{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5BSJDFY325XWNIXCCCT3EE6ZTS","short_pith_number":"pith:5BSJDFY3","schema_version":"1.0","canonical_sha256":"e86491971bd76f66a2e210a7b213d99c9d6adaf86aed38740162b782d047c698","source":{"kind":"arxiv","id":"2605.26283","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aymane Ajbar, Durjoy Dey, Yuhong Yan","submitted_at":"2026-05-25T19:09:35Z","abstract_excerpt":"Modern deep learning offers powerful tools for automated retinal screening, but it remains unclear how different visual model families compare in realistic multi-disease settings and under domain shift. In this work, we benchmark twelve architectures across four model families: convolutional neural networks, vision transformers, hybrid CNN-transformer backbones, and vision-language models, using the Retinal Fundus Multi-disease Image Dataset (RFMiD). We evaluate two tasks: binary screening for any retinal disease and multi-label classification across 28 disease classes. Using standardized trai"},"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":"2605.26283","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T19:09:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a03e9f05e85f9a711e87a31b27dbd428b251bd8f5edcbe92f464549565b54b94","abstract_canon_sha256":"426a5250daf0aeebd01127e972f9a211c410103cbfd52eb3e128dba866cd52dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:10.022286Z","signature_b64":"7AvBhE8DZ64S9NJDvr7C8kt++TgvkpOJn0M3xVxW3zTBdktOssOpRZCm7BI4EZhgzg5GTYtxATTo1V0LCS6kCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e86491971bd76f66a2e210a7b213d99c9d6adaf86aed38740162b782d047c698","last_reissued_at":"2026-05-27T01:05:10.021483Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:10.021483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aymane Ajbar, Durjoy Dey, Yuhong Yan","submitted_at":"2026-05-25T19:09:35Z","abstract_excerpt":"Modern deep learning offers powerful tools for automated retinal screening, but it remains unclear how different visual model families compare in realistic multi-disease settings and under domain shift. In this work, we benchmark twelve architectures across four model families: convolutional neural networks, vision transformers, hybrid CNN-transformer backbones, and vision-language models, using the Retinal Fundus Multi-disease Image Dataset (RFMiD). We evaluate two tasks: binary screening for any retinal disease and multi-label classification across 28 disease classes. Using standardized trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26283","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/2605.26283/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":"2605.26283","created_at":"2026-05-27T01:05:10.021621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26283v1","created_at":"2026-05-27T01:05:10.021621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26283","created_at":"2026-05-27T01:05:10.021621+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BSJDFY325XW","created_at":"2026-05-27T01:05:10.021621+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BSJDFY325XWNIXC","created_at":"2026-05-27T01:05:10.021621+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BSJDFY3","created_at":"2026-05-27T01:05:10.021621+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/5BSJDFY325XWNIXCCCT3EE6ZTS","json":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS.json","graph_json":"https://pith.science/api/pith-number/5BSJDFY325XWNIXCCCT3EE6ZTS/graph.json","events_json":"https://pith.science/api/pith-number/5BSJDFY325XWNIXCCCT3EE6ZTS/events.json","paper":"https://pith.science/paper/5BSJDFY3"},"agent_actions":{"view_html":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS","download_json":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS.json","view_paper":"https://pith.science/paper/5BSJDFY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26283&json=true","fetch_graph":"https://pith.science/api/pith-number/5BSJDFY325XWNIXCCCT3EE6ZTS/graph.json","fetch_events":"https://pith.science/api/pith-number/5BSJDFY325XWNIXCCCT3EE6ZTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/action/storage_attestation","attest_author":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/action/author_attestation","sign_citation":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/action/citation_signature","submit_replication":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/action/replication_record"}},"created_at":"2026-05-27T01:05:10.021621+00:00","updated_at":"2026-05-27T01:05:10.021621+00:00"}