{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XODZ7P7IRMQWQ3JVNHV7IJHBLJ","short_pith_number":"pith:XODZ7P7I","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"},"canonical_sha256":"bb879fbfe88b21686d3569ebf424e15a7d27b5780b0c0b2dae1e3471b3f9bcca","source":{"kind":"arxiv","id":"2601.11632","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.11632","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2601.11632v3","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11632","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"XODZ7P7IRMQW","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"XODZ7P7IRMQWQ3JV","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"XODZ7P7I","created_at":"2026-05-28T01:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XODZ7P7IRMQWQ3JVNHV7IJHBLJ","target":"record","payload":{"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"},"canonical_sha256":"bb879fbfe88b21686d3569ebf424e15a7d27b5780b0c0b2dae1e3471b3f9bcca","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"},"source_kind":"arxiv","source_id":"2601.11632","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZT06TVhWh6b7CRaMi/1w8AT3Y/Qw2Ag9yacSL0NuO7YRafy+WV8mN492t4irOkRvXfD8Mo2EoGfcDQk4wKLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:22:33.746417Z"},"content_sha256":"d344dd7d404c5a97cacd363ed9d7d30b90c4f8741113163360e0a158fb3657f8","schema_version":"1.0","event_id":"sha256:d344dd7d404c5a97cacd363ed9d7d30b90c4f8741113163360e0a158fb3657f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XODZ7P7IRMQWQ3JVNHV7IJHBLJ","target":"graph","payload":{"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"},"verdict_id":"6e874506-69f0-41b5-945c-642fe7bb6940"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DXuc9x2+SYFaGHqLiju9kU9H4jN3/IWmuNfKUXhAzkhYM10ZMMeuAD3jcbC200HlySdgv8uG4ZYE4sTwJRCaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:22:33.746891Z"},"content_sha256":"6a923c631658283f1eedf65356bc36e8f929af3376d11faf6c516dd4866a83df","schema_version":"1.0","event_id":"sha256:6a923c631658283f1eedf65356bc36e8f929af3376d11faf6c516dd4866a83df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/bundle.json","state_url":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T15:22:33Z","links":{"resolver":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ","bundle":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/bundle.json","state":"https://pith.science/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XODZ7P7IRMQWQ3JVNHV7IJHBLJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XODZ7P7IRMQWQ3JVNHV7IJHBLJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5caf495aa892e5cb638cee688588e87e82cc12b1ed3537d4c9fcd6c3da1ef5a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-14T07:16:11Z","title_canon_sha256":"6c0aac27e602569de5afe28f9c1c2d34e60daf8752b60ceefc4c9f5a892df5bf"},"schema_version":"1.0","source":{"id":"2601.11632","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.11632","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2601.11632v3","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11632","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"XODZ7P7IRMQW","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"XODZ7P7IRMQWQ3JV","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"XODZ7P7I","created_at":"2026-05-28T01:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:6a923c631658283f1eedf65356bc36e8f929af3376d11faf6c516dd4866a83df","target":"graph","created_at":"2026-05-28T01:04:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive experiments on FVQA 2.0+ and MVQA benchmarks demonstrate that KG-ViP significantly outperforms existing VQA methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"90f20d79f02a239876b934b71b739ea58f19d117efb3e3de3b816baa269b1a95"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"936322e059e14cf6511e50dc2decb8b06bc2d2afefb9bc14dda2bebbc3ee83eb"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.11632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ao Ke, Xike Xie, Yukun Cao, Zhiyang Li","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-14T07:16:11Z","title":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.11632","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T14:45:02.696687Z","id":"6e874506-69f0-41b5-945c-642fe7bb6940","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"Extensive experiments on FVQA 2.0+ and MVQA benchmarks demonstrate that KG-ViP significantly outperforms existing VQA methods.","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."}},"verdict_id":"6e874506-69f0-41b5-945c-642fe7bb6940"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d344dd7d404c5a97cacd363ed9d7d30b90c4f8741113163360e0a158fb3657f8","target":"record","created_at":"2026-05-28T01:04:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5caf495aa892e5cb638cee688588e87e82cc12b1ed3537d4c9fcd6c3da1ef5a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-14T07:16:11Z","title_canon_sha256":"6c0aac27e602569de5afe28f9c1c2d34e60daf8752b60ceefc4c9f5a892df5bf"},"schema_version":"1.0","source":{"id":"2601.11632","kind":"arxiv","version":3}},"canonical_sha256":"bb879fbfe88b21686d3569ebf424e15a7d27b5780b0c0b2dae1e3471b3f9bcca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb879fbfe88b21686d3569ebf424e15a7d27b5780b0c0b2dae1e3471b3f9bcca","first_computed_at":"2026-05-28T01:04:35.437739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:35.437739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2WxLK18f66KuR6Msgy+PRNJ/OA8kSWOLFSWRy3uX0HVGXmvzETIzi/unWTWbzqjFTTYkr0GZ+w8IRe/cV1rKAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:35.438163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.11632","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d344dd7d404c5a97cacd363ed9d7d30b90c4f8741113163360e0a158fb3657f8","sha256:6a923c631658283f1eedf65356bc36e8f929af3376d11faf6c516dd4866a83df"],"state_sha256":"425f50457e2651763a2897e6417869b63992c6af3e62b7b53d1819c2b6a47963"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V2z3XNzG6+P4FxkCDeDXUuQpMld/pgAtfhFTqh21mxGAYEbvVoSZkdjKqZxg1eJBli3yIwDcPtJ5hJ4KWYANAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T15:22:33.749189Z","bundle_sha256":"b2047603c8b165efa8e222b6241c916ba827f30418052c781103e034f09dbeb7"}}