ebbbbb7536a760e06a279cfa0c34d38a2b69145046c"},"schema_version":"1.0"},"canonical_sha256":"d073916daf09375efe49194bbcacae92ed7e941538f06d60aa582cbbc60efa97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:45.210418Z","signature_b64":"0J6Ch3WkU0SYKwmB8vWtJvszYNNS++/lZ8rZfr6Pxl14UFFOzsVpjVha4eFypydbn22FB4QgkwigG5IYb6fIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d073916daf09375efe49194bbcacae92ed7e941538f06d60aa582cbbc60efa97","last_reissued_at":"2026-07-05T07:22:45.209928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:45.209928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06457","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":"2026-07-05T07:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mlHrIIluiTKiIbJTBLEOLM0tzuzIlBjD4Ev10pT97KqCFMaZXNg60xu29+qT0VA5mMQ3hagsh8lW1CZlX0UBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:48:17.640026Z"},"content_sha256":"7175faafd2edf893590d5deb6356178a074d2269304a278863807a1bc3d7efa6","schema_version":"1.0","event_id":"sha256:7175faafd2edf893590d5deb6356178a074d2269304a278863807a1bc3d7efa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2BZZC3NPBE3V57SJDFF3ZLFOSL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models with Retrieval-Augmented Generation for Zero-Shot Disease Phenotyping","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Andrew C. Nelsen, Brandon K. Fornwalt, David M. Vidmar, Gabriel Altay, Jessica K. De Freitas, John M. Pfeifer, Kabir Manghnani, Kellie Morland, Martin C. Stumpe, Riccardo Miotto, Ruijun Chen, Will E. Thompson","submitted_at":"2023-12-11T15:45:27Z","abstract_excerpt":"Identifying disease phenotypes from electronic health records (EHRs) is critical for numerous secondary uses. Manually encoding physician knowledge into rules is particularly challenging for rare diseases due to inadequate EHR coding, necessitating review of clinical notes. Large language models (LLMs) offer promise in text understanding but may not efficiently handle real-world clinical documentation. We propose a zero-shot LLM-based method enriched by retrieval-augmented generation and MapReduce, which pre-identifies disease-related text snippets to be used in parallel as queries for the LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06457","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/2312.06457/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":"2026-07-05T07:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxird6JPt21cx3y3PT7aSahuUFvB4dqmzO52JLbUUm7Fz64T45+i++ZlruexMAG9nhjO+DfeNvBW10VLYsfmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:48:17.640634Z"},"content_sha256":"31c28925443fa2778854b3504d861b0e3f6016c85ac59c0682953c1de9491ac7","schema_version":"1.0","event_id":"sha256:31c28925443fa2778854b3504d861b0e3f6016c85ac59c0682953c1de9491ac7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BZZC3NPBE3V57SJDFF3ZLFOSL/bundle.json","state_url":"https://pith.science/pith/2BZZC3NPBE3V57SJDFF3ZLFOSL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BZZC3NPBE3V57SJDFF3ZLFOSL/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":"2026-08-23T17:48:17Z","links":{"resolver":"https://pith.science/pith/2BZZC3NPBE3V57SJDFF3ZLFOSL","bundle":"https://pith.science/pith/2BZZC3NPBE3V57SJDFF3ZLFOSL/bundle.json","state":"https://pith.science/pith/2BZZC3NPBE3V57SJDFF3ZLFOSL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BZZC3NPBE3V57SJDFF3ZLFOSL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2BZZC3NPBE3V57SJDFF3ZLFOSL","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":"db291c73f0dc81318be33ebbbbb7536a760e06a279cfa0c34d38a2b69145046c","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T15:45:27Z","title_canon_sha256":"0a62a5c960cda8a241196227c6665e143e7afba4be321d2aa9958e45f453519a"},"schema_version":"1.0","source":{"id":"2312.06457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06457","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06457v1","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06457","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"2BZZC3NPBE3V","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"2BZZC3NPBE3V57SJ","created_at":"2026-07-05T07:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"2BZZC3NP","created_at":"2026-07-05T07:22:45Z"}],"graph_snapshots":[{"event_id":"sha256:31c28925443fa2778854b3504d861b0e3f6016c85ac59c0682953c1de9491ac7","target":"graph","created_at":"2026-07-05T07:22:45Z","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/2312.06457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying disease phenotypes from electronic health records (EHRs) is critical for numerous secondary uses. Manually encoding physician knowledge into rules is particularly challenging for rare diseases due to inadequate EHR coding, necessitating review of clinical notes. Large language models (LLMs) offer promise in text understanding but may not efficiently handle real-world clinical documentation. We propose a zero-shot LLM-based method enriched by retrieval-augmented generation and MapReduce, which pre-identifies disease-related text snippets to be used in parallel as queries for the LLM","authors_text":"Andrew C. Nelsen, Brandon K. Fornwalt, David M. Vidmar, Gabriel Altay, Jessica K. De Freitas, John M. Pfeifer, Kabir Manghnani, Kellie Morland, Martin C. Stumpe, Riccardo Miotto, Ruijun Chen, Will E. Thompson","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T15:45:27Z","title":"Large Language Models with Retrieval-Augmented Generation for Zero-Shot Disease Phenotyping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06457","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":"sha256:7175faafd2edf893590d5deb6356178a074d2269304a278863807a1bc3d7efa6","target":"record","created_at":"2026-07-05T07:22:45Z","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":"db291c73f0dc81318be33ebbbbb7536a760e06a279cfa0c34d38a2b69145046c","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-11T15:45:27Z","title_canon_sha256":"0a62a5c960cda8a241196227c6665e143e7afba4be321d2aa9958e45f453519a"},"schema_version":"1.0","source":{"id":"2312.06457","kind":"arxiv","version":1}},"canonical_sha256":"d073916daf09375efe49194bbcacae92ed7e941538f06d60aa582cbbc60efa97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d073916daf09375efe49194bbcacae92ed7e941538f06d60aa582cbbc60efa97","first_computed_at":"2026-07-05T07:22:45.209928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:45.209928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0J6Ch3WkU0SYKwmB8vWtJvszYNNS++/lZ8rZfr6Pxl14UFFOzsVpjVha4eFypydbn22FB4QgkwigG5IYb6fIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:45.210418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7175faafd2edf893590d5deb6356178a074d2269304a278863807a1bc3d7efa6","sha256:31c28925443fa2778854b3504d861b0e3f6016c85ac59c0682953c1de9491ac7"],"state_sha256":"8686b43da5841948400b2abe2a0f6f8f82e29981b7d8a6bc93a6425ca66e2e8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzA2i3RSsst8d47lEIvhHIH5kdcuLFDIUwGQaB1y9Nk4jXy7s4r+jipMGiwQ/BXGFnU0Nb2qX0TeH4a7LjggAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:48:17.645802Z","bundle_sha256":"db5ca4a09e5ec76ec3f256402ef15b83530971950ed9ed43084f505708f6a855"}}