{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KZ5K6C5HPJRLXXLLLRG36ERAXK","short_pith_number":"pith:KZ5K6C5H","schema_version":"1.0","canonical_sha256":"567aaf0ba77a62bbdd6b5c4dbf1220babeec9122f3226538976178ea52986802","source":{"kind":"arxiv","id":"2507.15867","version":2},"attestation_state":"computed","paper":{"title":"RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.LG","authors_text":"Adam Cross, Jimeng Sun, John Wu","submitted_at":"2025-07-14T23:31:15Z","abstract_excerpt":"Rare diseases affect 1 in 10 Americans yet remain systematically underdocumented in clinical records. ICD-based systems cannot capture their breadth, over 50\\% of Orphanet codes lack a direct ICD mapping and only 2.2\\% of HPO codes have matching ICD codes, leaving patient populations invisible and delaying diagnosis. Mining unstructured clinical notes offers a direct path forward, but real notes are long, noisy, and abbreviation-dense, and limited annotations make fine-tuning infeasible, demanding approaches that generalize without task-specific training. We present Rare Disease Mining Agents "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.15867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T23:31:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"title_canon_sha256":"a5633a463cc55ed30dea79026011164cf761aacc89dcb038b16f14a9391501df","abstract_canon_sha256":"90a811a0c9bdd0d8c0a440c0a855a828268de32a065c9db0e31619b0492f79ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:35.039563Z","signature_b64":"WyyrhuKJbMn8twRhY3ryDwz1osqGAe0Zo0dA/KRCum3/vL38eqSt7gEaG9YIhYYM9jAzw2qqbs0n8IoMF0VEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"567aaf0ba77a62bbdd6b5c4dbf1220babeec9122f3226538976178ea52986802","last_reissued_at":"2026-05-18T03:09:35.038662Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:35.038662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.LG","authors_text":"Adam Cross, Jimeng Sun, John Wu","submitted_at":"2025-07-14T23:31:15Z","abstract_excerpt":"Rare diseases affect 1 in 10 Americans yet remain systematically underdocumented in clinical records. ICD-based systems cannot capture their breadth, over 50\\% of Orphanet codes lack a direct ICD mapping and only 2.2\\% of HPO codes have matching ICD codes, leaving patient populations invisible and delaying diagnosis. Mining unstructured clinical notes offers a direct path forward, but real notes are long, noisy, and abbreviation-dense, and limited annotations make fine-tuning infeasible, demanding approaches that generalize without task-specific training. We present Rare Disease Mining Agents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15867","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.15867","created_at":"2026-05-18T03:09:35.038815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15867v2","created_at":"2026-05-18T03:09:35.038815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15867","created_at":"2026-05-18T03:09:35.038815+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZ5K6C5HPJRL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZ5K6C5HPJRLXXLL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZ5K6C5H","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK","json":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK.json","graph_json":"https://pith.science/api/pith-number/KZ5K6C5HPJRLXXLLLRG36ERAXK/graph.json","events_json":"https://pith.science/api/pith-number/KZ5K6C5HPJRLXXLLLRG36ERAXK/events.json","paper":"https://pith.science/paper/KZ5K6C5H"},"agent_actions":{"view_html":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK","download_json":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK.json","view_paper":"https://pith.science/paper/KZ5K6C5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15867&json=true","fetch_graph":"https://pith.science/api/pith-number/KZ5K6C5HPJRLXXLLLRG36ERAXK/graph.json","fetch_events":"https://pith.science/api/pith-number/KZ5K6C5HPJRLXXLLLRG36ERAXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/action/storage_attestation","attest_author":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/action/author_attestation","sign_citation":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/action/citation_signature","submit_replication":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/action/replication_record"}},"created_at":"2026-05-18T03:09:35.038815+00:00","updated_at":"2026-05-18T03:09:35.038815+00:00"}