{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:76MSVRKDZQ4YZOBMVZEIPHLRRI","short_pith_number":"pith:76MSVRKD","schema_version":"1.0","canonical_sha256":"ff992ac543cc398cb82cae48879d718a27b2cedc739b560ea0f85b3442730dd6","source":{"kind":"arxiv","id":"2406.18839","version":1},"attestation_state":"computed","paper":{"title":"Disentangling Knowledge-based and Visual Reasoning by Question Decomposition in KB-VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Elham J. Barezi, Parisa Kordjamshidi","submitted_at":"2024-06-27T02:19:38Z","abstract_excerpt":"We study the Knowledge-Based visual question-answering problem, for which given a question, the models need to ground it into the visual modality to find the answer. Although many recent works use question-dependent captioners to verbalize the given image and use Large Language Models to solve the VQA problem, the research results show they are not reasonably performing for multi-hop questions. Our study shows that replacing a complex question with several simpler questions helps to extract more relevant information from the image and provide a stronger comprehension of it. Moreover, we analyz"},"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":"2406.18839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-27T02:19:38Z","cross_cats_sorted":[],"title_canon_sha256":"3509f9ba1f2a9c58a58d5a3bc9ad463689879e7cfab902609c6d84221b079526","abstract_canon_sha256":"806ce718883c2da752902dbc9b385d9e67831edd94a5b0152d50a30fe748339d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:26.428926Z","signature_b64":"d8sAKQFaN6bHrylOXgxeCvVU1jFcftL+pLu5Q3GWsSsT8DrOBP3KRtv/LtmqI2MGpa2tb5gd//rqvYmgRmmpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff992ac543cc398cb82cae48879d718a27b2cedc739b560ea0f85b3442730dd6","last_reissued_at":"2026-07-05T08:37:26.428498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:26.428498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Knowledge-based and Visual Reasoning by Question Decomposition in KB-VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Elham J. Barezi, Parisa Kordjamshidi","submitted_at":"2024-06-27T02:19:38Z","abstract_excerpt":"We study the Knowledge-Based visual question-answering problem, for which given a question, the models need to ground it into the visual modality to find the answer. Although many recent works use question-dependent captioners to verbalize the given image and use Large Language Models to solve the VQA problem, the research results show they are not reasonably performing for multi-hop questions. Our study shows that replacing a complex question with several simpler questions helps to extract more relevant information from the image and provide a stronger comprehension of it. Moreover, we analyz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18839","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/2406.18839/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":"2406.18839","created_at":"2026-07-05T08:37:26.428562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18839v1","created_at":"2026-07-05T08:37:26.428562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18839","created_at":"2026-07-05T08:37:26.428562+00:00"},{"alias_kind":"pith_short_12","alias_value":"76MSVRKDZQ4Y","created_at":"2026-07-05T08:37:26.428562+00:00"},{"alias_kind":"pith_short_16","alias_value":"76MSVRKDZQ4YZOBM","created_at":"2026-07-05T08:37:26.428562+00:00"},{"alias_kind":"pith_short_8","alias_value":"76MSVRKD","created_at":"2026-07-05T08:37:26.428562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16420","citing_title":"Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI","json":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI.json","graph_json":"https://pith.science/api/pith-number/76MSVRKDZQ4YZOBMVZEIPHLRRI/graph.json","events_json":"https://pith.science/api/pith-number/76MSVRKDZQ4YZOBMVZEIPHLRRI/events.json","paper":"https://pith.science/paper/76MSVRKD"},"agent_actions":{"view_html":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI","download_json":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI.json","view_paper":"https://pith.science/paper/76MSVRKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18839&json=true","fetch_graph":"https://pith.science/api/pith-number/76MSVRKDZQ4YZOBMVZEIPHLRRI/graph.json","fetch_events":"https://pith.science/api/pith-number/76MSVRKDZQ4YZOBMVZEIPHLRRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI/action/storage_attestation","attest_author":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI/action/author_attestation","sign_citation":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI/action/citation_signature","submit_replication":"https://pith.science/pith/76MSVRKDZQ4YZOBMVZEIPHLRRI/action/replication_record"}},"created_at":"2026-07-05T08:37:26.428562+00:00","updated_at":"2026-07-05T08:37:26.428562+00:00"}