{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TY3H2JINGPDQSUJRXRDY5G4W4P","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":"6c7ef862a97f0e8d26b8ceb7917fb8cc42e87cc5a039503c12e4f86bcfdd8a5f","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-22T13:21:58Z","title_canon_sha256":"ae7c370645a8fc546e5713c80cbc395f217ee27f1ae852b2531d668ab12453fd"},"schema_version":"1.0","source":{"id":"2108.09717","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09717","created_at":"2026-07-05T04:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09717v8","created_at":"2026-07-05T04:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09717","created_at":"2026-07-05T04:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"TY3H2JINGPDQ","created_at":"2026-07-05T04:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"TY3H2JINGPDQSUJR","created_at":"2026-07-05T04:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"TY3H2JIN","created_at":"2026-07-05T04:40:23Z"}],"graph_snapshots":[{"event_id":"sha256:be4de95c46c47506202e19e0391401b7c185e9cef132c6125d527374d5f217eb","target":"graph","created_at":"2026-07-05T04:40:23Z","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/2108.09717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The open-ended question answering task of Text-VQA often requires reading and reasoning about rarely seen or completely unseen scene-text content of an image. We address this zero-shot nature of the problem by proposing the generalized use of external knowledge to augment our understanding of the scene text. We design a framework to extract, validate, and reason with knowledge using a standard multimodal transformer for vision language understanding tasks. Through empirical evidence and qualitative results, we demonstrate how external knowledge can highlight instance-only cues and thus help de","authors_text":"Arka Ujjal Dey, Ernest Valveny, Gaurav Harit","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-22T13:21:58Z","title":"EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09717","kind":"arxiv","version":8},"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:db4d9292f03dfe0cde9f0c0e2f954b9b5aac19d34368ec47dffedef49be3dde4","target":"record","created_at":"2026-07-05T04:40:23Z","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":"6c7ef862a97f0e8d26b8ceb7917fb8cc42e87cc5a039503c12e4f86bcfdd8a5f","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-22T13:21:58Z","title_canon_sha256":"ae7c370645a8fc546e5713c80cbc395f217ee27f1ae852b2531d668ab12453fd"},"schema_version":"1.0","source":{"id":"2108.09717","kind":"arxiv","version":8}},"canonical_sha256":"9e367d250d33c7095131bc478e9b96e3fb1d570803011d911951386335a1b029","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e367d250d33c7095131bc478e9b96e3fb1d570803011d911951386335a1b029","first_computed_at":"2026-07-05T04:40:23.682699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:23.682699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h3R0xSome6WFxRMAoFUkQCKm4d8bnnUXsXtHYRDjieZHKNQaC6FVjI0IXqj8w2kLAc+OxL45kJVrpXi3IFSSBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:23.683177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.09717","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db4d9292f03dfe0cde9f0c0e2f954b9b5aac19d34368ec47dffedef49be3dde4","sha256:be4de95c46c47506202e19e0391401b7c185e9cef132c6125d527374d5f217eb"],"state_sha256":"524a348cb22b88fb976f317f1f5e8b8a60b03cc743c69f6499cdac081503c4f6"}