{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7IHQJG24LB5GASR5VWY7NR4ETR","short_pith_number":"pith:7IHQJG24","schema_version":"1.0","canonical_sha256":"fa0f049b5c587a604a3dadb1f6c7849c70aaf3ddd48e6a1c0a660598de8fd964","source":{"kind":"arxiv","id":"2509.09159","version":1},"attestation_state":"computed","paper":{"title":"A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jinyuan Liu, Sihang Liu, Xinru Zhang, Zhiyue Liu","submitted_at":"2025-09-11T05:40:26Z","abstract_excerpt":"Knowledge-based visual question answering (KB-VQA) requires a model to understand images and utilize external knowledge to provide accurate answers. Existing approaches often directly augment models with retrieved information from knowledge sources while ignoring substantial knowledge redundancy, which introduces noise into the answering process. To address this, we propose a training-free framework with knowledge focusing for KB-VQA, that mitigates the impact of noise by enhancing knowledge relevance and reducing redundancy. First, for knowledge retrieval, our framework concludes essential pa"},"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":"2509.09159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T05:40:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a62fe6030c0d01de381be19736559baba832f53499bfb76f213e08f484e8eeb7","abstract_canon_sha256":"e4a755fb67ae94366f36c529bf50f0aa0d1313785ecf14e07ecab888e73ebc18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:30.729199Z","signature_b64":"vXC3iFOmC1v+lFbaz6K4b71AJ0f7ZQDSXcHOGL6jIT3erSFGz1FYFWZsvPnogME0sKj4YSDOyn/yQwT6TN3/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa0f049b5c587a604a3dadb1f6c7849c70aaf3ddd48e6a1c0a660598de8fd964","last_reissued_at":"2026-07-05T12:09:30.728659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:30.728659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jinyuan Liu, Sihang Liu, Xinru Zhang, Zhiyue Liu","submitted_at":"2025-09-11T05:40:26Z","abstract_excerpt":"Knowledge-based visual question answering (KB-VQA) requires a model to understand images and utilize external knowledge to provide accurate answers. Existing approaches often directly augment models with retrieved information from knowledge sources while ignoring substantial knowledge redundancy, which introduces noise into the answering process. To address this, we propose a training-free framework with knowledge focusing for KB-VQA, that mitigates the impact of noise by enhancing knowledge relevance and reducing redundancy. First, for knowledge retrieval, our framework concludes essential pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09159","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/2509.09159/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":"2509.09159","created_at":"2026-07-05T12:09:30.728718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09159v1","created_at":"2026-07-05T12:09:30.728718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09159","created_at":"2026-07-05T12:09:30.728718+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IHQJG24LB5G","created_at":"2026-07-05T12:09:30.728718+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IHQJG24LB5GASR5","created_at":"2026-07-05T12:09:30.728718+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IHQJG24","created_at":"2026-07-05T12:09:30.728718+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/7IHQJG24LB5GASR5VWY7NR4ETR","json":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR.json","graph_json":"https://pith.science/api/pith-number/7IHQJG24LB5GASR5VWY7NR4ETR/graph.json","events_json":"https://pith.science/api/pith-number/7IHQJG24LB5GASR5VWY7NR4ETR/events.json","paper":"https://pith.science/paper/7IHQJG24"},"agent_actions":{"view_html":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR","download_json":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR.json","view_paper":"https://pith.science/paper/7IHQJG24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09159&json=true","fetch_graph":"https://pith.science/api/pith-number/7IHQJG24LB5GASR5VWY7NR4ETR/graph.json","fetch_events":"https://pith.science/api/pith-number/7IHQJG24LB5GASR5VWY7NR4ETR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR/action/storage_attestation","attest_author":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR/action/author_attestation","sign_citation":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR/action/citation_signature","submit_replication":"https://pith.science/pith/7IHQJG24LB5GASR5VWY7NR4ETR/action/replication_record"}},"created_at":"2026-07-05T12:09:30.728718+00:00","updated_at":"2026-07-05T12:09:30.728718+00:00"}