{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z5Y5RYKJS5O3BXQKKWBXRRSHBX","short_pith_number":"pith:Z5Y5RYKJ","schema_version":"1.0","canonical_sha256":"cf71d8e149975db0de0a558378c6470df815cb9f819f111f2beac56f2d14b376","source":{"kind":"arxiv","id":"2203.09138","version":1},"attestation_state":"computed","paper":{"title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bang Liu, Jing Yu, Mingxin Cui, Qi Wu, Yang Ding, Yue Hu","submitted_at":"2022-03-17T07:42:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.09138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T07:42:14Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"976c7f8397f7f5c718237a54e478a04adcd78da6ed46e1bf9e16e1102471f916","abstract_canon_sha256":"2767ea2d5dc1c2752c6efa772deb73e4d3e2881c1f5b658ecbfcad45eec3526b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:07.932432Z","signature_b64":"CCg5pvsx4copNK8z+HvcloeOJzZYJSx14x7/goh6IOuNJLsDB693nS5HxpeHgtxAU8F/4YF0p4iVQmSVCb14BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf71d8e149975db0de0a558378c6470df815cb9f819f111f2beac56f2d14b376","last_reissued_at":"2026-07-05T04:06:07.931973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:07.931973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bang Liu, Jing Yu, Mingxin Cui, Qi Wu, Yang Ding, Yue Hu","submitted_at":"2022-03-17T07:42:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09138","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/2203.09138/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.09138","created_at":"2026-07-05T04:06:07.932031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09138v1","created_at":"2026-07-05T04:06:07.932031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09138","created_at":"2026-07-05T04:06:07.932031+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5Y5RYKJS5O3","created_at":"2026-07-05T04:06:07.932031+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5Y5RYKJS5O3BXQK","created_at":"2026-07-05T04:06:07.932031+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5Y5RYKJ","created_at":"2026-07-05T04:06:07.932031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX","json":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX.json","graph_json":"https://pith.science/api/pith-number/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/graph.json","events_json":"https://pith.science/api/pith-number/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/events.json","paper":"https://pith.science/paper/Z5Y5RYKJ"},"agent_actions":{"view_html":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX","download_json":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX.json","view_paper":"https://pith.science/paper/Z5Y5RYKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09138&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/action/storage_attestation","attest_author":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/action/author_attestation","sign_citation":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/action/citation_signature","submit_replication":"https://pith.science/pith/Z5Y5RYKJS5O3BXQKKWBXRRSHBX/action/replication_record"}},"created_at":"2026-07-05T04:06:07.932031+00:00","updated_at":"2026-07-05T04:06:07.932031+00:00"}