{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CNJTIXS4R2SOBNAH3HM2FEJY4A","short_pith_number":"pith:CNJTIXS4","schema_version":"1.0","canonical_sha256":"1353345e5c8ea4e0b407d9d9a29138e0322d79517164dc64316a2023f83dfc09","source":{"kind":"arxiv","id":"2403.12416","version":3},"attestation_state":"computed","paper":{"title":"Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chong Ma, Dajiang Zhu, Dinggang Shen, Hanqi Jiang, Lei Guo, Tianming Liu, Tuo Zhang, Wenting Chen, Xiang Li, Xiaowei Yu, Yiwei Li, Zhengliang Liu, Zihao Wu","submitted_at":"2024-03-19T03:59:14Z","abstract_excerpt":"In the medical multi-modal frameworks, the alignment of cross-modality features presents a significant challenge. However, existing works have learned features that are implicitly aligned from the data, without considering the explicit relationships in the medical context. This data-reliance may lead to low generalization of the learned alignment relationships. In this work, we propose the Eye-gaze Guided Multi-modal Alignment (EGMA) framework to harness eye-gaze data for better alignment of medical visual and textual features. We explore the natural auxiliary role of radiologists' eye-gaze da"},"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":"2403.12416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T03:59:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1d3ee5e3437f3ed2d717b16989f02348690dca9c29d8c4019b4e059fd60b127c","abstract_canon_sha256":"fe55b13b40fcd4a82ee33801f289f301b7f2c1b3e8484176c3cbd06b3f59f3bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:49.429854Z","signature_b64":"qPfr5JfBl1BkNDUhDgm4txHnzgnLuf2r+dFJmfFT+CtEW/9aBoxi6EfTogI0aVAteu3QCxCdmTa+iO/SPvVHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1353345e5c8ea4e0b407d9d9a29138e0322d79517164dc64316a2023f83dfc09","last_reissued_at":"2026-07-05T08:31:49.429337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:49.429337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chong Ma, Dajiang Zhu, Dinggang Shen, Hanqi Jiang, Lei Guo, Tianming Liu, Tuo Zhang, Wenting Chen, Xiang Li, Xiaowei Yu, Yiwei Li, Zhengliang Liu, Zihao Wu","submitted_at":"2024-03-19T03:59:14Z","abstract_excerpt":"In the medical multi-modal frameworks, the alignment of cross-modality features presents a significant challenge. However, existing works have learned features that are implicitly aligned from the data, without considering the explicit relationships in the medical context. This data-reliance may lead to low generalization of the learned alignment relationships. In this work, we propose the Eye-gaze Guided Multi-modal Alignment (EGMA) framework to harness eye-gaze data for better alignment of medical visual and textual features. We explore the natural auxiliary role of radiologists' eye-gaze da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12416","kind":"arxiv","version":3},"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/2403.12416/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":"2403.12416","created_at":"2026-07-05T08:31:49.429404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12416v3","created_at":"2026-07-05T08:31:49.429404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12416","created_at":"2026-07-05T08:31:49.429404+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNJTIXS4R2SO","created_at":"2026-07-05T08:31:49.429404+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNJTIXS4R2SOBNAH","created_at":"2026-07-05T08:31:49.429404+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNJTIXS4","created_at":"2026-07-05T08:31:49.429404+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/CNJTIXS4R2SOBNAH3HM2FEJY4A","json":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A.json","graph_json":"https://pith.science/api/pith-number/CNJTIXS4R2SOBNAH3HM2FEJY4A/graph.json","events_json":"https://pith.science/api/pith-number/CNJTIXS4R2SOBNAH3HM2FEJY4A/events.json","paper":"https://pith.science/paper/CNJTIXS4"},"agent_actions":{"view_html":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A","download_json":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A.json","view_paper":"https://pith.science/paper/CNJTIXS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12416&json=true","fetch_graph":"https://pith.science/api/pith-number/CNJTIXS4R2SOBNAH3HM2FEJY4A/graph.json","fetch_events":"https://pith.science/api/pith-number/CNJTIXS4R2SOBNAH3HM2FEJY4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A/action/storage_attestation","attest_author":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A/action/author_attestation","sign_citation":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A/action/citation_signature","submit_replication":"https://pith.science/pith/CNJTIXS4R2SOBNAH3HM2FEJY4A/action/replication_record"}},"created_at":"2026-07-05T08:31:49.429404+00:00","updated_at":"2026-07-05T08:31:49.429404+00:00"}