{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6D4EG7NHZH7QHHU2SQAORRHCLO","short_pith_number":"pith:6D4EG7NH","schema_version":"1.0","canonical_sha256":"f0f8437da7c9ff039e9a9400e8c4e25baf43fa3d244475e7041103c51f03b200","source":{"kind":"arxiv","id":"2505.22222","version":1},"attestation_state":"computed","paper":{"title":"Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Honghan Wu, Jiashu Shen, Jinge Wu, Pardeep Vasudev, Su-Hwan Kim, Yunsoo Kim","submitted_at":"2025-05-28T10:54:40Z","abstract_excerpt":"Recent advancements in multimodal Large Language Models (LLMs) have significantly enhanced the automation of medical image analysis, particularly in generating radiology reports from chest X-rays (CXR). However, these models still suffer from hallucinations and clinically significant errors, limiting their reliability in real-world applications. In this study, we propose Look & Mark (L&M), a novel grounding fixation strategy that integrates radiologist eye fixations (Look) and bounding box annotations (Mark) into the LLM prompting framework. Unlike conventional fine-tuning, L&M leverages in-co"},"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":"2505.22222","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T10:54:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e0fd44745bc6fe6f48f82443fc1aae9bffa37e4f2ebbf9960f8584efca574d96","abstract_canon_sha256":"ab6f2a6ec62e717bd654df5ab5a59aedeea5b8bc04f7e6d8a91d2f4e682edc16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:11.672205Z","signature_b64":"i2hHLOYTWnbVCCqzv/uTEcnLGQl9Biv8vQMirmEhbLI4Q5dRFBzyBybZ/yiG2UbXWkA6MH+8alO18vv9HYbtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f8437da7c9ff039e9a9400e8c4e25baf43fa3d244475e7041103c51f03b200","last_reissued_at":"2026-07-05T11:11:11.671634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:11.671634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Honghan Wu, Jiashu Shen, Jinge Wu, Pardeep Vasudev, Su-Hwan Kim, Yunsoo Kim","submitted_at":"2025-05-28T10:54:40Z","abstract_excerpt":"Recent advancements in multimodal Large Language Models (LLMs) have significantly enhanced the automation of medical image analysis, particularly in generating radiology reports from chest X-rays (CXR). However, these models still suffer from hallucinations and clinically significant errors, limiting their reliability in real-world applications. In this study, we propose Look & Mark (L&M), a novel grounding fixation strategy that integrates radiologist eye fixations (Look) and bounding box annotations (Mark) into the LLM prompting framework. Unlike conventional fine-tuning, L&M leverages in-co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22222","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/2505.22222/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":"2505.22222","created_at":"2026-07-05T11:11:11.671699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22222v1","created_at":"2026-07-05T11:11:11.671699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22222","created_at":"2026-07-05T11:11:11.671699+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D4EG7NHZH7Q","created_at":"2026-07-05T11:11:11.671699+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D4EG7NHZH7QHHU2","created_at":"2026-07-05T11:11:11.671699+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D4EG7NH","created_at":"2026-07-05T11:11:11.671699+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/6D4EG7NHZH7QHHU2SQAORRHCLO","json":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO.json","graph_json":"https://pith.science/api/pith-number/6D4EG7NHZH7QHHU2SQAORRHCLO/graph.json","events_json":"https://pith.science/api/pith-number/6D4EG7NHZH7QHHU2SQAORRHCLO/events.json","paper":"https://pith.science/paper/6D4EG7NH"},"agent_actions":{"view_html":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO","download_json":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO.json","view_paper":"https://pith.science/paper/6D4EG7NH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22222&json=true","fetch_graph":"https://pith.science/api/pith-number/6D4EG7NHZH7QHHU2SQAORRHCLO/graph.json","fetch_events":"https://pith.science/api/pith-number/6D4EG7NHZH7QHHU2SQAORRHCLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO/action/storage_attestation","attest_author":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO/action/author_attestation","sign_citation":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO/action/citation_signature","submit_replication":"https://pith.science/pith/6D4EG7NHZH7QHHU2SQAORRHCLO/action/replication_record"}},"created_at":"2026-07-05T11:11:11.671699+00:00","updated_at":"2026-07-05T11:11:11.671699+00:00"}