{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A56Q3SNGBVCDRRVUSV4CMZRZ7A","short_pith_number":"pith:A56Q3SNG","schema_version":"1.0","canonical_sha256":"077d0dc9a60d4438c6b49578266639f80e65be74b7e2e1f5ea818d1b95cb856a","source":{"kind":"arxiv","id":"2505.12057","version":1},"attestation_state":"computed","paper":{"title":"CorBenchX: Large-Scale Chest X-Ray Error Dataset and Vision-Language Model Benchmark for Report Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyu Lian, Jing Qin, Jing Zou, Lihao Liu, Qingqiu Li, Shujun Wang, Xiaohan Yan","submitted_at":"2025-05-17T15:39:39Z","abstract_excerpt":"AI-driven models have shown great promise in detecting errors in radiology reports, yet the field lacks a unified benchmark for rigorous evaluation of error detection and further correction. To address this gap, we introduce CorBenchX, a comprehensive suite for automated error detection and correction in chest X-ray reports, designed to advance AI-assisted quality control in clinical practice. We first synthesize a large-scale dataset of 26,326 chest X-ray error reports by injecting clinically common errors via prompting DeepSeek-R1, with each corrupted report paired with its original text, er"},"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":"2505.12057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T15:39:39Z","cross_cats_sorted":[],"title_canon_sha256":"6599d24b2da23258db10d40686dd7b1171ad0c0e46c5602abed1a8dd82bc978a","abstract_canon_sha256":"8ae7a71ecfcc865b42cb6d61c48a8d2dbc4f14795295642002fda2539f2cfdcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:57.746474Z","signature_b64":"9Et3ZXEd4MZi5Ys7HAtB6IGGNl0XArR3UCLcRqk2j8TKxIk6rUklsbz7pi5SZKarUztINsuax7Hw2ELyqmuqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"077d0dc9a60d4438c6b49578266639f80e65be74b7e2e1f5ea818d1b95cb856a","last_reissued_at":"2026-07-05T11:04:57.746023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:57.746023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CorBenchX: Large-Scale Chest X-Ray Error Dataset and Vision-Language Model Benchmark for Report Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyu Lian, Jing Qin, Jing Zou, Lihao Liu, Qingqiu Li, Shujun Wang, Xiaohan Yan","submitted_at":"2025-05-17T15:39:39Z","abstract_excerpt":"AI-driven models have shown great promise in detecting errors in radiology reports, yet the field lacks a unified benchmark for rigorous evaluation of error detection and further correction. To address this gap, we introduce CorBenchX, a comprehensive suite for automated error detection and correction in chest X-ray reports, designed to advance AI-assisted quality control in clinical practice. We first synthesize a large-scale dataset of 26,326 chest X-ray error reports by injecting clinically common errors via prompting DeepSeek-R1, with each corrupted report paired with its original text, er"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12057","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/2505.12057/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":"2505.12057","created_at":"2026-07-05T11:04:57.746081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12057v1","created_at":"2026-07-05T11:04:57.746081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12057","created_at":"2026-07-05T11:04:57.746081+00:00"},{"alias_kind":"pith_short_12","alias_value":"A56Q3SNGBVCD","created_at":"2026-07-05T11:04:57.746081+00:00"},{"alias_kind":"pith_short_16","alias_value":"A56Q3SNGBVCDRRVU","created_at":"2026-07-05T11:04:57.746081+00:00"},{"alias_kind":"pith_short_8","alias_value":"A56Q3SNG","created_at":"2026-07-05T11:04:57.746081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05810","citing_title":"CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A","json":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A.json","graph_json":"https://pith.science/api/pith-number/A56Q3SNGBVCDRRVUSV4CMZRZ7A/graph.json","events_json":"https://pith.science/api/pith-number/A56Q3SNGBVCDRRVUSV4CMZRZ7A/events.json","paper":"https://pith.science/paper/A56Q3SNG"},"agent_actions":{"view_html":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A","download_json":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A.json","view_paper":"https://pith.science/paper/A56Q3SNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12057&json=true","fetch_graph":"https://pith.science/api/pith-number/A56Q3SNGBVCDRRVUSV4CMZRZ7A/graph.json","fetch_events":"https://pith.science/api/pith-number/A56Q3SNGBVCDRRVUSV4CMZRZ7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A/action/storage_attestation","attest_author":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A/action/author_attestation","sign_citation":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A/action/citation_signature","submit_replication":"https://pith.science/pith/A56Q3SNGBVCDRRVUSV4CMZRZ7A/action/replication_record"}},"created_at":"2026-07-05T11:04:57.746081+00:00","updated_at":"2026-07-05T11:04:57.746081+00:00"}