{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XODZ7P7IRMQWQ3JVNHV7IJHBLJ","short_pith_number":"pith:XODZ7P7I","schema_version":"1.0","canonical_sha256":"bb879fbfe88b21686d3569ebf424e15a7d27b5780b0c0b2dae1e3471b3f9bcca","source":{"kind":"arxiv","id":"2601.11632","version":3},"attestation_state":"computed","paper":{"title":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"KG-ViP fuses scene graphs and commonsense graphs via a query-guided pipeline to reduce hallucination and sharpen visual detail in multi-modal LLMs for VQA.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Ke, Xike Xie, Yukun Cao, Zhiyang Li","submitted_at":"2026-01-14T07:16:11Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and scene graphs provide precisely complementary solutions to these respective deficiencies by providing rich external knowledge and capturing fine-grained visual details. However, prior works typically treat them in isolation, overlooking their synergistic potential. To bridge this gap, we propose KG-ViP, a unified framework that empowers MLLMs by fusing scene gr"},"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":true},"canonical_record":{"source":{"id":"2601.11632","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-14T07:16:11Z","cross_cats_sorted":[],"title_canon_sha256":"6c0aac27e602569de5afe28f9c1c2d34e60daf8752b60ceefc4c9f5a892df5bf","abstract_canon_sha256":"5caf495aa892e5cb638cee688588e87e82cc12b1ed3537d4c9fcd6c3da1ef5a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:35.438163Z","signature_b64":"2WxLK18f66KuR6Msgy+PRNJ/OA8kSWOLFSWRy3uX0HVGXmvzETIzi/unWTWbzqjFTTYkr0GZ+w8IRe/cV1rKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb879fbfe88b21686d3569ebf424e15a7d27b5780b0c0b2dae1e3471b3f9bcca","last_reissued_at":"2026-05-28T01:04:35.437739Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:35.437739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"KG-ViP fuses scene graphs and commonsense graphs via a query-guided pipeline to reduce hallucination and sharpen visual detail in multi-modal LLMs for VQA.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Ke, Xike Xie, Yukun Cao, Zhiyang Li","submitted_at":"2026-01-14T07:16:11Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and scene graphs provide precisely complementary solutions to these respective deficiencies by providing rich external knowledge and capturing fine-grained visual details. However, prior works typically treat them in isolation, overlooking their synergistic potential. To bridge this gap, we propose KG-ViP, a unified framework that empowers MLLMs by fusing scene gr"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments on FVQA 2.0+ and MVQA benchmarks demonstrate that KG-ViP significantly outperforms existing VQA methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the novel retrieval-and-fusion pipeline, using the query as a semantic bridge to integrate scene graphs and commonsense graphs, will produce reliable multi-modal reasoning without introducing new errors or irrelevant information.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"KG-ViP fuses scene graphs and commonsense graphs via a query-based retrieval-and-fusion pipeline to improve multi-modal LLM performance on visual question answering.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"KG-ViP fuses scene graphs and commonsense graphs via a query-guided pipeline to reduce hallucination and sharpen visual detail in multi-modal LLMs for VQA.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"90f20d79f02a239876b934b71b739ea58f19d117efb3e3de3b816baa269b1a95"},"source":{"id":"2601.11632","kind":"arxiv","version":3},"verdict":{"id":"6e874506-69f0-41b5-945c-642fe7bb6940","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T14:45:02.696687Z","strongest_claim":"Extensive experiments on FVQA 2.0+ and MVQA benchmarks demonstrate that KG-ViP significantly outperforms existing VQA methods.","one_line_summary":"KG-ViP fuses scene graphs and commonsense graphs via a query-based retrieval-and-fusion pipeline to improve multi-modal LLM performance on visual question answering.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the novel retrieval-and-fusion pipeline, using the query as a semantic bridge to integrate scene graphs and commonsense graphs, will produce reliable multi-modal reasoning without introducing new errors or irrelevant information.","pith_extraction_headline":"KG-ViP fuses scene graphs and commonsense graphs via a query-guided pipeline to reduce hallucination and sharpen visual detail in multi-modal LLMs for VQA."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.11632/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":2,"snapshot_sha256":"936322e059e14cf6511e50dc2decb8b06bc2d2afefb9bc14dda2bebbc3ee83eb"},"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":"2601.11632","created_at":"2026-05-28T01:04:35.437793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.11632v3","created_at":"2026-05-28T01:04:35.437793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11632","created_at":"2026-05-28T01:04:35.437793+00:00"},{"alias_kind":"pith_short_12","alias_value":"XODZ7P7IRMQW","created_at":"2026-05-28T01:04:35.437793+00:00"},{"alias_kind":"pith_short_16","alias_value":"XODZ7P7IRMQWQ3JV","created_at":"2026-05-28T01:04:35.437793+00:00"},{"alias_kind":"pith_short_8","alias_value":"XODZ7P7I","created_at":"2026-05-28T01:04:35.437793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ","json":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ.json","graph_json":"https://pith.science/api/pith-number/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/graph.json","events_json":"https://pith.science/api/pith-number/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/events.json","paper":"https://pith.science/paper/XODZ7P7I"},"agent_actions":{"view_html":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ","download_json":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ.json","view_paper":"https://pith.science/paper/XODZ7P7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.11632&json=true","fetch_graph":"https://pith.science/api/pith-number/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/action/storage_attestation","attest_author":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/action/author_attestation","sign_citation":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/action/citation_signature","submit_replication":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/action/replication_record"}},"created_at":"2026-05-28T01:04:35.437793+00:00","updated_at":"2026-05-28T01:04:35.437793+00:00"}