{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YLYVBV4NEP5M2AMGUNNWIMGYU5","short_pith_number":"pith:YLYVBV4N","canonical_record":{"source":{"id":"2308.06354","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T19:18:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8597f1369767b940de5ea38872e5135f64507dde2bbc03dfcadc2f9271dacf5e","abstract_canon_sha256":"a703f12ba65de625a6f585362eca351b73c3fddbf192a803846093cb367dc6f0"},"schema_version":"1.0"},"canonical_sha256":"c2f150d78d23facd0186a35b6430d8a75071f052f3c06cccaff6802b3b615eb0","source":{"kind":"arxiv","id":"2308.06354","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06354","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06354v2","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06354","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"pith_short_12","alias_value":"YLYVBV4NEP5M","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"pith_short_16","alias_value":"YLYVBV4NEP5M2AMG","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"pith_short_8","alias_value":"YLYVBV4N","created_at":"2026-07-05T07:52:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YLYVBV4NEP5M2AMGUNNWIMGYU5","target":"record","payload":{"canonical_record":{"source":{"id":"2308.06354","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T19:18:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8597f1369767b940de5ea38872e5135f64507dde2bbc03dfcadc2f9271dacf5e","abstract_canon_sha256":"a703f12ba65de625a6f585362eca351b73c3fddbf192a803846093cb367dc6f0"},"schema_version":"1.0"},"canonical_sha256":"c2f150d78d23facd0186a35b6430d8a75071f052f3c06cccaff6802b3b615eb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:11.707445Z","signature_b64":"Ny2q/XF2BALJXtFKVUgdDqUXUEGQNT2EOUBBMPy/LV+ScBaPCKfpk5C/njIcepze2H43K5Aeb7AXhzkbtVxRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f150d78d23facd0186a35b6430d8a75071f052f3c06cccaff6802b3b615eb0","last_reissued_at":"2026-07-05T07:52:11.706958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:11.706958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.06354","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":"2026-07-05T07:52:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOxOc3sDyK5WEPoKi7wdlHFD7qUy8eshHRZXOSj0aSL9rj7R0hmLELlMAag9xJ60sstmoSG52M82Sgj+F0n7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:50.809071Z"},"content_sha256":"c0efe4a5c60ad85844540da12c32edef8478360bb1790e7158018ba72edb4dda","schema_version":"1.0","event_id":"sha256:c0efe4a5c60ad85844540da12c32edef8478360bb1790e7158018ba72edb4dda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YLYVBV4NEP5M2AMGUNNWIMGYU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models to Identify Social Determinants of Health in Electronic Health Records","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Kann, Danielle S. Bitterman, Guergana K. Savova, Hugo JWL Aerts, Idalid Franco, Jack Qian, Madeleine Goldstein, Marco Guevara, Raymond H. Mak, Shalini Moningi, Shan Chen, Spencer Thomas, Susan Harper, Tafadzwa L. Chaunzwa","submitted_at":"2023-08-11T19:18:35Z","abstract_excerpt":"Social determinants of health (SDoH) have an important impact on patient outcomes but are incompletely collected from the electronic health records (EHR). This study researched the ability of large language models to extract SDoH from free text in EHRs, where they are most commonly documented, and explored the role of synthetic clinical text for improving the extraction of these scarcely documented, yet extremely valuable, clinical data. 800 patient notes were annotated for SDoH categories, and several transformer-based models were evaluated. The study also experimented with synthetic data gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06354","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/2308.06354/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":"2026-07-05T07:52:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KA0QOGmYbkSudPVroT3yMs6e8LADcZ3szA1H+Y0qrC+HGgeGizJGSIctzaX0sh34Hc9hsIMF4w3uzT7Ot39LCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:50.809466Z"},"content_sha256":"2125846ee1a6258dcdd7922a16e39ad4b687730a1b6b29222e4833d60a90ee7d","schema_version":"1.0","event_id":"sha256:2125846ee1a6258dcdd7922a16e39ad4b687730a1b6b29222e4833d60a90ee7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLYVBV4NEP5M2AMGUNNWIMGYU5/bundle.json","state_url":"https://pith.science/pith/YLYVBV4NEP5M2AMGUNNWIMGYU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLYVBV4NEP5M2AMGUNNWIMGYU5/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":"2026-07-06T19:05:50Z","links":{"resolver":"https://pith.science/pith/YLYVBV4NEP5M2AMGUNNWIMGYU5","bundle":"https://pith.science/pith/YLYVBV4NEP5M2AMGUNNWIMGYU5/bundle.json","state":"https://pith.science/pith/YLYVBV4NEP5M2AMGUNNWIMGYU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLYVBV4NEP5M2AMGUNNWIMGYU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YLYVBV4NEP5M2AMGUNNWIMGYU5","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":"a703f12ba65de625a6f585362eca351b73c3fddbf192a803846093cb367dc6f0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T19:18:35Z","title_canon_sha256":"8597f1369767b940de5ea38872e5135f64507dde2bbc03dfcadc2f9271dacf5e"},"schema_version":"1.0","source":{"id":"2308.06354","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06354","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06354v2","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06354","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"pith_short_12","alias_value":"YLYVBV4NEP5M","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"pith_short_16","alias_value":"YLYVBV4NEP5M2AMG","created_at":"2026-07-05T07:52:11Z"},{"alias_kind":"pith_short_8","alias_value":"YLYVBV4N","created_at":"2026-07-05T07:52:11Z"}],"graph_snapshots":[{"event_id":"sha256:2125846ee1a6258dcdd7922a16e39ad4b687730a1b6b29222e4833d60a90ee7d","target":"graph","created_at":"2026-07-05T07:52:11Z","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/2308.06354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social determinants of health (SDoH) have an important impact on patient outcomes but are incompletely collected from the electronic health records (EHR). This study researched the ability of large language models to extract SDoH from free text in EHRs, where they are most commonly documented, and explored the role of synthetic clinical text for improving the extraction of these scarcely documented, yet extremely valuable, clinical data. 800 patient notes were annotated for SDoH categories, and several transformer-based models were evaluated. The study also experimented with synthetic data gen","authors_text":"Benjamin Kann, Danielle S. Bitterman, Guergana K. Savova, Hugo JWL Aerts, Idalid Franco, Jack Qian, Madeleine Goldstein, Marco Guevara, Raymond H. Mak, Shalini Moningi, Shan Chen, Spencer Thomas, Susan Harper, Tafadzwa L. Chaunzwa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T19:18:35Z","title":"Large Language Models to Identify Social Determinants of Health in Electronic Health Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06354","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:c0efe4a5c60ad85844540da12c32edef8478360bb1790e7158018ba72edb4dda","target":"record","created_at":"2026-07-05T07:52:11Z","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":"a703f12ba65de625a6f585362eca351b73c3fddbf192a803846093cb367dc6f0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T19:18:35Z","title_canon_sha256":"8597f1369767b940de5ea38872e5135f64507dde2bbc03dfcadc2f9271dacf5e"},"schema_version":"1.0","source":{"id":"2308.06354","kind":"arxiv","version":2}},"canonical_sha256":"c2f150d78d23facd0186a35b6430d8a75071f052f3c06cccaff6802b3b615eb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2f150d78d23facd0186a35b6430d8a75071f052f3c06cccaff6802b3b615eb0","first_computed_at":"2026-07-05T07:52:11.706958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:11.706958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ny2q/XF2BALJXtFKVUgdDqUXUEGQNT2EOUBBMPy/LV+ScBaPCKfpk5C/njIcepze2H43K5Aeb7AXhzkbtVxRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:11.707445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.06354","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0efe4a5c60ad85844540da12c32edef8478360bb1790e7158018ba72edb4dda","sha256:2125846ee1a6258dcdd7922a16e39ad4b687730a1b6b29222e4833d60a90ee7d"],"state_sha256":"3b78ad6beecd43d76f050767abf3c325cbc65a17957176b4fc33bd7708c33f9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zy6ZlM/OVXgvZytKYlSE+hgDpx3ZuUGA0h7/s3teivECttIK9r7yoEl+JAJSY1Nup+1wenHAF4FrKfmcsjOlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:05:50.811698Z","bundle_sha256":"242efb2e3ee5ad503f0f92a13d54e720fd7110713da05e9677e4594d1c38a0fd"}}