{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BLLMZAB5MUBQO3IPTTULXVNFWO","short_pith_number":"pith:BLLMZAB5","canonical_record":{"source":{"id":"2409.09095","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T20:03:26Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"ff2732614886056b1db3ad3c11cc13858a497aa22dbff7180cee35813a404736","abstract_canon_sha256":"0f0d17a4a70e4521350ec77eef5ee7b44c2663799e27f1b0d30bfc0d2e43d6c3"},"schema_version":"1.0"},"canonical_sha256":"0ad6cc803d6503076d0f9ce8bbd5a5b38b1da087511bda2d3fdded710cb701b1","source":{"kind":"arxiv","id":"2409.09095","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09095","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09095v2","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09095","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"BLLMZAB5MUBQ","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"BLLMZAB5MUBQO3IP","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"BLLMZAB5","created_at":"2026-07-05T09:35:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BLLMZAB5MUBQO3IPTTULXVNFWO","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09095","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T20:03:26Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"ff2732614886056b1db3ad3c11cc13858a497aa22dbff7180cee35813a404736","abstract_canon_sha256":"0f0d17a4a70e4521350ec77eef5ee7b44c2663799e27f1b0d30bfc0d2e43d6c3"},"schema_version":"1.0"},"canonical_sha256":"0ad6cc803d6503076d0f9ce8bbd5a5b38b1da087511bda2d3fdded710cb701b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:51.700589Z","signature_b64":"swS7Cmt3s2+8eXhN+O7nxhLgbskVg/3hY4jIiXS3Qtquz4t3FYIFpwujMl4baEGVmPY08yRRead8bwNGHWD/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad6cc803d6503076d0f9ce8bbd5a5b38b1da087511bda2d3fdded710cb701b1","last_reissued_at":"2026-07-05T09:35:51.700067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:51.700067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09095","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":"2026-07-05T09:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CUznn338ohGOiY8IcSK9nTzSVIbzmMdptSmXHg4DNcL0bIZMBIWgijiB1NerEXW51uIAeMzviptwR10R11NJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:10:54.599988Z"},"content_sha256":"c7b0c436eb9219cfa4d5a3e7468875ba6d7707d673e0ead5cce88bee61d904ef","schema_version":"1.0","event_id":"sha256:c7b0c436eb9219cfa4d5a3e7468875ba6d7707d673e0ead5cce88bee61d904ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BLLMZAB5MUBQO3IPTTULXVNFWO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"meds_reader: A fast and efficient EHR processing library","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Ethan Steinberg, Jason Alan Fries, Matthew B. A. McDermott, Michael Wornow, Nigam H. Shah, Suhana Bedi","submitted_at":"2024-09-12T20:03:26Z","abstract_excerpt":"The growing demand for machine learning in healthcare requires processing increasingly large electronic health record (EHR) datasets, but existing pipelines are not computationally efficient or scalable. In this paper, we introduce meds_reader, an optimized Python package for efficient EHR data processing that is designed to take advantage of many intrinsic properties of EHR data for improved speed. We then demonstrate the benefits of meds_reader by reimplementing key components of two major EHR processing pipelines, achieving 10-100x improvements in memory, speed, and disk usage. The code for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09095","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/2409.09095/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":"2026-07-05T09:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Cdr2LEfOH2DZFc/vPpsUqX3CnXZFdwBMd8x4b25ndZ8cYRZb0HFoLxI444wWMfeKxE0oDJ5spa+haKvWQKhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:10:54.600380Z"},"content_sha256":"21bd72ae492a2fba5cce1e878451c9ddd1799c11046fbf1ca7fd67c6dc6f5da3","schema_version":"1.0","event_id":"sha256:21bd72ae492a2fba5cce1e878451c9ddd1799c11046fbf1ca7fd67c6dc6f5da3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLLMZAB5MUBQO3IPTTULXVNFWO/bundle.json","state_url":"https://pith.science/pith/BLLMZAB5MUBQO3IPTTULXVNFWO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLLMZAB5MUBQO3IPTTULXVNFWO/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":"2026-07-06T08:10:54Z","links":{"resolver":"https://pith.science/pith/BLLMZAB5MUBQO3IPTTULXVNFWO","bundle":"https://pith.science/pith/BLLMZAB5MUBQO3IPTTULXVNFWO/bundle.json","state":"https://pith.science/pith/BLLMZAB5MUBQO3IPTTULXVNFWO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLLMZAB5MUBQO3IPTTULXVNFWO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BLLMZAB5MUBQO3IPTTULXVNFWO","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":"0f0d17a4a70e4521350ec77eef5ee7b44c2663799e27f1b0d30bfc0d2e43d6c3","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T20:03:26Z","title_canon_sha256":"ff2732614886056b1db3ad3c11cc13858a497aa22dbff7180cee35813a404736"},"schema_version":"1.0","source":{"id":"2409.09095","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09095","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09095v2","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09095","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"BLLMZAB5MUBQ","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"BLLMZAB5MUBQO3IP","created_at":"2026-07-05T09:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"BLLMZAB5","created_at":"2026-07-05T09:35:51Z"}],"graph_snapshots":[{"event_id":"sha256:21bd72ae492a2fba5cce1e878451c9ddd1799c11046fbf1ca7fd67c6dc6f5da3","target":"graph","created_at":"2026-07-05T09:35:51Z","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/2409.09095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing demand for machine learning in healthcare requires processing increasingly large electronic health record (EHR) datasets, but existing pipelines are not computationally efficient or scalable. In this paper, we introduce meds_reader, an optimized Python package for efficient EHR data processing that is designed to take advantage of many intrinsic properties of EHR data for improved speed. We then demonstrate the benefits of meds_reader by reimplementing key components of two major EHR processing pipelines, achieving 10-100x improvements in memory, speed, and disk usage. The code for","authors_text":"Ethan Steinberg, Jason Alan Fries, Matthew B. A. McDermott, Michael Wornow, Nigam H. Shah, Suhana Bedi","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T20:03:26Z","title":"meds_reader: A fast and efficient EHR processing library"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09095","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:c7b0c436eb9219cfa4d5a3e7468875ba6d7707d673e0ead5cce88bee61d904ef","target":"record","created_at":"2026-07-05T09:35:51Z","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":"0f0d17a4a70e4521350ec77eef5ee7b44c2663799e27f1b0d30bfc0d2e43d6c3","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T20:03:26Z","title_canon_sha256":"ff2732614886056b1db3ad3c11cc13858a497aa22dbff7180cee35813a404736"},"schema_version":"1.0","source":{"id":"2409.09095","kind":"arxiv","version":2}},"canonical_sha256":"0ad6cc803d6503076d0f9ce8bbd5a5b38b1da087511bda2d3fdded710cb701b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ad6cc803d6503076d0f9ce8bbd5a5b38b1da087511bda2d3fdded710cb701b1","first_computed_at":"2026-07-05T09:35:51.700067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:51.700067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"swS7Cmt3s2+8eXhN+O7nxhLgbskVg/3hY4jIiXS3Qtquz4t3FYIFpwujMl4baEGVmPY08yRRead8bwNGHWD/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:51.700589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09095","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7b0c436eb9219cfa4d5a3e7468875ba6d7707d673e0ead5cce88bee61d904ef","sha256:21bd72ae492a2fba5cce1e878451c9ddd1799c11046fbf1ca7fd67c6dc6f5da3"],"state_sha256":"7bb9deeafe0377de8a96f6486cdcc00e8f254f7d72a7003d495a481c9e469047"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wGE74+XKsmPIoEHtPWMbOlzgUi3CdSYM9i9tgNpeZtnG8ZJv0NCm8Gaywa/uRizrls2Azh7x3+S5LPJ9TZRxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:10:54.602300Z","bundle_sha256":"28840cb7b5a9c3d105c626f5b655a44c8ab6abfb301b075ace258935bc37c980"}}