{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HPXWSEPXQRVZKWQZI2VWFNCUD2","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":"39bea77ffecb0224fd3baac6ddbe5fbd21447141f0aabd94dc21146e30c8f374","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T04:09:23Z","title_canon_sha256":"e3b1676179e2ef0f91347882e3d4cca9393c9fd58dae9db194d4c766d62b0965"},"schema_version":"1.0","source":{"id":"2205.01883","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.01883","created_at":"2026-07-05T04:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2205.01883v1","created_at":"2026-07-05T04:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01883","created_at":"2026-07-05T04:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"HPXWSEPXQRVZ","created_at":"2026-07-05T04:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"HPXWSEPXQRVZKWQZ","created_at":"2026-07-05T04:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"HPXWSEPX","created_at":"2026-07-05T04:20:23Z"}],"graph_snapshots":[{"event_id":"sha256:26e7885beea200e52a3e5d77950bba560f7c3661fdce1df3a567bc6458d738b3","target":"graph","created_at":"2026-07-05T04:20:23Z","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/2205.01883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of data creation. In this paper, we propose a method that automatically derives VQA examples at volume, by leveraging the abundance of existing image-caption annotations combined with neural models for textual question generation. We show that the resulting data is of high-quality. VQA models trained on our data improve state-of-the-art zero-shot accuracy by double digits and achieve a level of robustness that lacks in the same model trained on human-a","authors_text":"Doron Kukliansky, Idan Szpektor, Nan Ding, Radu Soricut, Soravit Changpinyo, Xi Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T04:09:23Z","title":"All You May Need for VQA are Image Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01883","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:cc3fe31f5570b9e2c7c93b2c62d3928dc686bca12362ec9a156f463b36d8e2ad","target":"record","created_at":"2026-07-05T04:20:23Z","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":"39bea77ffecb0224fd3baac6ddbe5fbd21447141f0aabd94dc21146e30c8f374","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T04:09:23Z","title_canon_sha256":"e3b1676179e2ef0f91347882e3d4cca9393c9fd58dae9db194d4c766d62b0965"},"schema_version":"1.0","source":{"id":"2205.01883","kind":"arxiv","version":1}},"canonical_sha256":"3bef6911f7846b955a1946ab62b4541e899241076fdd8eaad17ff865ea003203","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bef6911f7846b955a1946ab62b4541e899241076fdd8eaad17ff865ea003203","first_computed_at":"2026-07-05T04:20:23.230711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:23.230711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GH87PS/FkHfBFR6tb1dbEO8Z5zRgkD2iL6IOco/mx9WqEa5xlrhlEuGTA7JR4fDajDOcmqXtn6Hf95MmhYmDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:23.231261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.01883","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc3fe31f5570b9e2c7c93b2c62d3928dc686bca12362ec9a156f463b36d8e2ad","sha256:26e7885beea200e52a3e5d77950bba560f7c3661fdce1df3a567bc6458d738b3"],"state_sha256":"d19b871776fe762a9083d10fdfbd427f268894397718b6a3c0c3dc6a98602bc8"}