{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:45SBVC2DYIQELQKP2MDGO272SS","short_pith_number":"pith:45SBVC2D","schema_version":"1.0","canonical_sha256":"e7641a8b43c22045c14fd306676bfa94a16c3178849e5149175354584a4151b6","source":{"kind":"arxiv","id":"2407.15346","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Feng Tian, Guang Dai, Haonan Lin, Jiahao Nie, Ping Chen, Qianying Wang, Wenbin An, WenKai Shi, Yan Chen, Yaqiang Wu","submitted_at":"2024-07-22T03:05:32Z","abstract_excerpt":"Knowledge-based Visual Question Answering (KVQA) requires both image and world knowledge to answer questions. Current methods first retrieve knowledge from the image and external knowledge base with the original complex question, then generate answers with Large Language Models (LLMs). However, since the original question contains complex elements that require knowledge from different sources, acquiring different kinds of knowledge in a coupled manner may confuse models and hinder them from retrieving precise knowledge. Furthermore, the ``forward-only'' answering process fails to explicitly ca"},"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":"2407.15346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T03:05:32Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"3cadcfcac2e6250cd3a1446c980de493b7f1655cbee43a306a8b7f2be5185299","abstract_canon_sha256":"84b91c5fc859fcc1a988f7a3a16c7c389b3abf70b9de03b2d5c15636da27b444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:42.335101Z","signature_b64":"HbdN1LrmQKRnw5KlkumwKf98yghmRP98SKMWlMP+iEkZ6SYPAg7/TeGgConZWp+2j6Z9esyZMeTGaD9fgLtqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7641a8b43c22045c14fd306676bfa94a16c3178849e5149175354584a4151b6","last_reissued_at":"2026-07-05T08:46:42.334567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:42.334567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Feng Tian, Guang Dai, Haonan Lin, Jiahao Nie, Ping Chen, Qianying Wang, Wenbin An, WenKai Shi, Yan Chen, Yaqiang Wu","submitted_at":"2024-07-22T03:05:32Z","abstract_excerpt":"Knowledge-based Visual Question Answering (KVQA) requires both image and world knowledge to answer questions. Current methods first retrieve knowledge from the image and external knowledge base with the original complex question, then generate answers with Large Language Models (LLMs). However, since the original question contains complex elements that require knowledge from different sources, acquiring different kinds of knowledge in a coupled manner may confuse models and hinder them from retrieving precise knowledge. Furthermore, the ``forward-only'' answering process fails to explicitly ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15346","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/2407.15346/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":"2407.15346","created_at":"2026-07-05T08:46:42.334627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15346v1","created_at":"2026-07-05T08:46:42.334627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15346","created_at":"2026-07-05T08:46:42.334627+00:00"},{"alias_kind":"pith_short_12","alias_value":"45SBVC2DYIQE","created_at":"2026-07-05T08:46:42.334627+00:00"},{"alias_kind":"pith_short_16","alias_value":"45SBVC2DYIQELQKP","created_at":"2026-07-05T08:46:42.334627+00:00"},{"alias_kind":"pith_short_8","alias_value":"45SBVC2D","created_at":"2026-07-05T08:46:42.334627+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/45SBVC2DYIQELQKP2MDGO272SS","json":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS.json","graph_json":"https://pith.science/api/pith-number/45SBVC2DYIQELQKP2MDGO272SS/graph.json","events_json":"https://pith.science/api/pith-number/45SBVC2DYIQELQKP2MDGO272SS/events.json","paper":"https://pith.science/paper/45SBVC2D"},"agent_actions":{"view_html":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS","download_json":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS.json","view_paper":"https://pith.science/paper/45SBVC2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15346&json=true","fetch_graph":"https://pith.science/api/pith-number/45SBVC2DYIQELQKP2MDGO272SS/graph.json","fetch_events":"https://pith.science/api/pith-number/45SBVC2DYIQELQKP2MDGO272SS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS/action/storage_attestation","attest_author":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS/action/author_attestation","sign_citation":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS/action/citation_signature","submit_replication":"https://pith.science/pith/45SBVC2DYIQELQKP2MDGO272SS/action/replication_record"}},"created_at":"2026-07-05T08:46:42.334627+00:00","updated_at":"2026-07-05T08:46:42.334627+00:00"}