{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QQYKMCIFNUMOBR6R5DYN4UNZPW","short_pith_number":"pith:QQYKMCIF","schema_version":"1.0","canonical_sha256":"8430a609056d18e0c7d1e8f0de51b97db4fa2a3bb02ad2e72f91cd1e08c1cee8","source":{"kind":"arxiv","id":"2506.04353","version":1},"attestation_state":"computed","paper":{"title":"ReXVQA: A Large-scale Visual Question Answering Benchmark for Generalist Chest X-ray Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ankit Pal, Jung-Oh Lee, Malaikannan Sankarasubbu, Meesun Lee, Pranav Rajpurkar, Seunghyeon Roh, Won Jung Kim, Xiaoman Zhang","submitted_at":"2025-06-04T18:11:59Z","abstract_excerpt":"We present ReXVQA, the largest and most comprehensive benchmark for visual question answering (VQA) in chest radiology, comprising approximately 696,000 questions paired with 160,000 chest X-rays studies across training, validation, and test sets. Unlike prior efforts that rely heavily on template based queries, ReXVQA introduces a diverse and clinically authentic task suite reflecting five core radiological reasoning skills: presence assessment, location analysis, negation detection, differential diagnosis, and geometric reasoning. We evaluate eight state-of-the-art multimodal large language "},"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":"2506.04353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T18:11:59Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.LG"],"title_canon_sha256":"1b98d65a40f121b70d2eea3202683546bfb40015ed8ab3858c0ebf7d79b7cc2b","abstract_canon_sha256":"517b48b41731680cf77f9eec274b4221a44ea6ee9bd0829bde0b000b2c0199d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:13.145910Z","signature_b64":"Eg4PqJJmAlWskwzEhMIByQm7tpn6HRnkkdroVRS9iUsqkkbHp8bP+UVpsf5NhJJPLSVllHqKsnPYrikvAgaPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8430a609056d18e0c7d1e8f0de51b97db4fa2a3bb02ad2e72f91cd1e08c1cee8","last_reissued_at":"2026-07-05T11:16:13.145336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:13.145336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReXVQA: A Large-scale Visual Question Answering Benchmark for Generalist Chest X-ray Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ankit Pal, Jung-Oh Lee, Malaikannan Sankarasubbu, Meesun Lee, Pranav Rajpurkar, Seunghyeon Roh, Won Jung Kim, Xiaoman Zhang","submitted_at":"2025-06-04T18:11:59Z","abstract_excerpt":"We present ReXVQA, the largest and most comprehensive benchmark for visual question answering (VQA) in chest radiology, comprising approximately 696,000 questions paired with 160,000 chest X-rays studies across training, validation, and test sets. Unlike prior efforts that rely heavily on template based queries, ReXVQA introduces a diverse and clinically authentic task suite reflecting five core radiological reasoning skills: presence assessment, location analysis, negation detection, differential diagnosis, and geometric reasoning. We evaluate eight state-of-the-art multimodal large language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04353","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/2506.04353/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":"2506.04353","created_at":"2026-07-05T11:16:13.145414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04353v1","created_at":"2026-07-05T11:16:13.145414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04353","created_at":"2026-07-05T11:16:13.145414+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQYKMCIFNUMO","created_at":"2026-07-05T11:16:13.145414+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQYKMCIFNUMOBR6R","created_at":"2026-07-05T11:16:13.145414+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQYKMCIF","created_at":"2026-07-05T11:16:13.145414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05810","citing_title":"CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13756","citing_title":"MedRCube: A Multidimensional Framework for Fine-Grained and In-Depth Evaluation of MLLMs in Medical Imaging","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW","json":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW.json","graph_json":"https://pith.science/api/pith-number/QQYKMCIFNUMOBR6R5DYN4UNZPW/graph.json","events_json":"https://pith.science/api/pith-number/QQYKMCIFNUMOBR6R5DYN4UNZPW/events.json","paper":"https://pith.science/paper/QQYKMCIF"},"agent_actions":{"view_html":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW","download_json":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW.json","view_paper":"https://pith.science/paper/QQYKMCIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04353&json=true","fetch_graph":"https://pith.science/api/pith-number/QQYKMCIFNUMOBR6R5DYN4UNZPW/graph.json","fetch_events":"https://pith.science/api/pith-number/QQYKMCIFNUMOBR6R5DYN4UNZPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW/action/storage_attestation","attest_author":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW/action/author_attestation","sign_citation":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW/action/citation_signature","submit_replication":"https://pith.science/pith/QQYKMCIFNUMOBR6R5DYN4UNZPW/action/replication_record"}},"created_at":"2026-07-05T11:16:13.145414+00:00","updated_at":"2026-07-05T11:16:13.145414+00:00"}