{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KPYKXGKG6TM33VGDABTAS4QUOP","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":"ac483eb0d8c9e733f713d71c8c570ff9c761d81a8d7f80e2fbf9e490d7d19ff1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T05:54:41Z","title_canon_sha256":"af0fe25a82236ecbe2e1648689cb3e897b2a374486e5d7864bfed8ff5f0e46e0"},"schema_version":"1.0","source":{"id":"2106.00245","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00245","created_at":"2026-07-05T03:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00245v2","created_at":"2026-07-05T03:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00245","created_at":"2026-07-05T03:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"KPYKXGKG6TM3","created_at":"2026-07-05T03:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"KPYKXGKG6TM33VGD","created_at":"2026-07-05T03:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"KPYKXGKG","created_at":"2026-07-05T03:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:22c4c07fb372b3f5a74cf81781470f6dc301d4f82a32d5a8e371d4fa40eb95f0","target":"graph","created_at":"2026-07-05T03:05:33Z","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/2106.00245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains unclear whether these state-of-the-art (SOTA) models are robust when encountering examples in the wild. To study this, we introduce Adversarial VQA, a new large-scale VQA benchmark, collected iteratively via an adversarial human-and-model-in-the-loop procedure. Through this new benchmark, we discover several interesting findings. (i) Surprisingly, we find that during dataset collection, non-expert annotators can easily","authors_text":"Jie Lei, Jingjing Liu, Linjie Li, Zhe Gan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T05:54:41Z","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00245","kind":"arxiv","version":2},"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":"sha256:5204c297c6408a540324e1e967bef4d0323494c60566e783b5e0e2420d219729","target":"record","created_at":"2026-07-05T03:05:33Z","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":"ac483eb0d8c9e733f713d71c8c570ff9c761d81a8d7f80e2fbf9e490d7d19ff1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-01T05:54:41Z","title_canon_sha256":"af0fe25a82236ecbe2e1648689cb3e897b2a374486e5d7864bfed8ff5f0e46e0"},"schema_version":"1.0","source":{"id":"2106.00245","kind":"arxiv","version":2}},"canonical_sha256":"53f0ab9946f4d9bdd4c3006609721473ce99a93cebf94c945249190cebe7d6bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53f0ab9946f4d9bdd4c3006609721473ce99a93cebf94c945249190cebe7d6bc","first_computed_at":"2026-07-05T03:05:33.991493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:33.991493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WM5+gZMMA8HWYspHrVHooO8e8LS1Y54fquyLR21aW3r1S98ce8K4CeKBaVnFHjUYij4HZaATGErdNKm/PzyTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:33.991929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00245","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5204c297c6408a540324e1e967bef4d0323494c60566e783b5e0e2420d219729","sha256:22c4c07fb372b3f5a74cf81781470f6dc301d4f82a32d5a8e371d4fa40eb95f0"],"state_sha256":"15e381e388f37c186ee1f7f4533b01928bd80db008772191cf1da1f3c03bdcd6"}