{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZDNOQ6MRI4BGZPZHRZZBVSZ3JV","short_pith_number":"pith:ZDNOQ6MR","canonical_record":{"source":{"id":"2307.03687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T16:06:02Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"6effa237a055075f0ce61d14aa05d2d8f9ca3301b8b0dd36687e9bbf5fb7afa3","abstract_canon_sha256":"5bea68b77a3d820de29d2e567ee1701da0c3afea1715447a09c7418088d5719c"},"schema_version":"1.0"},"canonical_sha256":"c8dae8799147026cbf278e721acb3b4d71e923aeb1f32ef14327c201dda0c37b","source":{"kind":"arxiv","id":"2307.03687","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03687","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03687v2","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03687","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZDNOQ6MRI4BG","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZDNOQ6MRI4BGZPZH","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZDNOQ6MR","created_at":"2026-07-05T08:21:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZDNOQ6MRI4BGZPZHRZZBVSZ3JV","target":"record","payload":{"canonical_record":{"source":{"id":"2307.03687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T16:06:02Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"6effa237a055075f0ce61d14aa05d2d8f9ca3301b8b0dd36687e9bbf5fb7afa3","abstract_canon_sha256":"5bea68b77a3d820de29d2e567ee1701da0c3afea1715447a09c7418088d5719c"},"schema_version":"1.0"},"canonical_sha256":"c8dae8799147026cbf278e721acb3b4d71e923aeb1f32ef14327c201dda0c37b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:05.657620Z","signature_b64":"fWp94iqf3SFvUDqCqi+MXPqDBsR/PWAVnJqazwqcQqDuHJoL4gKg2giardwc+qwSVFp6yW/UTD/wAN587tXXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8dae8799147026cbf278e721acb3b4d71e923aeb1f32ef14327c201dda0c37b","last_reissued_at":"2026-07-05T08:21:05.657038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:05.657038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.03687","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":"2026-07-05T08:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q9U+Y6+zyFNFUH3a5oIYZEHPP0QFhPX2lNj74wm2rxd5EckOlHAyyexduyCADgkl9rWJFHke9Bo2CdZGgA90BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:27:25.093380Z"},"content_sha256":"e9be87efd6659c740299054035eedfd68b1d4db4a929437e9fe7b5b4351602b1","schema_version":"1.0","event_id":"sha256:e9be87efd6659c740299054035eedfd68b1d4db4a929437e9fe7b5b4351602b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZDNOQ6MRI4BGZPZHRZZBVSZ3JV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging text data for causal inference using electronic health records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.CL","authors_text":"Aaron R. Kaufman, Leo A. Celi, Luke Miratrix, Reagan Mozer","submitted_at":"2023-06-09T16:06:02Z","abstract_excerpt":"In studies that rely on data from electronic health records (EHRs), unstructured text data such as clinical progress notes offer a rich source of information about patient characteristics and care that may be missing from structured data. Despite the prevalence of text in clinical research, these data are often ignored for the purposes of quantitative analysis due their complexity. This paper presents a unified framework for leveraging text data to support causal inference with electronic health data at multiple stages of analysis. In particular, we consider how natural language processing and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03687","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/2307.03687/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":"2026-07-05T08:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ITgRS8Qp4/JWO0vjjUHkmPUjr1YuI+E/w91Oj6gbsUh9xIXtxjpZfJiop3aljU3QIQ7Db61Yi/vP8eXBN0ArAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:27:25.093937Z"},"content_sha256":"9eca0d739e19de9808e18f0f554ca76eb9dc1542c75940735bb2f8d7023f5c10","schema_version":"1.0","event_id":"sha256:9eca0d739e19de9808e18f0f554ca76eb9dc1542c75940735bb2f8d7023f5c10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDNOQ6MRI4BGZPZHRZZBVSZ3JV/bundle.json","state_url":"https://pith.science/pith/ZDNOQ6MRI4BGZPZHRZZBVSZ3JV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDNOQ6MRI4BGZPZHRZZBVSZ3JV/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":"2026-08-10T19:27:25Z","links":{"resolver":"https://pith.science/pith/ZDNOQ6MRI4BGZPZHRZZBVSZ3JV","bundle":"https://pith.science/pith/ZDNOQ6MRI4BGZPZHRZZBVSZ3JV/bundle.json","state":"https://pith.science/pith/ZDNOQ6MRI4BGZPZHRZZBVSZ3JV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDNOQ6MRI4BGZPZHRZZBVSZ3JV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZDNOQ6MRI4BGZPZHRZZBVSZ3JV","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":"5bea68b77a3d820de29d2e567ee1701da0c3afea1715447a09c7418088d5719c","cross_cats_sorted":["stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T16:06:02Z","title_canon_sha256":"6effa237a055075f0ce61d14aa05d2d8f9ca3301b8b0dd36687e9bbf5fb7afa3"},"schema_version":"1.0","source":{"id":"2307.03687","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03687","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03687v2","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03687","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZDNOQ6MRI4BG","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZDNOQ6MRI4BGZPZH","created_at":"2026-07-05T08:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZDNOQ6MR","created_at":"2026-07-05T08:21:05Z"}],"graph_snapshots":[{"event_id":"sha256:9eca0d739e19de9808e18f0f554ca76eb9dc1542c75940735bb2f8d7023f5c10","target":"graph","created_at":"2026-07-05T08:21:05Z","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/2307.03687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In studies that rely on data from electronic health records (EHRs), unstructured text data such as clinical progress notes offer a rich source of information about patient characteristics and care that may be missing from structured data. Despite the prevalence of text in clinical research, these data are often ignored for the purposes of quantitative analysis due their complexity. This paper presents a unified framework for leveraging text data to support causal inference with electronic health data at multiple stages of analysis. In particular, we consider how natural language processing and","authors_text":"Aaron R. Kaufman, Leo A. Celi, Luke Miratrix, Reagan Mozer","cross_cats":["stat.AP","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T16:06:02Z","title":"Leveraging text data for causal inference using electronic health records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03687","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:e9be87efd6659c740299054035eedfd68b1d4db4a929437e9fe7b5b4351602b1","target":"record","created_at":"2026-07-05T08:21:05Z","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":"5bea68b77a3d820de29d2e567ee1701da0c3afea1715447a09c7418088d5719c","cross_cats_sorted":["stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T16:06:02Z","title_canon_sha256":"6effa237a055075f0ce61d14aa05d2d8f9ca3301b8b0dd36687e9bbf5fb7afa3"},"schema_version":"1.0","source":{"id":"2307.03687","kind":"arxiv","version":2}},"canonical_sha256":"c8dae8799147026cbf278e721acb3b4d71e923aeb1f32ef14327c201dda0c37b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8dae8799147026cbf278e721acb3b4d71e923aeb1f32ef14327c201dda0c37b","first_computed_at":"2026-07-05T08:21:05.657038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:05.657038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fWp94iqf3SFvUDqCqi+MXPqDBsR/PWAVnJqazwqcQqDuHJoL4gKg2giardwc+qwSVFp6yW/UTD/wAN587tXXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:05.657620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03687","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9be87efd6659c740299054035eedfd68b1d4db4a929437e9fe7b5b4351602b1","sha256:9eca0d739e19de9808e18f0f554ca76eb9dc1542c75940735bb2f8d7023f5c10"],"state_sha256":"a66e4ee9100fc394064693d60d2806cad4bd0466451b84462e3ac443eb840401"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Ra0nfpOewQiQWwjhES6djfY9D8jFBLDVTfQWf0zRBC9dJ6RRauTwKCl3OD9M3nqM4+nF7rblvhxM7te6ssgDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:27:25.100476Z","bundle_sha256":"6f36ba00ba73c9325abffb9b2b78016bdfb7d2e89bfc0da9976eea3ace33fa24"}}