{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EU3SA3NGDYKMHECMOP4MS5ZGYK","short_pith_number":"pith:EU3SA3NG","schema_version":"1.0","canonical_sha256":"2537206da61e14c3904c73f8c97726c29218b190720f1aff8fea00f8a47f4163","source":{"kind":"arxiv","id":"2606.29503","version":1},"attestation_state":"computed","paper":{"title":"The Verbose Context Problem in Medical Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anjum Khurshid, Min-Gyu Kim, Shiva Kaul, Sriram Vishwanath","submitted_at":"2026-06-28T17:03:01Z","abstract_excerpt":"The verbose context problem occurs when structured concepts have token-inefficient textual representations. This bottleneck is acute in population health: cohort-level analysis of longitudinal patient records requires reasoning over thousands of medically-coded events, often exceeding 400K tokens in total. We present PopMedQA, a benchmark isolating this problem through computational tasks on groups of longitudinal patient records. We construct the benchmark using neopatient, a new library for language-controlled generation of artificial patient records. Through extensive ablations -- including"},"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":"2606.29503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T17:03:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49c9f180346cf7f0fcda1fdcad3564c3c6d43cd804812afc8236ecae4b4c4a79","abstract_canon_sha256":"5de24255661b985e4a3e18a35faa12d9c2d7520723f99bb283e470fc58cf725a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:09.485839Z","signature_b64":"P1MYC2bmSEfvF6h9usboZgP9sFc/y86lMGMc9sTMHQIt3EsCSZ1xLTMWX1TdrjLIlh9ZggukrXio4csyuTqHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2537206da61e14c3904c73f8c97726c29218b190720f1aff8fea00f8a47f4163","last_reissued_at":"2026-06-30T01:18:09.485381Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:09.485381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Verbose Context Problem in Medical Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anjum Khurshid, Min-Gyu Kim, Shiva Kaul, Sriram Vishwanath","submitted_at":"2026-06-28T17:03:01Z","abstract_excerpt":"The verbose context problem occurs when structured concepts have token-inefficient textual representations. This bottleneck is acute in population health: cohort-level analysis of longitudinal patient records requires reasoning over thousands of medically-coded events, often exceeding 400K tokens in total. We present PopMedQA, a benchmark isolating this problem through computational tasks on groups of longitudinal patient records. We construct the benchmark using neopatient, a new library for language-controlled generation of artificial patient records. Through extensive ablations -- including"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29503","kind":"arxiv","version":1},"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/2606.29503/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.29503","created_at":"2026-06-30T01:18:09.485448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29503v1","created_at":"2026-06-30T01:18:09.485448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29503","created_at":"2026-06-30T01:18:09.485448+00:00"},{"alias_kind":"pith_short_12","alias_value":"EU3SA3NGDYKM","created_at":"2026-06-30T01:18:09.485448+00:00"},{"alias_kind":"pith_short_16","alias_value":"EU3SA3NGDYKMHECM","created_at":"2026-06-30T01:18:09.485448+00:00"},{"alias_kind":"pith_short_8","alias_value":"EU3SA3NG","created_at":"2026-06-30T01:18:09.485448+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/EU3SA3NGDYKMHECMOP4MS5ZGYK","json":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK.json","graph_json":"https://pith.science/api/pith-number/EU3SA3NGDYKMHECMOP4MS5ZGYK/graph.json","events_json":"https://pith.science/api/pith-number/EU3SA3NGDYKMHECMOP4MS5ZGYK/events.json","paper":"https://pith.science/paper/EU3SA3NG"},"agent_actions":{"view_html":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK","download_json":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK.json","view_paper":"https://pith.science/paper/EU3SA3NG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29503&json=true","fetch_graph":"https://pith.science/api/pith-number/EU3SA3NGDYKMHECMOP4MS5ZGYK/graph.json","fetch_events":"https://pith.science/api/pith-number/EU3SA3NGDYKMHECMOP4MS5ZGYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK/action/storage_attestation","attest_author":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK/action/author_attestation","sign_citation":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK/action/citation_signature","submit_replication":"https://pith.science/pith/EU3SA3NGDYKMHECMOP4MS5ZGYK/action/replication_record"}},"created_at":"2026-06-30T01:18:09.485448+00:00","updated_at":"2026-06-30T01:18:09.485448+00:00"}