{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y5Y7EUFTDHQRAB6DYQPBSXFNQ5","short_pith_number":"pith:Y5Y7EUFT","canonical_record":{"source":{"id":"2411.13163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T09:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"7180dde08184d10360e679594b1a293854820d3be85148fc41f2165d8b1bc939","abstract_canon_sha256":"aec44368e2a64003cb19bc6ae8aef1a0931492dd5ba373453a28ba3ff1fe5c23"},"schema_version":"1.0"},"canonical_sha256":"c771f250b319e11007c3c41e195cad8760684a9946f9c5f6384a8b15d9872029","source":{"kind":"arxiv","id":"2411.13163","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13163","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13163v2","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13163","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y5Y7EUFTDHQR","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y5Y7EUFTDHQRAB6D","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y5Y7EUFT","created_at":"2026-07-05T10:30:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y5Y7EUFTDHQRAB6DYQPBSXFNQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T09:59:12Z","cross_cats_sorted":[],"title_canon_sha256":"7180dde08184d10360e679594b1a293854820d3be85148fc41f2165d8b1bc939","abstract_canon_sha256":"aec44368e2a64003cb19bc6ae8aef1a0931492dd5ba373453a28ba3ff1fe5c23"},"schema_version":"1.0"},"canonical_sha256":"c771f250b319e11007c3c41e195cad8760684a9946f9c5f6384a8b15d9872029","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:26.943989Z","signature_b64":"G68guQAp2hNK8bpPT4mLp5/543GTrYySn1MjIAUXWZ9VAwcoUbLJUUPzlby4zSkhh9kyxFeiGV+EGAOKJs8KDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c771f250b319e11007c3c41e195cad8760684a9946f9c5f6384a8b15d9872029","last_reissued_at":"2026-07-05T10:30:26.943464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:26.943464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13163","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":"2026-07-05T10:30:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tXDBzFDQ5CkVv0/ICcG51eVFdRQ//o/y4+HKhC8VIykUcL3NdPDDsbIFnF6ghkRLse81AUSyBfbG1iR+8f1dBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:45:06.478211Z"},"content_sha256":"d780273b9ad23a83a49aafc0baed1784946dad56ac81ef52cf15b2fe3dbc9256","schema_version":"1.0","event_id":"sha256:d780273b9ad23a83a49aafc0baed1784946dad56ac81ef52cf15b2fe3dbc9256"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y5Y7EUFTDHQRAB6DYQPBSXFNQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Taylor, Andrea Hita Ardiaca, Caterina Tozzi, James Weatherall, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2024-11-20T09:59:12Z","abstract_excerpt":"The reuse of historical clinical trial data has significant potential to accelerate medical research and drug development. However, interoperability challenges, particularly with missing medical codes, hinders effective data integration across studies. While Large Language Models (LLMs) offer a promising solution for automated coding without labeled data, current approaches face challenges on complex coding tasks. We introduce ALIGN, a novel compositional LLM-based system for automated, zero-shot medical coding. ALIGN follows a three-step process: (1) diverse candidate code generation; (2) sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13163","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/2411.13163/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":"2026-07-05T10:30:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rEF6uM5W3d9KG1QJDtfq6VhqW96CJScV9QvT/r7r6ew+oATPxFrZDHUF58nf6W4YngylxMmrs34V/q59nSe4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:45:06.478726Z"},"content_sha256":"7ed68b9492089e3af8301a09ed7c3a1019dca93e17131eb8c2e17e26cf76178b","schema_version":"1.0","event_id":"sha256:7ed68b9492089e3af8301a09ed7c3a1019dca93e17131eb8c2e17e26cf76178b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5Y7EUFTDHQRAB6DYQPBSXFNQ5/bundle.json","state_url":"https://pith.science/pith/Y5Y7EUFTDHQRAB6DYQPBSXFNQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5Y7EUFTDHQRAB6DYQPBSXFNQ5/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":"2026-08-13T01:45:06Z","links":{"resolver":"https://pith.science/pith/Y5Y7EUFTDHQRAB6DYQPBSXFNQ5","bundle":"https://pith.science/pith/Y5Y7EUFTDHQRAB6DYQPBSXFNQ5/bundle.json","state":"https://pith.science/pith/Y5Y7EUFTDHQRAB6DYQPBSXFNQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5Y7EUFTDHQRAB6DYQPBSXFNQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y5Y7EUFTDHQRAB6DYQPBSXFNQ5","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":"aec44368e2a64003cb19bc6ae8aef1a0931492dd5ba373453a28ba3ff1fe5c23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T09:59:12Z","title_canon_sha256":"7180dde08184d10360e679594b1a293854820d3be85148fc41f2165d8b1bc939"},"schema_version":"1.0","source":{"id":"2411.13163","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13163","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13163v2","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13163","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y5Y7EUFTDHQR","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y5Y7EUFTDHQRAB6D","created_at":"2026-07-05T10:30:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y5Y7EUFT","created_at":"2026-07-05T10:30:26Z"}],"graph_snapshots":[{"event_id":"sha256:7ed68b9492089e3af8301a09ed7c3a1019dca93e17131eb8c2e17e26cf76178b","target":"graph","created_at":"2026-07-05T10:30:26Z","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/2411.13163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The reuse of historical clinical trial data has significant potential to accelerate medical research and drug development. However, interoperability challenges, particularly with missing medical codes, hinders effective data integration across studies. While Large Language Models (LLMs) offer a promising solution for automated coding without labeled data, current approaches face challenges on complex coding tasks. We introduce ALIGN, a novel compositional LLM-based system for automated, zero-shot medical coding. ALIGN follows a three-step process: (1) diverse candidate code generation; (2) sel","authors_text":"Adam Taylor, Andrea Hita Ardiaca, Caterina Tozzi, James Weatherall, Mihaela van der Schaar, Nabeel Seedat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T09:59:12Z","title":"Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13163","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:d780273b9ad23a83a49aafc0baed1784946dad56ac81ef52cf15b2fe3dbc9256","target":"record","created_at":"2026-07-05T10:30:26Z","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":"aec44368e2a64003cb19bc6ae8aef1a0931492dd5ba373453a28ba3ff1fe5c23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T09:59:12Z","title_canon_sha256":"7180dde08184d10360e679594b1a293854820d3be85148fc41f2165d8b1bc939"},"schema_version":"1.0","source":{"id":"2411.13163","kind":"arxiv","version":2}},"canonical_sha256":"c771f250b319e11007c3c41e195cad8760684a9946f9c5f6384a8b15d9872029","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c771f250b319e11007c3c41e195cad8760684a9946f9c5f6384a8b15d9872029","first_computed_at":"2026-07-05T10:30:26.943464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:26.943464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G68guQAp2hNK8bpPT4mLp5/543GTrYySn1MjIAUXWZ9VAwcoUbLJUUPzlby4zSkhh9kyxFeiGV+EGAOKJs8KDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:26.943989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13163","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d780273b9ad23a83a49aafc0baed1784946dad56ac81ef52cf15b2fe3dbc9256","sha256:7ed68b9492089e3af8301a09ed7c3a1019dca93e17131eb8c2e17e26cf76178b"],"state_sha256":"d31b7eac55135c9a514bdd80ac50b38bb487ad8c7fe2d0d9594eb8651a4a471b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q41D1l/O3/DVKeQ4riwghhXNI5OJaLNig/XfOZh57jXLRXXY9rljg0vp46mM+oBrGIqKdX7Oy+s/sxo5M381Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:45:06.482260Z","bundle_sha256":"af82229e1856093a27e426829d30857eedaf712d3fdfddef5aa848235f27349f"}}