{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MMXPH5K7WX6MZ7GDDLWTAZT73Y","short_pith_number":"pith:MMXPH5K7","schema_version":"1.0","canonical_sha256":"632ef3f55fb5fcccfcc31aed30667fde3a18118975833575c3a65261c60117c1","source":{"kind":"arxiv","id":"2603.07900","version":2},"attestation_state":"computed","paper":{"title":"EveryQuery: Zero-Shot Clinical Prediction via Task-Conditioned Pretraining over Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gregory Kondas, Isaac Kohane, Liat Antwarg Friedman, Matthew McDermott, Payal Chandak","submitted_at":"2026-03-09T02:45:22Z","abstract_excerpt":"Foundation models pretrained on electronic health records (EHR) have demonstrated zero-shot clinical prediction capabilities by generating synthetic patient futures and aggregating statistics over sampled trajectories. However, this autoregressive inference procedure is computationally expensive, statistically noisy, and not natively promptable because users cannot directly condition predictions on specific clinical questions. In this preliminary work, we introduce EveryQuery, an EHR foundation model that achieves zero-shot inference through task-conditioned pre-training. Rather than generatin"},"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":"2603.07900","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-09T02:45:22Z","cross_cats_sorted":[],"title_canon_sha256":"881237cbe82503b5ae8d5c5e4490b6a84c414356d737b52f283988df1c3b0765","abstract_canon_sha256":"cb4be139b1e5bb74fd89d30e3b50049e100c9818aad5f3c6b943e68ca9e29387"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:42.872689Z","signature_b64":"npOrf9fBkJcduj6EJYU4hanRG7vzIAP57kWF7/iF/B1xAJx9XMVWKnrJ+vQpowifwY3YYEkw6nvwbTugKj2dCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"632ef3f55fb5fcccfcc31aed30667fde3a18118975833575c3a65261c60117c1","last_reissued_at":"2026-05-20T00:05:42.872157Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:42.872157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EveryQuery: Zero-Shot Clinical Prediction via Task-Conditioned Pretraining over Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gregory Kondas, Isaac Kohane, Liat Antwarg Friedman, Matthew McDermott, Payal Chandak","submitted_at":"2026-03-09T02:45:22Z","abstract_excerpt":"Foundation models pretrained on electronic health records (EHR) have demonstrated zero-shot clinical prediction capabilities by generating synthetic patient futures and aggregating statistics over sampled trajectories. However, this autoregressive inference procedure is computationally expensive, statistically noisy, and not natively promptable because users cannot directly condition predictions on specific clinical questions. In this preliminary work, we introduce EveryQuery, an EHR foundation model that achieves zero-shot inference through task-conditioned pre-training. Rather than generatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07900","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/2603.07900/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":"2603.07900","created_at":"2026-05-20T00:05:42.872225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.07900v2","created_at":"2026-05-20T00:05:42.872225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07900","created_at":"2026-05-20T00:05:42.872225+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMXPH5K7WX6M","created_at":"2026-05-20T00:05:42.872225+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMXPH5K7WX6MZ7GD","created_at":"2026-05-20T00:05:42.872225+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMXPH5K7","created_at":"2026-05-20T00:05:42.872225+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/MMXPH5K7WX6MZ7GDDLWTAZT73Y","json":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y.json","graph_json":"https://pith.science/api/pith-number/MMXPH5K7WX6MZ7GDDLWTAZT73Y/graph.json","events_json":"https://pith.science/api/pith-number/MMXPH5K7WX6MZ7GDDLWTAZT73Y/events.json","paper":"https://pith.science/paper/MMXPH5K7"},"agent_actions":{"view_html":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y","download_json":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y.json","view_paper":"https://pith.science/paper/MMXPH5K7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.07900&json=true","fetch_graph":"https://pith.science/api/pith-number/MMXPH5K7WX6MZ7GDDLWTAZT73Y/graph.json","fetch_events":"https://pith.science/api/pith-number/MMXPH5K7WX6MZ7GDDLWTAZT73Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y/action/storage_attestation","attest_author":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y/action/author_attestation","sign_citation":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y/action/citation_signature","submit_replication":"https://pith.science/pith/MMXPH5K7WX6MZ7GDDLWTAZT73Y/action/replication_record"}},"created_at":"2026-05-20T00:05:42.872225+00:00","updated_at":"2026-05-20T00:05:42.872225+00:00"}