{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZETC5DU74H75JONG4MMILZDJ6S","short_pith_number":"pith:ZETC5DU7","schema_version":"1.0","canonical_sha256":"c9262e8e9fe1ffd4b9a6e31885e469f4ba593e65e099793ab0513a5d8743bcfa","source":{"kind":"arxiv","id":"2506.02544","version":2},"attestation_state":"computed","paper":{"title":"CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Fan Liu, Jingyuan Zhang, Liqiang Nie, Victoria W., Yang Tian, Yupeng Hu","submitted_at":"2025-06-03T07:32:40Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (MMRAG) has been introduced to enhance Multimodal Large Language Models by incorporating externally retrieved multimodal knowledge, but it introduces two challenges: Parametric-Retrieved Knowledge Inconsistency (PRKI), where discrepancies between parametric and retrieved knowledge create uncertainty in determining reliability, and Visual-Textual Knowledge Inconsistency (VTKI), where misalignment between visual and textual sources disrupts entity representation. To address these challenges, we propose Cross-source knowledge \\textbf{Re}conciliation for M"},"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":"2506.02544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T07:32:40Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"864d6976b684f56ef736071160c39963714ca3f2b24c25530e529539f89087c2","abstract_canon_sha256":"65534f2231eaed7a8ee9686565aef35d77b029655f61efa68962ae39791abfe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:09.659686Z","signature_b64":"BW6L2k9Gukdb7mXXk8d6wpHMZw/8xUU9U1Uzx9aJ6p0UmOpE/nztCUo9uXvQpSof+1+X5jL9VEmVedDpKpsPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9262e8e9fe1ffd4b9a6e31885e469f4ba593e65e099793ab0513a5d8743bcfa","last_reissued_at":"2026-07-05T11:16:09.659071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:09.659071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Fan Liu, Jingyuan Zhang, Liqiang Nie, Victoria W., Yang Tian, Yupeng Hu","submitted_at":"2025-06-03T07:32:40Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (MMRAG) has been introduced to enhance Multimodal Large Language Models by incorporating externally retrieved multimodal knowledge, but it introduces two challenges: Parametric-Retrieved Knowledge Inconsistency (PRKI), where discrepancies between parametric and retrieved knowledge create uncertainty in determining reliability, and Visual-Textual Knowledge Inconsistency (VTKI), where misalignment between visual and textual sources disrupts entity representation. To address these challenges, we propose Cross-source knowledge \\textbf{Re}conciliation for M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02544","kind":"arxiv","version":2},"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/2506.02544/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":"2506.02544","created_at":"2026-07-05T11:16:09.659149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02544v2","created_at":"2026-07-05T11:16:09.659149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02544","created_at":"2026-07-05T11:16:09.659149+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZETC5DU74H75","created_at":"2026-07-05T11:16:09.659149+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZETC5DU74H75JONG","created_at":"2026-07-05T11:16:09.659149+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZETC5DU7","created_at":"2026-07-05T11:16:09.659149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23881","citing_title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00159","citing_title":"Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13856","citing_title":"QKVQA: Question-Focused Filtering for Knowledge-based VQA","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00104","citing_title":"R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S","json":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S.json","graph_json":"https://pith.science/api/pith-number/ZETC5DU74H75JONG4MMILZDJ6S/graph.json","events_json":"https://pith.science/api/pith-number/ZETC5DU74H75JONG4MMILZDJ6S/events.json","paper":"https://pith.science/paper/ZETC5DU7"},"agent_actions":{"view_html":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S","download_json":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S.json","view_paper":"https://pith.science/paper/ZETC5DU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02544&json=true","fetch_graph":"https://pith.science/api/pith-number/ZETC5DU74H75JONG4MMILZDJ6S/graph.json","fetch_events":"https://pith.science/api/pith-number/ZETC5DU74H75JONG4MMILZDJ6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S/action/storage_attestation","attest_author":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S/action/author_attestation","sign_citation":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S/action/citation_signature","submit_replication":"https://pith.science/pith/ZETC5DU74H75JONG4MMILZDJ6S/action/replication_record"}},"created_at":"2026-07-05T11:16:09.659149+00:00","updated_at":"2026-07-05T11:16:09.659149+00:00"}