{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5BSJDFY325XWNIXCCCT3EE6ZTS","short_pith_number":"pith:5BSJDFY3","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"},"canonical_sha256":"e86491971bd76f66a2e210a7b213d99c9d6adaf86aed38740162b782d047c698","source":{"kind":"arxiv","id":"2605.26283","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26283","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26283v1","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26283","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"5BSJDFY325XW","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"5BSJDFY325XWNIXC","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"5BSJDFY3","created_at":"2026-05-27T01:05:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5BSJDFY325XWNIXCCCT3EE6ZTS","target":"record","payload":{"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"},"canonical_sha256":"e86491971bd76f66a2e210a7b213d99c9d6adaf86aed38740162b782d047c698","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"},"source_kind":"arxiv","source_id":"2605.26283","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJt/i0Ok0IetnNOzte3RuNZGztyJG9agF9o2w2qoCj+nSCzXXgSLKea5wu/9f2frPem0otx6beWGdepEdiXLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:50:31.437182Z"},"content_sha256":"c0d37c0846eb263f70cfe5e74dedd7f02e751128853299fc3e41160023b3948e","schema_version":"1.0","event_id":"sha256:c0d37c0846eb263f70cfe5e74dedd7f02e751128853299fc3e41160023b3948e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5BSJDFY325XWNIXCCCT3EE6ZTS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81r2BUnXTkGaLmoBpIgjuAYzfK5hCSf14KcHwww+9k800zbyTMhMFGD+pwVvEoUAWbAR/aKb2rZ6oERGiw1+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:50:31.437917Z"},"content_sha256":"0c710061b3473d6e880ac157e2a6fcf4e117dbceff471bd957bdd8911f180b18","schema_version":"1.0","event_id":"sha256:0c710061b3473d6e880ac157e2a6fcf4e117dbceff471bd957bdd8911f180b18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/bundle.json","state_url":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T06:50:31Z","links":{"resolver":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS","bundle":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/bundle.json","state":"https://pith.science/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BSJDFY325XWNIXCCCT3EE6ZTS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5BSJDFY325XWNIXCCCT3EE6ZTS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"426a5250daf0aeebd01127e972f9a211c410103cbfd52eb3e128dba866cd52dc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T19:09:35Z","title_canon_sha256":"a03e9f05e85f9a711e87a31b27dbd428b251bd8f5edcbe92f464549565b54b94"},"schema_version":"1.0","source":{"id":"2605.26283","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26283","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26283v1","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26283","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"5BSJDFY325XW","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"5BSJDFY325XWNIXC","created_at":"2026-05-27T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"5BSJDFY3","created_at":"2026-05-27T01:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:0c710061b3473d6e880ac157e2a6fcf4e117dbceff471bd957bdd8911f180b18","target":"graph","created_at":"2026-05-27T01:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.26283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aymane Ajbar, Durjoy Dey, Yuhong Yan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T19:09:35Z","title":"Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26283","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c0d37c0846eb263f70cfe5e74dedd7f02e751128853299fc3e41160023b3948e","target":"record","created_at":"2026-05-27T01:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"426a5250daf0aeebd01127e972f9a211c410103cbfd52eb3e128dba866cd52dc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T19:09:35Z","title_canon_sha256":"a03e9f05e85f9a711e87a31b27dbd428b251bd8f5edcbe92f464549565b54b94"},"schema_version":"1.0","source":{"id":"2605.26283","kind":"arxiv","version":1}},"canonical_sha256":"e86491971bd76f66a2e210a7b213d99c9d6adaf86aed38740162b782d047c698","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e86491971bd76f66a2e210a7b213d99c9d6adaf86aed38740162b782d047c698","first_computed_at":"2026-05-27T01:05:10.021483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:10.021483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7AvBhE8DZ64S9NJDvr7C8kt++TgvkpOJn0M3xVxW3zTBdktOssOpRZCm7BI4EZhgzg5GTYtxATTo1V0LCS6kCQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:10.022286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26283","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0d37c0846eb263f70cfe5e74dedd7f02e751128853299fc3e41160023b3948e","sha256:0c710061b3473d6e880ac157e2a6fcf4e117dbceff471bd957bdd8911f180b18"],"state_sha256":"abc53c8838528d6501a71794b43ad7467555c54dd6784a40f056e673d9950034"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OgLCs+0fBLtM/BG/IF+txE2306fSLQ7BZp267TF/YEX5e+8c6FxIhP+Up4qYoeR3Ajrq9cP/QQEKa9FwTcRSBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:50:31.441917Z","bundle_sha256":"846f3f441481b46b0a3bc6e9f6fcf5ea2a6e76e37fe6994c0d9d936915f48240"}}