{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XVH434MRFMVRN2ADTEL7D3VKUF","short_pith_number":"pith:XVH434MR","schema_version":"1.0","canonical_sha256":"bd4fcdf1912b2b16e8039917f1eeaaa1621f48e78e22784536e82ce51e9ecabe","source":{"kind":"arxiv","id":"2508.13068","version":1},"attestation_state":"computed","paper":{"title":"Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Farig Sadeque, Saman Sarker Joy, Shuchismita Anwar, Swakkhar Shatabda, Tanjim Islam Riju","submitted_at":"2025-08-18T16:42:29Z","abstract_excerpt":"We propose a two-stage multimodal framework that enhances disease classification and region-aware radiology report generation from chest X-rays, leveraging the MIMIC-Eye dataset. In the first stage, we introduce a gaze-guided contrastive learning architecture for disease classification. It integrates visual features, clinical labels, bounding boxes, and radiologist eye-tracking signals and is equipped with a novel multi-term gaze-attention loss combining MSE, KL divergence, correlation, and center-of-mass alignment. Incorporating fixations improves F1 score from 0.597 to 0.631 (+5.70%) and AUC"},"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":"2508.13068","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T16:42:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f446b05fe1e71866f6f7832ccaae0cf1e091ece54adafd05fd37ffcf1e7aba2","abstract_canon_sha256":"a4ec7a5fc6d87c682b18f8a2bcd0b956f4b9bb7b9e8b0c91e4828ba5578e745e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:31.911171Z","signature_b64":"i7tuu2Gnc3PVxQ7qRxB3qKJ7vvyJr7nU3jqPeUcEqZW9uo/6SWCJNfcOyIgNL+FFjq+KjdtVotYwJPdSedelDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4fcdf1912b2b16e8039917f1eeaaa1621f48e78e22784536e82ce51e9ecabe","last_reissued_at":"2026-07-05T11:55:31.910701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:31.910701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Farig Sadeque, Saman Sarker Joy, Shuchismita Anwar, Swakkhar Shatabda, Tanjim Islam Riju","submitted_at":"2025-08-18T16:42:29Z","abstract_excerpt":"We propose a two-stage multimodal framework that enhances disease classification and region-aware radiology report generation from chest X-rays, leveraging the MIMIC-Eye dataset. In the first stage, we introduce a gaze-guided contrastive learning architecture for disease classification. It integrates visual features, clinical labels, bounding boxes, and radiologist eye-tracking signals and is equipped with a novel multi-term gaze-attention loss combining MSE, KL divergence, correlation, and center-of-mass alignment. Incorporating fixations improves F1 score from 0.597 to 0.631 (+5.70%) and AUC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13068","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/2508.13068/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":"2508.13068","created_at":"2026-07-05T11:55:31.910759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13068v1","created_at":"2026-07-05T11:55:31.910759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13068","created_at":"2026-07-05T11:55:31.910759+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVH434MRFMVR","created_at":"2026-07-05T11:55:31.910759+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVH434MRFMVRN2AD","created_at":"2026-07-05T11:55:31.910759+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVH434MR","created_at":"2026-07-05T11:55:31.910759+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/XVH434MRFMVRN2ADTEL7D3VKUF","json":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF.json","graph_json":"https://pith.science/api/pith-number/XVH434MRFMVRN2ADTEL7D3VKUF/graph.json","events_json":"https://pith.science/api/pith-number/XVH434MRFMVRN2ADTEL7D3VKUF/events.json","paper":"https://pith.science/paper/XVH434MR"},"agent_actions":{"view_html":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF","download_json":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF.json","view_paper":"https://pith.science/paper/XVH434MR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13068&json=true","fetch_graph":"https://pith.science/api/pith-number/XVH434MRFMVRN2ADTEL7D3VKUF/graph.json","fetch_events":"https://pith.science/api/pith-number/XVH434MRFMVRN2ADTEL7D3VKUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF/action/storage_attestation","attest_author":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF/action/author_attestation","sign_citation":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF/action/citation_signature","submit_replication":"https://pith.science/pith/XVH434MRFMVRN2ADTEL7D3VKUF/action/replication_record"}},"created_at":"2026-07-05T11:55:31.910759+00:00","updated_at":"2026-07-05T11:55:31.910759+00:00"}