{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OWSSBIK4SGVAPGGJ5ULKEENQAV","short_pith_number":"pith:OWSSBIK4","schema_version":"1.0","canonical_sha256":"75a520a15c91aa0798c9ed16a211b00579fe2ec19bff400bbd9035231a1d6ba1","source":{"kind":"arxiv","id":"2606.21020","version":1},"attestation_state":"computed","paper":{"title":"CheXpercept: A Benchmark for Evaluating Expert-Level Lesion Perception in Chest X-rays","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Edward Choi, Geon Choi, Hangyul Yoon, Hyunju Shin, Hyunki Park, Jeong Yun Jang, Nalee Kim, Sang Hoon Seo","submitted_at":"2026-06-19T01:10:24Z","abstract_excerpt":"The evaluation of vision-language models (VLMs) for chest X-ray (CXR) analysis has largely been limited to disease-presence classification without visual grounding. Such evaluations fail to verify the expert-level lesion perception necessary to ensure the clinical reliability of VLMs. To address these limitations, we introduce CheXpercept, a sequential, multi-level perception benchmark that mirrors a radiologist's cognitive workflow across coarse-level detection, fine-level contour evaluation and revision, and semantic-level attribute extraction. To ensure high clinical fidelity at scale, we c"},"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":"2606.21020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T01:10:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a2d8746302b72825a8951d7a4141e61086c32d493b1558664747c9aaffe45ab","abstract_canon_sha256":"84e1471d9bda5822a539b72a0338952090c34bcc3ced0b28776434c454178c86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:27.081509Z","signature_b64":"FU8VzuUwv709Y2E+T0YU473Hk4aofVO86XXR4YpVzgrEX4fB8dPpkKA/wkEb58/5zVq6WFfy7RuljB54uHYHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75a520a15c91aa0798c9ed16a211b00579fe2ec19bff400bbd9035231a1d6ba1","last_reissued_at":"2026-06-23T01:12:27.081014Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:27.081014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CheXpercept: A Benchmark for Evaluating Expert-Level Lesion Perception in Chest X-rays","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Edward Choi, Geon Choi, Hangyul Yoon, Hyunju Shin, Hyunki Park, Jeong Yun Jang, Nalee Kim, Sang Hoon Seo","submitted_at":"2026-06-19T01:10:24Z","abstract_excerpt":"The evaluation of vision-language models (VLMs) for chest X-ray (CXR) analysis has largely been limited to disease-presence classification without visual grounding. Such evaluations fail to verify the expert-level lesion perception necessary to ensure the clinical reliability of VLMs. To address these limitations, we introduce CheXpercept, a sequential, multi-level perception benchmark that mirrors a radiologist's cognitive workflow across coarse-level detection, fine-level contour evaluation and revision, and semantic-level attribute extraction. To ensure high clinical fidelity at scale, we c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21020","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/2606.21020/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":"2606.21020","created_at":"2026-06-23T01:12:27.081086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21020v1","created_at":"2026-06-23T01:12:27.081086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21020","created_at":"2026-06-23T01:12:27.081086+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWSSBIK4SGVA","created_at":"2026-06-23T01:12:27.081086+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWSSBIK4SGVAPGGJ","created_at":"2026-06-23T01:12:27.081086+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWSSBIK4","created_at":"2026-06-23T01:12:27.081086+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/OWSSBIK4SGVAPGGJ5ULKEENQAV","json":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV.json","graph_json":"https://pith.science/api/pith-number/OWSSBIK4SGVAPGGJ5ULKEENQAV/graph.json","events_json":"https://pith.science/api/pith-number/OWSSBIK4SGVAPGGJ5ULKEENQAV/events.json","paper":"https://pith.science/paper/OWSSBIK4"},"agent_actions":{"view_html":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV","download_json":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV.json","view_paper":"https://pith.science/paper/OWSSBIK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21020&json=true","fetch_graph":"https://pith.science/api/pith-number/OWSSBIK4SGVAPGGJ5ULKEENQAV/graph.json","fetch_events":"https://pith.science/api/pith-number/OWSSBIK4SGVAPGGJ5ULKEENQAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV/action/storage_attestation","attest_author":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV/action/author_attestation","sign_citation":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV/action/citation_signature","submit_replication":"https://pith.science/pith/OWSSBIK4SGVAPGGJ5ULKEENQAV/action/replication_record"}},"created_at":"2026-06-23T01:12:27.081086+00:00","updated_at":"2026-06-23T01:12:27.081086+00:00"}