{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RTF44LEB37UUFGTM6RXDLFA3IH","short_pith_number":"pith:RTF44LEB","canonical_record":{"source":{"id":"2502.00943","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T22:31:54Z","cross_cats_sorted":[],"title_canon_sha256":"85c984eb2344eec359e13e95a598f08b0e88bd4333801302765b91a1e0414eab","abstract_canon_sha256":"dddaa705533142c97b33f85458342fd8ef085bda38cc995de1a69c871a2129d2"},"schema_version":"1.0"},"canonical_sha256":"8ccbce2c81dfe9429a6cf46e35941b41ea6ada62b9f9261de61642a722eea035","source":{"kind":"arxiv","id":"2502.00943","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00943","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00943v2","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00943","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"RTF44LEB37UU","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"pith_short_16","alias_value":"RTF44LEB37UUFGTM","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"pith_short_8","alias_value":"RTF44LEB","created_at":"2026-07-05T11:55:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RTF44LEB37UUFGTM6RXDLFA3IH","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00943","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T22:31:54Z","cross_cats_sorted":[],"title_canon_sha256":"85c984eb2344eec359e13e95a598f08b0e88bd4333801302765b91a1e0414eab","abstract_canon_sha256":"dddaa705533142c97b33f85458342fd8ef085bda38cc995de1a69c871a2129d2"},"schema_version":"1.0"},"canonical_sha256":"8ccbce2c81dfe9429a6cf46e35941b41ea6ada62b9f9261de61642a722eea035","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:38.108000Z","signature_b64":"z5JurzEhXLb3pZ+drk9X2Nnto8pqKvauK2jL3PeoAuXHy+X24HPI5vA15WzQ1mLB9T7s8wSjTL6ADa4Qzq9oBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ccbce2c81dfe9429a6cf46e35941b41ea6ada62b9f9261de61642a722eea035","last_reissued_at":"2026-07-05T11:55:38.107508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:38.107508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00943","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":"2026-07-05T11:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j07994GOKZjrppXyqn51W/SpbYB4RTYQcDbn35u2TNANft+VpzT42SN3W9G0G7xdB1Da2mnC1ECMVsmkxMfSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:00:51.495675Z"},"content_sha256":"42896079560a3c547a9ead72f28385031cd66d2e38b1cc6154bb775521bfb85a","schema_version":"1.0","event_id":"sha256:42896079560a3c547a9ead72f28385031cd66d2e38b1cc6154bb775521bfb85a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RTF44LEB37UUFGTM6RXDLFA3IH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Piening, Carlo Bifulco, Cliff Wong, Guo Hui Gan, Hoifung Poon, Jaspreet Bagga, Joseph C. Murray, Kristina Young, Luis M. Ahumada, Marvin Borja, Mu Wei, Qianchu Liu, Rom Leidner, Roshanthi Weerasinghe, Sam Preston, Sheng Zhang, Shrey Jain, Sid Kiblawi, Srinivasan Yegnasubramanian, Taxiarchis Botsis, Theodore Zhao, Tristan Naumann, Yanbo Xu, Yu Gu, Zelalem Gero","submitted_at":"2025-02-02T22:31:54Z","abstract_excerpt":"A significant fraction of real-world patient information resides in unstructured clinical text. Medical abstraction extracts and normalizes key structured attributes from free-text clinical notes, which is the prerequisite for a variety of important downstream applications, including registry curation, clinical trial operations, and real-world evidence generation. Prior medical abstraction methods typically resort to building attribute-specific models, each of which requires extensive manual effort such as rule creation or supervised label annotation for the individual attribute, thus limiting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00943","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/2502.00943/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":"2026-07-05T11:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qZ77eOyPWuFoLiJz89TNJc2dDyS/ZMBgvEH7slOummuqjipN6djpCgwGbMAWmuyMbWb8RpM3CRuTUeEiOFH9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:00:51.496040Z"},"content_sha256":"7e1e7854ee39734972c9d965aa979ccf19d098c6a7a9bc4d0958a09150c0fff7","schema_version":"1.0","event_id":"sha256:7e1e7854ee39734972c9d965aa979ccf19d098c6a7a9bc4d0958a09150c0fff7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RTF44LEB37UUFGTM6RXDLFA3IH/bundle.json","state_url":"https://pith.science/pith/RTF44LEB37UUFGTM6RXDLFA3IH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RTF44LEB37UUFGTM6RXDLFA3IH/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":"2026-07-07T12:00:51Z","links":{"resolver":"https://pith.science/pith/RTF44LEB37UUFGTM6RXDLFA3IH","bundle":"https://pith.science/pith/RTF44LEB37UUFGTM6RXDLFA3IH/bundle.json","state":"https://pith.science/pith/RTF44LEB37UUFGTM6RXDLFA3IH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RTF44LEB37UUFGTM6RXDLFA3IH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RTF44LEB37UUFGTM6RXDLFA3IH","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":"dddaa705533142c97b33f85458342fd8ef085bda38cc995de1a69c871a2129d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T22:31:54Z","title_canon_sha256":"85c984eb2344eec359e13e95a598f08b0e88bd4333801302765b91a1e0414eab"},"schema_version":"1.0","source":{"id":"2502.00943","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00943","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00943v2","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00943","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"RTF44LEB37UU","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"pith_short_16","alias_value":"RTF44LEB37UUFGTM","created_at":"2026-07-05T11:55:38Z"},{"alias_kind":"pith_short_8","alias_value":"RTF44LEB","created_at":"2026-07-05T11:55:38Z"}],"graph_snapshots":[{"event_id":"sha256:7e1e7854ee39734972c9d965aa979ccf19d098c6a7a9bc4d0958a09150c0fff7","target":"graph","created_at":"2026-07-05T11:55:38Z","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/2502.00943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A significant fraction of real-world patient information resides in unstructured clinical text. Medical abstraction extracts and normalizes key structured attributes from free-text clinical notes, which is the prerequisite for a variety of important downstream applications, including registry curation, clinical trial operations, and real-world evidence generation. Prior medical abstraction methods typically resort to building attribute-specific models, each of which requires extensive manual effort such as rule creation or supervised label annotation for the individual attribute, thus limiting","authors_text":"Brian Piening, Carlo Bifulco, Cliff Wong, Guo Hui Gan, Hoifung Poon, Jaspreet Bagga, Joseph C. Murray, Kristina Young, Luis M. Ahumada, Marvin Borja, Mu Wei, Qianchu Liu, Rom Leidner, Roshanthi Weerasinghe, Sam Preston, Sheng Zhang, Shrey Jain, Sid Kiblawi, Srinivasan Yegnasubramanian, Taxiarchis Botsis, Theodore Zhao, Tristan Naumann, Yanbo Xu, Yu Gu, Zelalem Gero","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T22:31:54Z","title":"Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00943","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":"sha256:42896079560a3c547a9ead72f28385031cd66d2e38b1cc6154bb775521bfb85a","target":"record","created_at":"2026-07-05T11:55:38Z","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":"dddaa705533142c97b33f85458342fd8ef085bda38cc995de1a69c871a2129d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T22:31:54Z","title_canon_sha256":"85c984eb2344eec359e13e95a598f08b0e88bd4333801302765b91a1e0414eab"},"schema_version":"1.0","source":{"id":"2502.00943","kind":"arxiv","version":2}},"canonical_sha256":"8ccbce2c81dfe9429a6cf46e35941b41ea6ada62b9f9261de61642a722eea035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ccbce2c81dfe9429a6cf46e35941b41ea6ada62b9f9261de61642a722eea035","first_computed_at":"2026-07-05T11:55:38.107508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:38.107508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5JurzEhXLb3pZ+drk9X2Nnto8pqKvauK2jL3PeoAuXHy+X24HPI5vA15WzQ1mLB9T7s8wSjTL6ADa4Qzq9oBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:38.108000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00943","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42896079560a3c547a9ead72f28385031cd66d2e38b1cc6154bb775521bfb85a","sha256:7e1e7854ee39734972c9d965aa979ccf19d098c6a7a9bc4d0958a09150c0fff7"],"state_sha256":"c9c1dd947a67079be03e8e7bad1e1d2a3c289145856cc114c5b3cd4ded4074f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6IlxByIKtOnRXqLVWj1fLsOLsmnYi9OQO9kQc2qGegJD9IT7KU2ZemCc+kF8IS/+ciTawbZ8rjYK9KZlRcuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:00:51.497951Z","bundle_sha256":"07daa2c3efd3cefd0f687c6c6f707f2bdec2d6a5120ad9f422a520323d2e8d11"}}