{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HXXW72TUWW4ZLDPVBOGF3G6CZO","short_pith_number":"pith:HXXW72TU","schema_version":"1.0","canonical_sha256":"3def6fea74b5b9958df50b8c5d9bc2cb8ff8cd6dee05ce4a9e599c2183e7921c","source":{"kind":"arxiv","id":"2109.00590","version":4},"attestation_state":"computed","paper":{"title":"WebQA: Multihop and Multimodal QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guihong Cao, Hisami Suzuki, Jianfeng Gao, Mridu Narang, Yingshan Chang, Yonatan Bisk","submitted_at":"2021-09-01T19:43:59Z","abstract_excerpt":"Scaling Visual Question Answering (VQA) to the open-domain and multi-hop nature of web searches, requires fundamental advances in visual representation learning, knowledge aggregation, and language generation. In this work, we introduce WebQA, a challenging new benchmark that proves difficult for large-scale state-of-the-art models which lack language groundable visual representations for novel objects and the ability to reason, yet trivial for humans. WebQA mirrors the way humans use the web: 1) Ask a question, 2) Choose sources to aggregate, and 3) Produce a fluent language response. This is"},"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":"2109.00590","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-01T19:43:59Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"b088f2c0b88920bd33465276788fd57392822937d2bdd48167e28359f1ed908b","abstract_canon_sha256":"558293fde2577028fcf71f19039360131069bb11f097aaca0de732d4d740fed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:58.498648Z","signature_b64":"R8fKc2gyGAMcQDXLFBSsS0uFP845ZGaVhpTkJrjMn4vrR/RTMFEoH9+dMbMuYu4AAiAhuHkez9izWImOWF4tAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3def6fea74b5b9958df50b8c5d9bc2cb8ff8cd6dee05ce4a9e599c2183e7921c","last_reissued_at":"2026-07-05T04:08:58.498175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:58.498175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebQA: Multihop and Multimodal QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guihong Cao, Hisami Suzuki, Jianfeng Gao, Mridu Narang, Yingshan Chang, Yonatan Bisk","submitted_at":"2021-09-01T19:43:59Z","abstract_excerpt":"Scaling Visual Question Answering (VQA) to the open-domain and multi-hop nature of web searches, requires fundamental advances in visual representation learning, knowledge aggregation, and language generation. In this work, we introduce WebQA, a challenging new benchmark that proves difficult for large-scale state-of-the-art models which lack language groundable visual representations for novel objects and the ability to reason, yet trivial for humans. WebQA mirrors the way humans use the web: 1) Ask a question, 2) Choose sources to aggregate, and 3) Produce a fluent language response. This is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00590","kind":"arxiv","version":4},"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/2109.00590/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":"2109.00590","created_at":"2026-07-05T04:08:58.498234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.00590v4","created_at":"2026-07-05T04:08:58.498234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00590","created_at":"2026-07-05T04:08:58.498234+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXXW72TUWW4Z","created_at":"2026-07-05T04:08:58.498234+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXXW72TUWW4ZLDPV","created_at":"2026-07-05T04:08:58.498234+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXXW72TU","created_at":"2026-07-05T04:08:58.498234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2408.03326","citing_title":"LLaVA-OneVision: Easy Visual Task Transfer","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO","json":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO.json","graph_json":"https://pith.science/api/pith-number/HXXW72TUWW4ZLDPVBOGF3G6CZO/graph.json","events_json":"https://pith.science/api/pith-number/HXXW72TUWW4ZLDPVBOGF3G6CZO/events.json","paper":"https://pith.science/paper/HXXW72TU"},"agent_actions":{"view_html":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO","download_json":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO.json","view_paper":"https://pith.science/paper/HXXW72TU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.00590&json=true","fetch_graph":"https://pith.science/api/pith-number/HXXW72TUWW4ZLDPVBOGF3G6CZO/graph.json","fetch_events":"https://pith.science/api/pith-number/HXXW72TUWW4ZLDPVBOGF3G6CZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO/action/storage_attestation","attest_author":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO/action/author_attestation","sign_citation":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO/action/citation_signature","submit_replication":"https://pith.science/pith/HXXW72TUWW4ZLDPVBOGF3G6CZO/action/replication_record"}},"created_at":"2026-07-05T04:08:58.498234+00:00","updated_at":"2026-07-05T04:08:58.498234+00:00"}