{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IT6D2AZGUW3MWXUM4FF5USTU33","short_pith_number":"pith:IT6D2AZG","schema_version":"1.0","canonical_sha256":"44fc3d0326a5b6cb5e8ce14bda4a74dec26d95ee2c4f44d73b6087926e7cc649","source":{"kind":"arxiv","id":"2204.10448","version":1},"attestation_state":"computed","paper":{"title":"Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Eun-Sol Kim, Woo Suk Choi, Yu-Jung Heo","submitted_at":"2022-04-22T00:49:50Z","abstract_excerpt":"Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is considered as a challenging problem since i) no supervision is given to the reasoning process and ii) high-order semantics of multi-hop knowledge facts need to be captured. In this paper, we introduce a concept of hypergraph to encode high-level semantics of a question and a knowledge base, and to learn high-order associations between them. The proposed mod"},"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":"2204.10448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-22T00:49:50Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"f01186406713cc8e14c226b484e9bf46cc4a49b7f4919192a92ca4b94212c481","abstract_canon_sha256":"b7272f8cf23ed28e2e13b8e4e99a29fbf28a3d30e431412ac8b8b1fe168a4cb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:57.000993Z","signature_b64":"T7Tc7oazFdlay0kCXnG0c2zODQBlBiAY2kWdLwBk1HOoIhKgWHR7MdHeaoMv88xGh8+MgQasjddKWBIm8ihSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44fc3d0326a5b6cb5e8ce14bda4a74dec26d95ee2c4f44d73b6087926e7cc649","last_reissued_at":"2026-07-05T04:16:57.000506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:57.000506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Eun-Sol Kim, Woo Suk Choi, Yu-Jung Heo","submitted_at":"2022-04-22T00:49:50Z","abstract_excerpt":"Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is considered as a challenging problem since i) no supervision is given to the reasoning process and ii) high-order semantics of multi-hop knowledge facts need to be captured. In this paper, we introduce a concept of hypergraph to encode high-level semantics of a question and a knowledge base, and to learn high-order associations between them. The proposed mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10448","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/2204.10448/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":"2204.10448","created_at":"2026-07-05T04:16:57.000568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10448v1","created_at":"2026-07-05T04:16:57.000568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10448","created_at":"2026-07-05T04:16:57.000568+00:00"},{"alias_kind":"pith_short_12","alias_value":"IT6D2AZGUW3M","created_at":"2026-07-05T04:16:57.000568+00:00"},{"alias_kind":"pith_short_16","alias_value":"IT6D2AZGUW3MWXUM","created_at":"2026-07-05T04:16:57.000568+00:00"},{"alias_kind":"pith_short_8","alias_value":"IT6D2AZG","created_at":"2026-07-05T04:16:57.000568+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/IT6D2AZGUW3MWXUM4FF5USTU33","json":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33.json","graph_json":"https://pith.science/api/pith-number/IT6D2AZGUW3MWXUM4FF5USTU33/graph.json","events_json":"https://pith.science/api/pith-number/IT6D2AZGUW3MWXUM4FF5USTU33/events.json","paper":"https://pith.science/paper/IT6D2AZG"},"agent_actions":{"view_html":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33","download_json":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33.json","view_paper":"https://pith.science/paper/IT6D2AZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10448&json=true","fetch_graph":"https://pith.science/api/pith-number/IT6D2AZGUW3MWXUM4FF5USTU33/graph.json","fetch_events":"https://pith.science/api/pith-number/IT6D2AZGUW3MWXUM4FF5USTU33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33/action/storage_attestation","attest_author":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33/action/author_attestation","sign_citation":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33/action/citation_signature","submit_replication":"https://pith.science/pith/IT6D2AZGUW3MWXUM4FF5USTU33/action/replication_record"}},"created_at":"2026-07-05T04:16:57.000568+00:00","updated_at":"2026-07-05T04:16:57.000568+00:00"}