{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P7G4YW2IGVBJFHLOMQGNUY67KW","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":"7b813b089d41ec389794a2674cc5b5605c58ebbf4170e44a8b18861fe9db93c8","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:45:42Z","title_canon_sha256":"57eb44842842e237654512e50190e105b98550c30c1b8c78feecf9a8f8b0656b"},"schema_version":"1.0","source":{"id":"2112.06888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06888","created_at":"2026-07-05T04:26:46Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06888v1","created_at":"2026-07-05T04:26:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06888","created_at":"2026-07-05T04:26:46Z"},{"alias_kind":"pith_short_12","alias_value":"P7G4YW2IGVBJ","created_at":"2026-07-05T04:26:46Z"},{"alias_kind":"pith_short_16","alias_value":"P7G4YW2IGVBJFHLO","created_at":"2026-07-05T04:26:46Z"},{"alias_kind":"pith_short_8","alias_value":"P7G4YW2I","created_at":"2026-07-05T04:26:46Z"}],"graph_snapshots":[{"event_id":"sha256:c8d86756aacf6d54657f78b5af08a0edb4f6101e83eb4e97c6c027041d9a8745","target":"graph","created_at":"2026-07-05T04:26:46Z","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/2112.06888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-Based Visual Question Answering (KBVQA) is a bi-modal task requiring external world knowledge in order to correctly answer a text question and associated image. Recent single modality text work has shown knowledge injection into pre-trained language models, specifically entity enhanced knowledge graph embeddings, can improve performance on downstream entity-centric tasks. In this work, we empirically study how and whether such methods, applied in a bi-modal setting, can improve an existing VQA system's performance on the KBVQA task. We experiment with two large publicly available VQA","authors_text":"Diego Garcia-Olano, Joydeep Ghosh, Yasumasa Onoe","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:45:42Z","title":"Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06888","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":"sha256:629b84288995da38b88fbd8f8af827271a7578d4a1a2f90d58ef0b62da6b573b","target":"record","created_at":"2026-07-05T04:26:46Z","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":"7b813b089d41ec389794a2674cc5b5605c58ebbf4170e44a8b18861fe9db93c8","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:45:42Z","title_canon_sha256":"57eb44842842e237654512e50190e105b98550c30c1b8c78feecf9a8f8b0656b"},"schema_version":"1.0","source":{"id":"2112.06888","kind":"arxiv","version":1}},"canonical_sha256":"7fcdcc5b483542929d6e640cda63df55b01b44a082d57e5f95407e90dfee4fbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fcdcc5b483542929d6e640cda63df55b01b44a082d57e5f95407e90dfee4fbb","first_computed_at":"2026-07-05T04:26:46.588384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:46.588384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sAW5eliNXCJKiYUxjSRAYpTU3I1Q9sH6RHwr1e1kehDJ89oEpcGKv8uUQAmiQFYGHMbe9Ewuzwib6VKNQaOlDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:46.588857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:629b84288995da38b88fbd8f8af827271a7578d4a1a2f90d58ef0b62da6b573b","sha256:c8d86756aacf6d54657f78b5af08a0edb4f6101e83eb4e97c6c027041d9a8745"],"state_sha256":"7a014853e1cbdd0a57061ffdd2015952008344507c4d965876a1ec5dffbcb748"}