{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TZ5I2NXV3WTFB23V6OGVUYG6RF","short_pith_number":"pith:TZ5I2NXV","schema_version":"1.0","canonical_sha256":"9e7a8d36f5dda650eb75f38d5a60de8943704e64e6e25f4381e392fb5fbc04f3","source":{"kind":"arxiv","id":"2509.15234","version":2},"attestation_state":"computed","paper":{"title":"Exploring the Capabilities of Large Language Model Encoders for Image-Text Retrieval in Chest X-rays","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changi Kim, Chang Min Park, Dongheon Lee, Donguk Kim, Gihun Cho, Hanbin Ko, Inhyeok Baek, Joonbeom Koo","submitted_at":"2025-09-17T09:44:59Z","abstract_excerpt":"Multimodal learning from paired medical images and clinical text is a central challenge in medical data-driven informatics, where effective cross-modal alignment is critical for scalable analysis and retrieval. In chest radiography, vision-language pretraining is constrained by heterogeneous radiology reports that contain abbreviations, impression-only notes, and institution-specific writing styles. Unlike general-domain settings, naively aggregating large collections of noisy reports can plateau or even degrade multimodal learning when reporting styles differ substantially. We propose a domai"},"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":"2509.15234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-17T09:44:59Z","cross_cats_sorted":[],"title_canon_sha256":"b96e4d335093376f07010902ac61624a5381764b97af52a9ea3378ab0a0ee86e","abstract_canon_sha256":"e6dcb6d952aba583e35b8b78c785f3206bfc90aafd7819036b0a916677c49497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:47.841284Z","signature_b64":"F8WuQGRIpyZaG5aG7s8kPXBZtru7VYFj8iKb92hg8TTiIFj6i89blzJTbv9iMm9u7IBgEbNMYANL/xKIiN4vDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e7a8d36f5dda650eb75f38d5a60de8943704e64e6e25f4381e392fb5fbc04f3","last_reissued_at":"2026-06-02T02:04:47.840765Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:47.840765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Capabilities of Large Language Model Encoders for Image-Text Retrieval in Chest X-rays","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changi Kim, Chang Min Park, Dongheon Lee, Donguk Kim, Gihun Cho, Hanbin Ko, Inhyeok Baek, Joonbeom Koo","submitted_at":"2025-09-17T09:44:59Z","abstract_excerpt":"Multimodal learning from paired medical images and clinical text is a central challenge in medical data-driven informatics, where effective cross-modal alignment is critical for scalable analysis and retrieval. In chest radiography, vision-language pretraining is constrained by heterogeneous radiology reports that contain abbreviations, impression-only notes, and institution-specific writing styles. Unlike general-domain settings, naively aggregating large collections of noisy reports can plateau or even degrade multimodal learning when reporting styles differ substantially. We propose a domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15234","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/2509.15234/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":"2509.15234","created_at":"2026-06-02T02:04:47.840835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.15234v2","created_at":"2026-06-02T02:04:47.840835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15234","created_at":"2026-06-02T02:04:47.840835+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZ5I2NXV3WTF","created_at":"2026-06-02T02:04:47.840835+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZ5I2NXV3WTFB23V","created_at":"2026-06-02T02:04:47.840835+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZ5I2NXV","created_at":"2026-06-02T02:04:47.840835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.04563","citing_title":"Temporal Inversion for Learning Interval Change in Chest X-Rays","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF","json":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF.json","graph_json":"https://pith.science/api/pith-number/TZ5I2NXV3WTFB23V6OGVUYG6RF/graph.json","events_json":"https://pith.science/api/pith-number/TZ5I2NXV3WTFB23V6OGVUYG6RF/events.json","paper":"https://pith.science/paper/TZ5I2NXV"},"agent_actions":{"view_html":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF","download_json":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF.json","view_paper":"https://pith.science/paper/TZ5I2NXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.15234&json=true","fetch_graph":"https://pith.science/api/pith-number/TZ5I2NXV3WTFB23V6OGVUYG6RF/graph.json","fetch_events":"https://pith.science/api/pith-number/TZ5I2NXV3WTFB23V6OGVUYG6RF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF/action/storage_attestation","attest_author":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF/action/author_attestation","sign_citation":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF/action/citation_signature","submit_replication":"https://pith.science/pith/TZ5I2NXV3WTFB23V6OGVUYG6RF/action/replication_record"}},"created_at":"2026-06-02T02:04:47.840835+00:00","updated_at":"2026-06-02T02:04:47.840835+00:00"}