{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z5Y5RYKJS5O3BXQKKWBXRRSHBX","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":"2767ea2d5dc1c2752c6efa772deb73e4d3e2881c1f5b658ecbfcad45eec3526b","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T07:42:14Z","title_canon_sha256":"976c7f8397f7f5c718237a54e478a04adcd78da6ed46e1bf9e16e1102471f916"},"schema_version":"1.0","source":{"id":"2203.09138","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09138","created_at":"2026-07-05T04:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09138v1","created_at":"2026-07-05T04:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09138","created_at":"2026-07-05T04:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"Z5Y5RYKJS5O3","created_at":"2026-07-05T04:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"Z5Y5RYKJS5O3BXQK","created_at":"2026-07-05T04:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"Z5Y5RYKJ","created_at":"2026-07-05T04:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:c3f027e65e61b2b93ca6ad66e0bde83ac651a5b21fc073f1992bb7ce9457ce49","target":"graph","created_at":"2026-07-05T04:06:07Z","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/2203.09138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only knowledge bases, which merely contain facts expressed by first-order predicates or language descriptions while lacking complex but indispensable multimodal knowledge for visual understanding. How to construct vision-relevant and explainable multimodal knowledge for the VQA scenario has been less studied. In this paper, we propose MuKEA to represent multimodal k","authors_text":"Bang Liu, Jing Yu, Mingxin Cui, Qi Wu, Yang Ding, Yue Hu","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T07:42:14Z","title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09138","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:f561b1f7ca4185aedb4d21edceee0da0dc77eecbc12df2d798ea8bdaadfc64ab","target":"record","created_at":"2026-07-05T04:06:07Z","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":"2767ea2d5dc1c2752c6efa772deb73e4d3e2881c1f5b658ecbfcad45eec3526b","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T07:42:14Z","title_canon_sha256":"976c7f8397f7f5c718237a54e478a04adcd78da6ed46e1bf9e16e1102471f916"},"schema_version":"1.0","source":{"id":"2203.09138","kind":"arxiv","version":1}},"canonical_sha256":"cf71d8e149975db0de0a558378c6470df815cb9f819f111f2beac56f2d14b376","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf71d8e149975db0de0a558378c6470df815cb9f819f111f2beac56f2d14b376","first_computed_at":"2026-07-05T04:06:07.931973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:07.931973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CCg5pvsx4copNK8z+HvcloeOJzZYJSx14x7/goh6IOuNJLsDB693nS5HxpeHgtxAU8F/4YF0p4iVQmSVCb14BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:07.932432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.09138","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f561b1f7ca4185aedb4d21edceee0da0dc77eecbc12df2d798ea8bdaadfc64ab","sha256:c3f027e65e61b2b93ca6ad66e0bde83ac651a5b21fc073f1992bb7ce9457ce49"],"state_sha256":"0ea292cb7f71fe6e29f71492ecdb7099c7f705191e67576c7096e0fb135f6fc4"}