{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SXJ2IZQZPDL5F7K5TNFRVHGYUB","short_pith_number":"pith:SXJ2IZQZ","schema_version":"1.0","canonical_sha256":"95d3a4661978d7d2fd5d9b4b1a9cd8a075446cc517c7f7bf7e468707815dbfa4","source":{"kind":"arxiv","id":"2403.10153","version":3},"attestation_state":"computed","paper":{"title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Pekka Marttinen, Yogesh Kumar","submitted_at":"2024-03-15T09:54:04Z","abstract_excerpt":"We introduce eCLIP, an enhanced version of the CLIP model that integrates expert annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in contrastive multi-modal medical imaging analysis, notably data scarcity and the \"modality gap\" -- a significant disparity between image and text embeddings that diminishes the quality of representations and hampers cross-modal interoperability. eCLIP integrates a heatmap processor and leverages mixup augmentation to efficiently utilize the scarce expert annotations, thus boosting the model's learning effectiveness. eCLIP is desi"},"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":"2403.10153","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T09:54:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37dd20fde10854f4b3d6cf8f32ae9f160fa0009b55a1e8eb21b4b58c6bc14f04","abstract_canon_sha256":"1d80345902fbf130d004439c27a03a8ae8cee52d7e5b602075c9cbb51f3ab08a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:53.958706Z","signature_b64":"wjCqUZgb7ve+aS4zVIrp4rrPDPc0OM5OuE5C+uHfowUdHpEjwmjUGWssG9ZdjyJu2r7gMe9QBmPWyyb3Di/1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d3a4661978d7d2fd5d9b4b1a9cd8a075446cc517c7f7bf7e468707815dbfa4","last_reissued_at":"2026-07-05T08:43:53.958134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:53.958134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Pekka Marttinen, Yogesh Kumar","submitted_at":"2024-03-15T09:54:04Z","abstract_excerpt":"We introduce eCLIP, an enhanced version of the CLIP model that integrates expert annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in contrastive multi-modal medical imaging analysis, notably data scarcity and the \"modality gap\" -- a significant disparity between image and text embeddings that diminishes the quality of representations and hampers cross-modal interoperability. eCLIP integrates a heatmap processor and leverages mixup augmentation to efficiently utilize the scarce expert annotations, thus boosting the model's learning effectiveness. eCLIP is desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10153","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/2403.10153/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":"2403.10153","created_at":"2026-07-05T08:43:53.958220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10153v3","created_at":"2026-07-05T08:43:53.958220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10153","created_at":"2026-07-05T08:43:53.958220+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXJ2IZQZPDL5","created_at":"2026-07-05T08:43:53.958220+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXJ2IZQZPDL5F7K5","created_at":"2026-07-05T08:43:53.958220+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXJ2IZQZ","created_at":"2026-07-05T08:43:53.958220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10733","citing_title":"A CNN-Transformer for Classification of Longitudinal 3D MRI Images -- A Case Study on Hepatocellular Carcinoma Prediction","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB","json":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB.json","graph_json":"https://pith.science/api/pith-number/SXJ2IZQZPDL5F7K5TNFRVHGYUB/graph.json","events_json":"https://pith.science/api/pith-number/SXJ2IZQZPDL5F7K5TNFRVHGYUB/events.json","paper":"https://pith.science/paper/SXJ2IZQZ"},"agent_actions":{"view_html":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB","download_json":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB.json","view_paper":"https://pith.science/paper/SXJ2IZQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10153&json=true","fetch_graph":"https://pith.science/api/pith-number/SXJ2IZQZPDL5F7K5TNFRVHGYUB/graph.json","fetch_events":"https://pith.science/api/pith-number/SXJ2IZQZPDL5F7K5TNFRVHGYUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB/action/storage_attestation","attest_author":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB/action/author_attestation","sign_citation":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB/action/citation_signature","submit_replication":"https://pith.science/pith/SXJ2IZQZPDL5F7K5TNFRVHGYUB/action/replication_record"}},"created_at":"2026-07-05T08:43:53.958220+00:00","updated_at":"2026-07-05T08:43:53.958220+00:00"}