{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N4TDF6BJYS5WNPL64MN6YZ3OW4","short_pith_number":"pith:N4TDF6BJ","schema_version":"1.0","canonical_sha256":"6f2632f829c4bb66bd7ee31bec676eb70ea8395720fa537006b9baff462a16ca","source":{"kind":"arxiv","id":"1902.05660","version":1},"attestation_state":"computed","paper":{"title":"Cycle-Consistency for Robust Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Marcus Rohrbach, Meet Shah, Xinlei Chen","submitted_at":"2019-02-15T02:07:18Z","abstract_excerpt":"Despite significant progress in Visual Question Answering over the years, robustness of today's VQA models leave much to be desired. We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that state-of-the-art VQA models are notoriously brittle to linguistic variations in questions. VQA-Rephrasings contains 3 human-provided rephrasings for 40k questions spanning 40k images from the VQA v2.0 validation dataset. As a step towards improving robustness of VQA models, we propose a model-agnostic framework that exploits cycle consistency. Specifically, we train a mo"},"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":"1902.05660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-15T02:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"9d897e24fd86fc89ffa1b8c88b367e3d13af99b9d64cbcf73bc52566aa79eaa8","abstract_canon_sha256":"1d8696a6697cf2d89fe9c2078247217daf02a841a8ab33f42c7220278e6bbc16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:56.609770Z","signature_b64":"uAUmo0NSnt2RBpOreC0MBybAbPlyjg9jaRTF1jh8pt7deG4cwZ3m97/i1bj2gFAu/Hw2BDKuArXue+obT/zrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f2632f829c4bb66bd7ee31bec676eb70ea8395720fa537006b9baff462a16ca","last_reissued_at":"2026-05-17T23:53:56.608928Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:56.608928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cycle-Consistency for Robust Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Marcus Rohrbach, Meet Shah, Xinlei Chen","submitted_at":"2019-02-15T02:07:18Z","abstract_excerpt":"Despite significant progress in Visual Question Answering over the years, robustness of today's VQA models leave much to be desired. We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that state-of-the-art VQA models are notoriously brittle to linguistic variations in questions. VQA-Rephrasings contains 3 human-provided rephrasings for 40k questions spanning 40k images from the VQA v2.0 validation dataset. As a step towards improving robustness of VQA models, we propose a model-agnostic framework that exploits cycle consistency. Specifically, we train a mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05660","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":""},"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":"1902.05660","created_at":"2026-05-17T23:53:56.609076+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05660v1","created_at":"2026-05-17T23:53:56.609076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05660","created_at":"2026-05-17T23:53:56.609076+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4TDF6BJYS5W","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4TDF6BJYS5WNPL6","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4TDF6BJ","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2308.13418","citing_title":"Nougat: Neural Optical Understanding for Academic Documents","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4","json":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4.json","graph_json":"https://pith.science/api/pith-number/N4TDF6BJYS5WNPL64MN6YZ3OW4/graph.json","events_json":"https://pith.science/api/pith-number/N4TDF6BJYS5WNPL64MN6YZ3OW4/events.json","paper":"https://pith.science/paper/N4TDF6BJ"},"agent_actions":{"view_html":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4","download_json":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4.json","view_paper":"https://pith.science/paper/N4TDF6BJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05660&json=true","fetch_graph":"https://pith.science/api/pith-number/N4TDF6BJYS5WNPL64MN6YZ3OW4/graph.json","fetch_events":"https://pith.science/api/pith-number/N4TDF6BJYS5WNPL64MN6YZ3OW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4/action/storage_attestation","attest_author":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4/action/author_attestation","sign_citation":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4/action/citation_signature","submit_replication":"https://pith.science/pith/N4TDF6BJYS5WNPL64MN6YZ3OW4/action/replication_record"}},"created_at":"2026-05-17T23:53:56.609076+00:00","updated_at":"2026-05-17T23:53:56.609076+00:00"}