{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HC4RWVEAFDI2VNIFBPIIIT7574","short_pith_number":"pith:HC4RWVEA","schema_version":"1.0","canonical_sha256":"38b91b548028d1aab5050bd0844ffdff0fef417a96ff960a449049bbe3429b4d","source":{"kind":"arxiv","id":"2311.00807","version":1},"attestation_state":"computed","paper":{"title":"VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Huan Liu, Raha Moraffah, Suraj Jyothi Unni","submitted_at":"2023-11-01T19:43:56Z","abstract_excerpt":"Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization datasets for VQA exhibit a unilateral focus on textual shifts while VQA being a multi-modal task contains shifts across both visual and textual domains. We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. Experiments demonstrate VQA-GEN dataset exposes the vulnerability of existing m"},"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":"2311.00807","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T19:43:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"648f78389ef93a68ab8311b66ea163fa1f31eaf8c01fc47d2789c1856d38a624","abstract_canon_sha256":"3e4fbee32904acc08e2563e4bd2c7a9b768bc94af7ef7b1c22e10f20977b01d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:15.838665Z","signature_b64":"JoBJGSRf2jYdKS44HRtpxUSpz7/1z/o/dYo82CdwObydtPPzCZTicffoIK7rQMBHnIhILrkKftxVwvo+gb1hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b91b548028d1aab5050bd0844ffdff0fef417a96ff960a449049bbe3429b4d","last_reissued_at":"2026-07-05T07:08:15.838255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:15.838255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Huan Liu, Raha Moraffah, Suraj Jyothi Unni","submitted_at":"2023-11-01T19:43:56Z","abstract_excerpt":"Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization datasets for VQA exhibit a unilateral focus on textual shifts while VQA being a multi-modal task contains shifts across both visual and textual domains. We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. Experiments demonstrate VQA-GEN dataset exposes the vulnerability of existing m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00807","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/2311.00807/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.00807","created_at":"2026-07-05T07:08:15.838322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00807v1","created_at":"2026-07-05T07:08:15.838322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00807","created_at":"2026-07-05T07:08:15.838322+00:00"},{"alias_kind":"pith_short_12","alias_value":"HC4RWVEAFDI2","created_at":"2026-07-05T07:08:15.838322+00:00"},{"alias_kind":"pith_short_16","alias_value":"HC4RWVEAFDI2VNIF","created_at":"2026-07-05T07:08:15.838322+00:00"},{"alias_kind":"pith_short_8","alias_value":"HC4RWVEA","created_at":"2026-07-05T07:08:15.838322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21755","citing_title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574","json":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574.json","graph_json":"https://pith.science/api/pith-number/HC4RWVEAFDI2VNIFBPIIIT7574/graph.json","events_json":"https://pith.science/api/pith-number/HC4RWVEAFDI2VNIFBPIIIT7574/events.json","paper":"https://pith.science/paper/HC4RWVEA"},"agent_actions":{"view_html":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574","download_json":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574.json","view_paper":"https://pith.science/paper/HC4RWVEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00807&json=true","fetch_graph":"https://pith.science/api/pith-number/HC4RWVEAFDI2VNIFBPIIIT7574/graph.json","fetch_events":"https://pith.science/api/pith-number/HC4RWVEAFDI2VNIFBPIIIT7574/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/action/storage_attestation","attest_author":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/action/author_attestation","sign_citation":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/action/citation_signature","submit_replication":"https://pith.science/pith/HC4RWVEAFDI2VNIFBPIIIT7574/action/replication_record"}},"created_at":"2026-07-05T07:08:15.838322+00:00","updated_at":"2026-07-05T07:08:15.838322+00:00"}