{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FUZ6LYQME7YIJJR4ASFV6YSUSU","short_pith_number":"pith:FUZ6LYQM","canonical_record":{"source":{"id":"2201.05299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-14T04:12:46Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ab84d9446afd803de7da1f89953069e1648c9d50f23de28b06adc6761000d0fa","abstract_canon_sha256":"c6bd045941ab02fa1ac07c3e6696d7afffb171e3417c3995623706f6ffe4c680"},"schema_version":"1.0"},"canonical_sha256":"2d33e5e20c27f084a63c048b5f62549524784eb8690f54c6b99694cfd487ecf2","source":{"kind":"arxiv","id":"2201.05299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05299","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05299v1","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05299","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"FUZ6LYQME7YI","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"FUZ6LYQME7YIJJR4","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"FUZ6LYQM","created_at":"2026-07-05T03:48:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FUZ6LYQME7YIJJR4ASFV6YSUSU","target":"record","payload":{"canonical_record":{"source":{"id":"2201.05299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-14T04:12:46Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ab84d9446afd803de7da1f89953069e1648c9d50f23de28b06adc6761000d0fa","abstract_canon_sha256":"c6bd045941ab02fa1ac07c3e6696d7afffb171e3417c3995623706f6ffe4c680"},"schema_version":"1.0"},"canonical_sha256":"2d33e5e20c27f084a63c048b5f62549524784eb8690f54c6b99694cfd487ecf2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:22.036861Z","signature_b64":"xSesckRfjRQCCArHxc4t1Qjda28y/e8muhyZFJr/RG9+VtPLt+sO9P06sLxKRzGArnfQsdCBqT6hLVYatDdZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d33e5e20c27f084a63c048b5f62549524784eb8690f54c6b99694cfd487ecf2","last_reissued_at":"2026-07-05T03:48:22.036519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:22.036519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.05299","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYBAgp6+JX0h9Rb8fiTD4W3NMRGoPZlVaY0ZGL9i9BtHr2gaWpOPqo6IC2ScyV9TBpNyBkxIksYtmBhHJE8QDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:10:15.928677Z"},"content_sha256":"3ea011d380560b3a8d0136dddf74ccd5a9e4e83938723d0f6e52c4a93a6d634e","schema_version":"1.0","event_id":"sha256:3ea011d380560b3a8d0136dddf74ccd5a9e4e83938723d0f6e52c4a93a6d634e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FUZ6LYQME7YIJJR4ASFV6YSUSU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Aishwarya Reganti, Feng Gao, Govind Thattai, Prem Natarajan, Qing Ping, Ying Nian Wu","submitted_at":"2022-01-14T04:12:46Z","abstract_excerpt":"Outside-knowledge visual question answering (OK-VQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information to answer the question. Most previous works address the problem by first fusing the image and question in the multi-modal space, which is inflexible for further fusion with a vast amount of external knowledge. In this paper, we call for a paradigm shift for the OK-VQA task, which transforms the image into plain text, so that we can enable knowledge passage retrieval, and generative question-answering in the natural l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05299","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/2201.05299/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P9FlO1Ms7vOIGvzvumoX059ALytDcsy6l2oGePe0xvUc9H5PauEexVIKiEJmNnB0WGXId1FlrT0UVCZCMPjcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:10:15.929184Z"},"content_sha256":"46378689481a3ee9e4b70a5e0f42414c34e089a3a20665d0343a0ac68f47ea8d","schema_version":"1.0","event_id":"sha256:46378689481a3ee9e4b70a5e0f42414c34e089a3a20665d0343a0ac68f47ea8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FUZ6LYQME7YIJJR4ASFV6YSUSU/bundle.json","state_url":"https://pith.science/pith/FUZ6LYQME7YIJJR4ASFV6YSUSU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FUZ6LYQME7YIJJR4ASFV6YSUSU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T07:10:15Z","links":{"resolver":"https://pith.science/pith/FUZ6LYQME7YIJJR4ASFV6YSUSU","bundle":"https://pith.science/pith/FUZ6LYQME7YIJJR4ASFV6YSUSU/bundle.json","state":"https://pith.science/pith/FUZ6LYQME7YIJJR4ASFV6YSUSU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FUZ6LYQME7YIJJR4ASFV6YSUSU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FUZ6LYQME7YIJJR4ASFV6YSUSU","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":"c6bd045941ab02fa1ac07c3e6696d7afffb171e3417c3995623706f6ffe4c680","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-14T04:12:46Z","title_canon_sha256":"ab84d9446afd803de7da1f89953069e1648c9d50f23de28b06adc6761000d0fa"},"schema_version":"1.0","source":{"id":"2201.05299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05299","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05299v1","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05299","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"FUZ6LYQME7YI","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"FUZ6LYQME7YIJJR4","created_at":"2026-07-05T03:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"FUZ6LYQM","created_at":"2026-07-05T03:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:46378689481a3ee9e4b70a5e0f42414c34e089a3a20665d0343a0ac68f47ea8d","target":"graph","created_at":"2026-07-05T03:48:22Z","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/2201.05299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Outside-knowledge visual question answering (OK-VQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information to answer the question. Most previous works address the problem by first fusing the image and question in the multi-modal space, which is inflexible for further fusion with a vast amount of external knowledge. In this paper, we call for a paradigm shift for the OK-VQA task, which transforms the image into plain text, so that we can enable knowledge passage retrieval, and generative question-answering in the natural l","authors_text":"Aishwarya Reganti, Feng Gao, Govind Thattai, Prem Natarajan, Qing Ping, Ying Nian Wu","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-14T04:12:46Z","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05299","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":"sha256:3ea011d380560b3a8d0136dddf74ccd5a9e4e83938723d0f6e52c4a93a6d634e","target":"record","created_at":"2026-07-05T03:48:22Z","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":"c6bd045941ab02fa1ac07c3e6696d7afffb171e3417c3995623706f6ffe4c680","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-14T04:12:46Z","title_canon_sha256":"ab84d9446afd803de7da1f89953069e1648c9d50f23de28b06adc6761000d0fa"},"schema_version":"1.0","source":{"id":"2201.05299","kind":"arxiv","version":1}},"canonical_sha256":"2d33e5e20c27f084a63c048b5f62549524784eb8690f54c6b99694cfd487ecf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d33e5e20c27f084a63c048b5f62549524784eb8690f54c6b99694cfd487ecf2","first_computed_at":"2026-07-05T03:48:22.036519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:22.036519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xSesckRfjRQCCArHxc4t1Qjda28y/e8muhyZFJr/RG9+VtPLt+sO9P06sLxKRzGArnfQsdCBqT6hLVYatDdZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:22.036861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ea011d380560b3a8d0136dddf74ccd5a9e4e83938723d0f6e52c4a93a6d634e","sha256:46378689481a3ee9e4b70a5e0f42414c34e089a3a20665d0343a0ac68f47ea8d"],"state_sha256":"abce9c1b8287c53f38c956ed8d74e28b07b17ea3c3cbceaa2e78852fefcb21b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vA4LHWi9gb75Pglg/8pX8OHF5Ra2TGwZv3SMp4o+e6X+PP74Tx7ukr5/6yKOZYf+MzquUKjvc6qWxYLmvQFFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:10:15.932489Z","bundle_sha256":"843e996e953f6722d8b1be56c7d95cfb64cffc1524dd80e344bf6e622ed54d31"}}