{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YYIFJ3MKB75ZAS4JGYKYY25LZZ","short_pith_number":"pith:YYIFJ3MK","schema_version":"1.0","canonical_sha256":"c61054ed8a0ffb904b8936158c6babce5c148b4299fa416ebd5113d5dd93fbf2","source":{"kind":"arxiv","id":"2502.05928","version":4},"attestation_state":"computed","paper":{"title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Hongjin Zhao, Hongyu Ge, Longkun Hao, Shoujun Zhou, Yihang Liu, Zhenxin Lin, Zihui Xu","submitted_at":"2025-02-09T15:08:10Z","abstract_excerpt":"Medical Visual Question Answering (Med-VQA) represents a critical and challenging subtask within the general VQA domain. Despite significant advancements in general VQA, multimodal large language models (MLLMs) still exhibit substantial limitations when handling multi-task VQA scenarios. These limitations manifest through erroneous spatial localization and misinterpretation of medical images, which primarily arise from two fundamental issues: inadequate image-text alignment and insufficient domain-specified knowledge for medical applications. To address these issues, we introduce the Cross-Mod"},"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":"2502.05928","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-09T15:08:10Z","cross_cats_sorted":[],"title_canon_sha256":"3ea17451c374b56621c85fca55cd81405b84da1da87cffdc952c7f9670498ee8","abstract_canon_sha256":"ec3a54cf2e0f43cad06255d661f2e871fc112c66a4c329b907dd3f02f04a5000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:12.064828Z","signature_b64":"Mhh2p1W6OjGHHcJmC2JZ+4mmP0f231B+E8nQOltJeNdGqr01dY/JvpnCQWd3SjMFnmzRo5LTM6xUha2rBoR1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c61054ed8a0ffb904b8936158c6babce5c148b4299fa416ebd5113d5dd93fbf2","last_reissued_at":"2026-07-05T11:35:12.064342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:12.064342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Hongjin Zhao, Hongyu Ge, Longkun Hao, Shoujun Zhou, Yihang Liu, Zhenxin Lin, Zihui Xu","submitted_at":"2025-02-09T15:08:10Z","abstract_excerpt":"Medical Visual Question Answering (Med-VQA) represents a critical and challenging subtask within the general VQA domain. Despite significant advancements in general VQA, multimodal large language models (MLLMs) still exhibit substantial limitations when handling multi-task VQA scenarios. These limitations manifest through erroneous spatial localization and misinterpretation of medical images, which primarily arise from two fundamental issues: inadequate image-text alignment and insufficient domain-specified knowledge for medical applications. To address these issues, we introduce the Cross-Mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05928","kind":"arxiv","version":4},"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/2502.05928/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":"2502.05928","created_at":"2026-07-05T11:35:12.064399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05928v4","created_at":"2026-07-05T11:35:12.064399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05928","created_at":"2026-07-05T11:35:12.064399+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYIFJ3MKB75Z","created_at":"2026-07-05T11:35:12.064399+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYIFJ3MKB75ZAS4J","created_at":"2026-07-05T11:35:12.064399+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYIFJ3MK","created_at":"2026-07-05T11:35:12.064399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11106","citing_title":"FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language model","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ","json":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ.json","graph_json":"https://pith.science/api/pith-number/YYIFJ3MKB75ZAS4JGYKYY25LZZ/graph.json","events_json":"https://pith.science/api/pith-number/YYIFJ3MKB75ZAS4JGYKYY25LZZ/events.json","paper":"https://pith.science/paper/YYIFJ3MK"},"agent_actions":{"view_html":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ","download_json":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ.json","view_paper":"https://pith.science/paper/YYIFJ3MK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05928&json=true","fetch_graph":"https://pith.science/api/pith-number/YYIFJ3MKB75ZAS4JGYKYY25LZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YYIFJ3MKB75ZAS4JGYKYY25LZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ/action/storage_attestation","attest_author":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ/action/author_attestation","sign_citation":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ/action/citation_signature","submit_replication":"https://pith.science/pith/YYIFJ3MKB75ZAS4JGYKYY25LZZ/action/replication_record"}},"created_at":"2026-07-05T11:35:12.064399+00:00","updated_at":"2026-07-05T11:35:12.064399+00:00"}