{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EB4N25U45ZKXMBHS7GXW3ZCRWW","short_pith_number":"pith:EB4N25U4","schema_version":"1.0","canonical_sha256":"2078dd769cee557604f2f9af6de451b59e021c08edc3dd1a143211eb1748670e","source":{"kind":"arxiv","id":"2501.15798","version":1},"attestation_state":"computed","paper":{"title":"MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenran Zhang, Huazhu Fu, Na Su, Nianfeng Tang, Ruiqi Wu, Shenqi Jing, Tao Zhou, Tengfei Ma, Tianxing Wu, Tianyu Mao, Wen Fan, Yi Zhou, Zhiting Cui","submitted_at":"2025-01-27T05:49:06Z","abstract_excerpt":"Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis. Although recent methods showcase promising achievements, they significantly rely on large-scale private image-text data but pay less attention to the pretraining manner, which limits their further advancements. In this work, we introduce MM-Retinal V2, a high-quality image-text paired dataset comprising CFP, FFA, and OCT image modalities. Then, we propose a novel fundus vision-language pretraining model, namely KeepFIT V2, which is pretrained by integrating knowledge"},"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":"2501.15798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T05:49:06Z","cross_cats_sorted":[],"title_canon_sha256":"681d09dcca3b713ad44e94ddab7b16a3682e4e024ceb745f5cb95a7c7d7d01fd","abstract_canon_sha256":"fd9c627a05c61bec64abcd283a3eb87eb08ea000e275ea70b6c2d0eeb92efb49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:54.542576Z","signature_b64":"/aoeH0XBj89PT0fDJOkFRfZ7X+7b7Z3pPO3MiNg60t0vvxJw/WfIgHlq5jbCdS3C2+SRIbXLsrxz4ZmXCWT7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2078dd769cee557604f2f9af6de451b59e021c08edc3dd1a143211eb1748670e","last_reissued_at":"2026-07-05T11:57:54.542094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:54.542094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenran Zhang, Huazhu Fu, Na Su, Nianfeng Tang, Ruiqi Wu, Shenqi Jing, Tao Zhou, Tengfei Ma, Tianxing Wu, Tianyu Mao, Wen Fan, Yi Zhou, Zhiting Cui","submitted_at":"2025-01-27T05:49:06Z","abstract_excerpt":"Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis. Although recent methods showcase promising achievements, they significantly rely on large-scale private image-text data but pay less attention to the pretraining manner, which limits their further advancements. In this work, we introduce MM-Retinal V2, a high-quality image-text paired dataset comprising CFP, FFA, and OCT image modalities. Then, we propose a novel fundus vision-language pretraining model, namely KeepFIT V2, which is pretrained by integrating knowledge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15798","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/2501.15798/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":"2501.15798","created_at":"2026-07-05T11:57:54.542155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15798v1","created_at":"2026-07-05T11:57:54.542155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15798","created_at":"2026-07-05T11:57:54.542155+00:00"},{"alias_kind":"pith_short_12","alias_value":"EB4N25U45ZKX","created_at":"2026-07-05T11:57:54.542155+00:00"},{"alias_kind":"pith_short_16","alias_value":"EB4N25U45ZKXMBHS","created_at":"2026-07-05T11:57:54.542155+00:00"},{"alias_kind":"pith_short_8","alias_value":"EB4N25U4","created_at":"2026-07-05T11:57:54.542155+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/EB4N25U45ZKXMBHS7GXW3ZCRWW","json":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW.json","graph_json":"https://pith.science/api/pith-number/EB4N25U45ZKXMBHS7GXW3ZCRWW/graph.json","events_json":"https://pith.science/api/pith-number/EB4N25U45ZKXMBHS7GXW3ZCRWW/events.json","paper":"https://pith.science/paper/EB4N25U4"},"agent_actions":{"view_html":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW","download_json":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW.json","view_paper":"https://pith.science/paper/EB4N25U4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15798&json=true","fetch_graph":"https://pith.science/api/pith-number/EB4N25U45ZKXMBHS7GXW3ZCRWW/graph.json","fetch_events":"https://pith.science/api/pith-number/EB4N25U45ZKXMBHS7GXW3ZCRWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW/action/storage_attestation","attest_author":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW/action/author_attestation","sign_citation":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW/action/citation_signature","submit_replication":"https://pith.science/pith/EB4N25U45ZKXMBHS7GXW3ZCRWW/action/replication_record"}},"created_at":"2026-07-05T11:57:54.542155+00:00","updated_at":"2026-07-05T11:57:54.542155+00:00"}