{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D25LTXGZUNBRFM56IOGQ3LKS44","short_pith_number":"pith:D25LTXGZ","schema_version":"1.0","canonical_sha256":"1ebab9dcd9a34312b3be438d0dad52e72c041b60bc2dbae6ef810325a83b5651","source":{"kind":"arxiv","id":"2605.22829","version":1},"attestation_state":"computed","paper":{"title":"LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Yanchu Guan, Yifan Zhu, Yue Lu, Yu Mi, Zhixuan Chu","submitted_at":"2026-04-18T05:04:49Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coarse-grained page-level retrieval, which fails to capture fine-grained semantic and layout structures in visually rich documents, thereby compromising retrieval accuracy and leading to redundant context in downstream tasks. To address these issues, we propose Layout-oriented Fine-grained Retrieval-Augmented Generation (LFRAG), a novel framework that advances multimodal RAG from p"},"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":"2605.22829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-18T05:04:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"650188c2e3565218f8b72d977b4e6dad79ab4e32a1c7dbb357bc93e6ad6d7ce1","abstract_canon_sha256":"43fe07d93ac3300e3050ac54c596ce11cac865fac7dbe3f36aedd8e1179d559a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T00:00:58.108981Z","signature_b64":"xr9UMecxjedCtbqRoFp4Op72tIWwUuPz8TJbyhgCS1lj3m3Y0e/MQDsQN7mv7WQ0SYkD1UyzllAEuMHzmjpKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ebab9dcd9a34312b3be438d0dad52e72c041b60bc2dbae6ef810325a83b5651","last_reissued_at":"2026-05-25T00:00:58.107120Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T00:00:58.107120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Yanchu Guan, Yifan Zhu, Yue Lu, Yu Mi, Zhixuan Chu","submitted_at":"2026-04-18T05:04:49Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coarse-grained page-level retrieval, which fails to capture fine-grained semantic and layout structures in visually rich documents, thereby compromising retrieval accuracy and leading to redundant context in downstream tasks. To address these issues, we propose Layout-oriented Fine-grained Retrieval-Augmented Generation (LFRAG), a novel framework that advances multimodal RAG from p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22829","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/2605.22829/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":"2605.22829","created_at":"2026-05-25T00:00:58.108195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22829v1","created_at":"2026-05-25T00:00:58.108195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22829","created_at":"2026-05-25T00:00:58.108195+00:00"},{"alias_kind":"pith_short_12","alias_value":"D25LTXGZUNBR","created_at":"2026-05-25T00:00:58.108195+00:00"},{"alias_kind":"pith_short_16","alias_value":"D25LTXGZUNBRFM56","created_at":"2026-05-25T00:00:58.108195+00:00"},{"alias_kind":"pith_short_8","alias_value":"D25LTXGZ","created_at":"2026-05-25T00:00:58.108195+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/D25LTXGZUNBRFM56IOGQ3LKS44","json":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44.json","graph_json":"https://pith.science/api/pith-number/D25LTXGZUNBRFM56IOGQ3LKS44/graph.json","events_json":"https://pith.science/api/pith-number/D25LTXGZUNBRFM56IOGQ3LKS44/events.json","paper":"https://pith.science/paper/D25LTXGZ"},"agent_actions":{"view_html":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44","download_json":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44.json","view_paper":"https://pith.science/paper/D25LTXGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22829&json=true","fetch_graph":"https://pith.science/api/pith-number/D25LTXGZUNBRFM56IOGQ3LKS44/graph.json","fetch_events":"https://pith.science/api/pith-number/D25LTXGZUNBRFM56IOGQ3LKS44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44/action/storage_attestation","attest_author":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44/action/author_attestation","sign_citation":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44/action/citation_signature","submit_replication":"https://pith.science/pith/D25LTXGZUNBRFM56IOGQ3LKS44/action/replication_record"}},"created_at":"2026-05-25T00:00:58.108195+00:00","updated_at":"2026-05-25T00:00:58.108195+00:00"}