{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MJH6IQT3OJVSBCUBNXAJYPSWYC","short_pith_number":"pith:MJH6IQT3","schema_version":"1.0","canonical_sha256":"624fe4427b726b208a816dc09c3e56c09b8f3df7e62cd40da0b8c292db38ae0f","source":{"kind":"arxiv","id":"2607.28580","version":1},"attestation_state":"computed","paper":{"title":"DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haonan Yuan, Jiacheng Tao, Jianxin Li, Qingyun Sun, Ziwei Zhang","submitted_at":"2026-07-30T17:40:05Z","abstract_excerpt":"While Multimodal Retrieval-Augmented Generation (MM-RAG) has shown promising results, it still struggles with complex multi-hop reasoning tasks. Existing methods primarily focus on independent instance-level matching, which often fails to capture explicit relationships across modalities and documents. Although Graph-enhanced methods introduce structural modeling, they face a fundamental challenge in multimodal scenarios: incorporating fine-grained visual features leads to rapid graph expansion and retrieval noise, whereas coarse-grained representations cause the discarding of critical local ev"},"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":"2607.28580","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T17:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"0d111967d4a485be7290b7466fc30a92b20bd44d8c7ada70c2e269fa72b44442","abstract_canon_sha256":"25d0cc75617fa832147c3973f5f03bfc14bb87bc6d1419270dcea2d831c7a1b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"624fe4427b726b208a816dc09c3e56c09b8f3df7e62cd40da0b8c292db38ae0f","last_reissued_at":"2026-07-31T01:38:36.091071Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:38:36.091071Z"},"graph_snapshot":{"paper":{"title":"DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haonan Yuan, Jiacheng Tao, Jianxin Li, Qingyun Sun, Ziwei Zhang","submitted_at":"2026-07-30T17:40:05Z","abstract_excerpt":"While Multimodal Retrieval-Augmented Generation (MM-RAG) has shown promising results, it still struggles with complex multi-hop reasoning tasks. Existing methods primarily focus on independent instance-level matching, which often fails to capture explicit relationships across modalities and documents. Although Graph-enhanced methods introduce structural modeling, they face a fundamental challenge in multimodal scenarios: incorporating fine-grained visual features leads to rapid graph expansion and retrieval noise, whereas coarse-grained representations cause the discarding of critical local ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28580","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/2607.28580/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":"2607.28580","created_at":"2026-07-31T01:38:36.094338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28580v1","created_at":"2026-07-31T01:38:36.094338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28580","created_at":"2026-07-31T01:38:36.094338+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJH6IQT3OJVS","created_at":"2026-07-31T01:38:36.094338+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJH6IQT3OJVSBCUB","created_at":"2026-07-31T01:38:36.094338+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJH6IQT3","created_at":"2026-07-31T01:38:36.094338+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/MJH6IQT3OJVSBCUBNXAJYPSWYC","json":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC.json","graph_json":"https://pith.science/api/pith-number/MJH6IQT3OJVSBCUBNXAJYPSWYC/graph.json","events_json":"https://pith.science/api/pith-number/MJH6IQT3OJVSBCUBNXAJYPSWYC/events.json","paper":"https://pith.science/paper/MJH6IQT3"},"agent_actions":{"view_html":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC","download_json":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC.json","view_paper":"https://pith.science/paper/MJH6IQT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28580&json=true","fetch_graph":"https://pith.science/api/pith-number/MJH6IQT3OJVSBCUBNXAJYPSWYC/graph.json","fetch_events":"https://pith.science/api/pith-number/MJH6IQT3OJVSBCUBNXAJYPSWYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC/action/storage_attestation","attest_author":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC/action/author_attestation","sign_citation":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC/action/citation_signature","submit_replication":"https://pith.science/pith/MJH6IQT3OJVSBCUBNXAJYPSWYC/action/replication_record"}},"created_at":"2026-07-31T01:38:36.094338+00:00","updated_at":"2026-07-31T01:38:36.094338+00:00"}