{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DMA52XWH5VDOD4IGT3TUPZMATO","short_pith_number":"pith:DMA52XWH","schema_version":"1.0","canonical_sha256":"1b01dd5ec7ed46e1f1069ee747e5809ba406ee2ba518e42f6677cd1390c50240","source":{"kind":"arxiv","id":"2405.11793","version":1},"attestation_state":"computed","paper":{"title":"MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenran Zhang, Huazhu Fu, Jianle Zhang, Ruiqi Wu, Tao Zhou, Yi Zhou","submitted_at":"2024-05-20T05:23:56Z","abstract_excerpt":"Current fundus image analysis models are predominantly built for specific tasks relying on individual datasets. The learning process is usually based on data-driven paradigm without prior knowledge, resulting in poor transferability and generalizability. To address this issue, we propose MM-Retinal, a multi-modal dataset that encompasses high-quality image-text pairs collected from professional fundus diagram books. Moreover, enabled by MM-Retinal, we present a novel Knowledge-enhanced foundational pretraining model which incorporates Fundus Image-Text expertise, called KeepFIT. It is designed"},"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":"2405.11793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T05:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"f2b0a9b181996e750cb2e4427efd7886b5abfd2933749dc314924647f3d4df20","abstract_canon_sha256":"3ce4ee7517738dd0ac842fe0f3e009b38c644504acbbc2d22b51e5c38b83e022"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:05.272601Z","signature_b64":"XKKooXpQJylALq5j5EVnlT/5mtpdWvP8kVq6QjD5UpDqtkRjBYcZb3SCuRISGFM6y7koTZGraYg+QAXEZZ22BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b01dd5ec7ed46e1f1069ee747e5809ba406ee2ba518e42f6677cd1390c50240","last_reissued_at":"2026-07-05T11:59:05.272091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:05.272091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenran Zhang, Huazhu Fu, Jianle Zhang, Ruiqi Wu, Tao Zhou, Yi Zhou","submitted_at":"2024-05-20T05:23:56Z","abstract_excerpt":"Current fundus image analysis models are predominantly built for specific tasks relying on individual datasets. The learning process is usually based on data-driven paradigm without prior knowledge, resulting in poor transferability and generalizability. To address this issue, we propose MM-Retinal, a multi-modal dataset that encompasses high-quality image-text pairs collected from professional fundus diagram books. Moreover, enabled by MM-Retinal, we present a novel Knowledge-enhanced foundational pretraining model which incorporates Fundus Image-Text expertise, called KeepFIT. It is designed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11793","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/2405.11793/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":"2405.11793","created_at":"2026-07-05T11:59:05.272150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11793v1","created_at":"2026-07-05T11:59:05.272150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11793","created_at":"2026-07-05T11:59:05.272150+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMA52XWH5VDO","created_at":"2026-07-05T11:59:05.272150+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMA52XWH5VDOD4IG","created_at":"2026-07-05T11:59:05.272150+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMA52XWH","created_at":"2026-07-05T11:59:05.272150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19522","citing_title":"REVEAL++: Differentiable Phenotypic Grouping for Vision-Language Retinal Modeling of Alzheimer's Disease Risk","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18757","citing_title":"REVEAL: Multimodal Vision-Language Alignment of Retinal Morphometry and Clinical Risks for Incident AD and Dementia Prediction","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO","json":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO.json","graph_json":"https://pith.science/api/pith-number/DMA52XWH5VDOD4IGT3TUPZMATO/graph.json","events_json":"https://pith.science/api/pith-number/DMA52XWH5VDOD4IGT3TUPZMATO/events.json","paper":"https://pith.science/paper/DMA52XWH"},"agent_actions":{"view_html":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO","download_json":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO.json","view_paper":"https://pith.science/paper/DMA52XWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11793&json=true","fetch_graph":"https://pith.science/api/pith-number/DMA52XWH5VDOD4IGT3TUPZMATO/graph.json","fetch_events":"https://pith.science/api/pith-number/DMA52XWH5VDOD4IGT3TUPZMATO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO/action/storage_attestation","attest_author":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO/action/author_attestation","sign_citation":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO/action/citation_signature","submit_replication":"https://pith.science/pith/DMA52XWH5VDOD4IGT3TUPZMATO/action/replication_record"}},"created_at":"2026-07-05T11:59:05.272150+00:00","updated_at":"2026-07-05T11:59:05.272150+00:00"}