{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HXXW72TUWW4ZLDPVBOGF3G6CZO","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":"558293fde2577028fcf71f19039360131069bb11f097aaca0de732d4d740fed5","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-01T19:43:59Z","title_canon_sha256":"b088f2c0b88920bd33465276788fd57392822937d2bdd48167e28359f1ed908b"},"schema_version":"1.0","source":{"id":"2109.00590","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00590","created_at":"2026-07-05T04:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00590v4","created_at":"2026-07-05T04:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00590","created_at":"2026-07-05T04:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"HXXW72TUWW4Z","created_at":"2026-07-05T04:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"HXXW72TUWW4ZLDPV","created_at":"2026-07-05T04:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"HXXW72TU","created_at":"2026-07-05T04:08:58Z"}],"graph_snapshots":[{"event_id":"sha256:4e533fe69c132d60ec0b1051b1c415862f0f1016f2d3547717b5f4935f777cd2","target":"graph","created_at":"2026-07-05T04:08:58Z","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/2109.00590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guihong Cao, Hisami Suzuki, Jianfeng Gao, Mridu Narang, Yingshan Chang, Yonatan Bisk","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-01T19:43:59Z","title":"WebQA: Multihop and Multimodal QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00590","kind":"arxiv","version":4},"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:d575671cff6393464e69216107f348056068ef9106cb0add12b25a8e28176ceb","target":"record","created_at":"2026-07-05T04:08:58Z","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":"558293fde2577028fcf71f19039360131069bb11f097aaca0de732d4d740fed5","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-01T19:43:59Z","title_canon_sha256":"b088f2c0b88920bd33465276788fd57392822937d2bdd48167e28359f1ed908b"},"schema_version":"1.0","source":{"id":"2109.00590","kind":"arxiv","version":4}},"canonical_sha256":"3def6fea74b5b9958df50b8c5d9bc2cb8ff8cd6dee05ce4a9e599c2183e7921c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3def6fea74b5b9958df50b8c5d9bc2cb8ff8cd6dee05ce4a9e599c2183e7921c","first_computed_at":"2026-07-05T04:08:58.498175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:58.498175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R8fKc2gyGAMcQDXLFBSsS0uFP845ZGaVhpTkJrjMn4vrR/RTMFEoH9+dMbMuYu4AAiAhuHkez9izWImOWF4tAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:58.498648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.00590","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d575671cff6393464e69216107f348056068ef9106cb0add12b25a8e28176ceb","sha256:4e533fe69c132d60ec0b1051b1c415862f0f1016f2d3547717b5f4935f777cd2"],"state_sha256":"02c5b24be03e6e9967af8abf6b9214dbafad984c6de1893b70ac8c5fe548a611"}