{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SJJC55N3LSKPLQFJ3JGUH5BBCY","short_pith_number":"pith:SJJC55N3","canonical_record":{"source":{"id":"2407.03386","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T08:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"e7dfbcf81e5d7c6ecaa7b24c2bbb2813ad5823adf23feb3e4dc60608dd292079","abstract_canon_sha256":"588468df76745de6b8f3a31722b3b5f1e8c9a5d63796573baf5ea305d66f7c1d"},"schema_version":"1.0"},"canonical_sha256":"92522ef5bb5c94f5c0a9da4d43f4211612c7d6ce6f33e4c4115b7092796ebbd0","source":{"kind":"arxiv","id":"2407.03386","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03386","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03386v5","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03386","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"SJJC55N3LSKP","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"SJJC55N3LSKPLQFJ","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"SJJC55N3","created_at":"2026-07-05T09:27:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SJJC55N3LSKPLQFJ3JGUH5BBCY","target":"record","payload":{"canonical_record":{"source":{"id":"2407.03386","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T08:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"e7dfbcf81e5d7c6ecaa7b24c2bbb2813ad5823adf23feb3e4dc60608dd292079","abstract_canon_sha256":"588468df76745de6b8f3a31722b3b5f1e8c9a5d63796573baf5ea305d66f7c1d"},"schema_version":"1.0"},"canonical_sha256":"92522ef5bb5c94f5c0a9da4d43f4211612c7d6ce6f33e4c4115b7092796ebbd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:56.562064Z","signature_b64":"/Xoni+bMooGbygTEYycm4exSdFHyaCjIT4lpBgH760Ni2DyyPpbWYvYFwwmIUr7zzh4MI3o9+Jhs0PPhk4ypBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92522ef5bb5c94f5c0a9da4d43f4211612c7d6ce6f33e4c4115b7092796ebbd0","last_reissued_at":"2026-07-05T09:27:56.561549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:56.561549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.03386","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ct13WwOuFiMxHsgq2t6eLW5YiXVa+3QKcXrN0iV7n+t0zeT/MIEXIkkEQwi3DkaSIC0tnDZ8enKaqYYt1mNfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T22:08:58.406861Z"},"content_sha256":"0615c92cd5c620ede83371f5bd9ae4e3b3603a61b5420aeede22cafac810520b","schema_version":"1.0","event_id":"sha256:0615c92cd5c620ede83371f5bd9ae4e3b3603a61b5420aeede22cafac810520b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SJJC55N3LSKPLQFJ3JGUH5BBCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Robustness Benchmark for Visual Question Answering (VQA)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abu Raihan Mostofa Kamal, Ishmam Tashdeed, Md. Azam Hossain, Md Farhan Ishmam, Md Hamjajul Ashmafee, Talukder Asir Saadat","submitted_at":"2024-07-03T08:35:03Z","abstract_excerpt":"Can Visual Question Answering (VQA) systems perform just as well when deployed in the real world? Or are they susceptible to realistic corruption effects e.g. image blur, which can be detrimental in sensitive applications, such as medical VQA? While linguistic or textual robustness has been thoroughly explored in the VQA literature, there has yet to be any significant work on the visual robustness of VQA models. We propose the first large-scale benchmark comprising 213,000 augmented images, challenging the visual robustness of multiple VQA models and assessing the strength of realistic visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03386","kind":"arxiv","version":5},"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/2407.03386/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":"2026-07-05T09:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQXzQK+9xBqf54DQyRsf5HQaznX+IF7ckaZ/h8ycBoFH2b8uCvV8tY/U8EPYPieqQKjhpOqxkUnAU5HbLL2GCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T22:08:58.407508Z"},"content_sha256":"9c2ea92d2f29b3d31ddab86cfb5ef5e2ae9a49fe690b3094f27003a54b9fb2c7","schema_version":"1.0","event_id":"sha256:9c2ea92d2f29b3d31ddab86cfb5ef5e2ae9a49fe690b3094f27003a54b9fb2c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJJC55N3LSKPLQFJ3JGUH5BBCY/bundle.json","state_url":"https://pith.science/pith/SJJC55N3LSKPLQFJ3JGUH5BBCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJJC55N3LSKPLQFJ3JGUH5BBCY/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":"2026-07-11T22:08:58Z","links":{"resolver":"https://pith.science/pith/SJJC55N3LSKPLQFJ3JGUH5BBCY","bundle":"https://pith.science/pith/SJJC55N3LSKPLQFJ3JGUH5BBCY/bundle.json","state":"https://pith.science/pith/SJJC55N3LSKPLQFJ3JGUH5BBCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJJC55N3LSKPLQFJ3JGUH5BBCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SJJC55N3LSKPLQFJ3JGUH5BBCY","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":"588468df76745de6b8f3a31722b3b5f1e8c9a5d63796573baf5ea305d66f7c1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T08:35:03Z","title_canon_sha256":"e7dfbcf81e5d7c6ecaa7b24c2bbb2813ad5823adf23feb3e4dc60608dd292079"},"schema_version":"1.0","source":{"id":"2407.03386","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03386","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03386v5","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03386","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"SJJC55N3LSKP","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"SJJC55N3LSKPLQFJ","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"SJJC55N3","created_at":"2026-07-05T09:27:56Z"}],"graph_snapshots":[{"event_id":"sha256:9c2ea92d2f29b3d31ddab86cfb5ef5e2ae9a49fe690b3094f27003a54b9fb2c7","target":"graph","created_at":"2026-07-05T09:27:56Z","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/2407.03386/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can Visual Question Answering (VQA) systems perform just as well when deployed in the real world? Or are they susceptible to realistic corruption effects e.g. image blur, which can be detrimental in sensitive applications, such as medical VQA? While linguistic or textual robustness has been thoroughly explored in the VQA literature, there has yet to be any significant work on the visual robustness of VQA models. We propose the first large-scale benchmark comprising 213,000 augmented images, challenging the visual robustness of multiple VQA models and assessing the strength of realistic visual ","authors_text":"Abu Raihan Mostofa Kamal, Ishmam Tashdeed, Md. Azam Hossain, Md Farhan Ishmam, Md Hamjajul Ashmafee, Talukder Asir Saadat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T08:35:03Z","title":"Visual Robustness Benchmark for Visual Question Answering (VQA)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03386","kind":"arxiv","version":5},"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":"sha256:0615c92cd5c620ede83371f5bd9ae4e3b3603a61b5420aeede22cafac810520b","target":"record","created_at":"2026-07-05T09:27:56Z","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":"588468df76745de6b8f3a31722b3b5f1e8c9a5d63796573baf5ea305d66f7c1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T08:35:03Z","title_canon_sha256":"e7dfbcf81e5d7c6ecaa7b24c2bbb2813ad5823adf23feb3e4dc60608dd292079"},"schema_version":"1.0","source":{"id":"2407.03386","kind":"arxiv","version":5}},"canonical_sha256":"92522ef5bb5c94f5c0a9da4d43f4211612c7d6ce6f33e4c4115b7092796ebbd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92522ef5bb5c94f5c0a9da4d43f4211612c7d6ce6f33e4c4115b7092796ebbd0","first_computed_at":"2026-07-05T09:27:56.561549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:56.561549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Xoni+bMooGbygTEYycm4exSdFHyaCjIT4lpBgH760Ni2DyyPpbWYvYFwwmIUr7zzh4MI3o9+Jhs0PPhk4ypBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:56.562064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03386","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0615c92cd5c620ede83371f5bd9ae4e3b3603a61b5420aeede22cafac810520b","sha256:9c2ea92d2f29b3d31ddab86cfb5ef5e2ae9a49fe690b3094f27003a54b9fb2c7"],"state_sha256":"77d5690de304134d828f55ea2dc4494e12976706d3f795be99e5d80f4e6a1956"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHd0lIF1HjZkA8/lYfLu+SnggpnPXniO6xUKxUkYhDLjkOkeBvKThXTwXuUx9v5MUcMrKSq5hPk5kIYpSLr0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T22:08:58.411259Z","bundle_sha256":"9e1785f744fdf3f3d20e5516240d845d59462f25007d7cc483aca9f3143703d1"}}