{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KZ5K6C5HPJRLXXLLLRG36ERAXK","short_pith_number":"pith:KZ5K6C5H","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"},"canonical_sha256":"567aaf0ba77a62bbdd6b5c4dbf1220babeec9122f3226538976178ea52986802","source":{"kind":"arxiv","id":"2507.15867","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15867","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15867v2","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15867","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"KZ5K6C5HPJRL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KZ5K6C5HPJRLXXLL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KZ5K6C5H","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KZ5K6C5HPJRLXXLLLRG36ERAXK","target":"record","payload":{"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"},"canonical_sha256":"567aaf0ba77a62bbdd6b5c4dbf1220babeec9122f3226538976178ea52986802","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"},"source_kind":"arxiv","source_id":"2507.15867","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":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iZKq4QRD6AH0rUNaFwYDyUVSYvFLi59nSgt3aBLaHuSRhvb7Phw3rXUmBeeRNtt9RwUTb6u5uFTPa/uBylDADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T10:27:47.231682Z"},"content_sha256":"b6f94343700a93a867720f63828e3daff2abc74078fbc55f3d14c9e43444bec1","schema_version":"1.0","event_id":"sha256:b6f94343700a93a867720f63828e3daff2abc74078fbc55f3d14c9e43444bec1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KZ5K6C5HPJRLXXLLLRG36ERAXK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFkisPEIOmMnq2J9E7C41Dwrz6MX5gQFDXxBDKxrNbKk1B00m26nw7ekwKhpCzz4n0yHBIqG17VAae2anb76BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T10:27:47.232041Z"},"content_sha256":"ba0da18a34713ae58183a8ad926df2617ef8317884b2066fc3db294d6963a20b","schema_version":"1.0","event_id":"sha256:ba0da18a34713ae58183a8ad926df2617ef8317884b2066fc3db294d6963a20b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/bundle.json","state_url":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/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":"2026-05-21T10:27:47Z","links":{"resolver":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK","bundle":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/bundle.json","state":"https://pith.science/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZ5K6C5HPJRLXXLLLRG36ERAXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KZ5K6C5HPJRLXXLLLRG36ERAXK","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":"90a811a0c9bdd0d8c0a440c0a855a828268de32a065c9db0e31619b0492f79ed","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T23:31:15Z","title_canon_sha256":"a5633a463cc55ed30dea79026011164cf761aacc89dcb038b16f14a9391501df"},"schema_version":"1.0","source":{"id":"2507.15867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15867","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15867v2","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15867","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"KZ5K6C5HPJRL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KZ5K6C5HPJRLXXLL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KZ5K6C5H","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ba0da18a34713ae58183a8ad926df2617ef8317884b2066fc3db294d6963a20b","target":"graph","created_at":"2026-05-18T03:09:35Z","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"},"paper":{"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 ","authors_text":"Adam Cross, Jimeng Sun, John Wu","cross_cats":["cs.AI","cs.CL","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T23:31:15Z","title":"RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15867","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:b6f94343700a93a867720f63828e3daff2abc74078fbc55f3d14c9e43444bec1","target":"record","created_at":"2026-05-18T03:09:35Z","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":"90a811a0c9bdd0d8c0a440c0a855a828268de32a065c9db0e31619b0492f79ed","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T23:31:15Z","title_canon_sha256":"a5633a463cc55ed30dea79026011164cf761aacc89dcb038b16f14a9391501df"},"schema_version":"1.0","source":{"id":"2507.15867","kind":"arxiv","version":2}},"canonical_sha256":"567aaf0ba77a62bbdd6b5c4dbf1220babeec9122f3226538976178ea52986802","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"567aaf0ba77a62bbdd6b5c4dbf1220babeec9122f3226538976178ea52986802","first_computed_at":"2026-05-18T03:09:35.038662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:35.038662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WyyrhuKJbMn8twRhY3ryDwz1osqGAe0Zo0dA/KRCum3/vL38eqSt7gEaG9YIhYYM9jAzw2qqbs0n8IoMF0VEAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:35.039563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6f94343700a93a867720f63828e3daff2abc74078fbc55f3d14c9e43444bec1","sha256:ba0da18a34713ae58183a8ad926df2617ef8317884b2066fc3db294d6963a20b"],"state_sha256":"85f9c4c678765d498a3c22031d225ed8d6f92dd300bdc8996d7fbc393af400d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRfqV6L+S/vKIQHHXc8xERotkBp9bytMa5uTgdyYe3e1Kp30sE8HogMNTlKTBMWyLPT897LiSTj4vWhIIhljDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T10:27:47.234823Z","bundle_sha256":"c81c07f3d50121e60a039ffb34366c36e5ccafee0e4e236c61fc68c8b0d82f11"}}