{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D25LTXGZUNBRFM56IOGQ3LKS44","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":"43fe07d93ac3300e3050ac54c596ce11cac865fac7dbe3f36aedd8e1179d559a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-18T05:04:49Z","title_canon_sha256":"650188c2e3565218f8b72d977b4e6dad79ab4e32a1c7dbb357bc93e6ad6d7ce1"},"schema_version":"1.0","source":{"id":"2605.22829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22829","created_at":"2026-05-25T00:00:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22829v1","created_at":"2026-05-25T00:00:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22829","created_at":"2026-05-25T00:00:58Z"},{"alias_kind":"pith_short_12","alias_value":"D25LTXGZUNBR","created_at":"2026-05-25T00:00:58Z"},{"alias_kind":"pith_short_16","alias_value":"D25LTXGZUNBRFM56","created_at":"2026-05-25T00:00:58Z"},{"alias_kind":"pith_short_8","alias_value":"D25LTXGZ","created_at":"2026-05-25T00:00:58Z"}],"graph_snapshots":[{"event_id":"sha256:8275dbc41fd9aa8468c95c7eaf0071dabcd64ae3ed38899b263e8d062540eab4","target":"graph","created_at":"2026-05-25T00:00:58Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.22829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Yanchu Guan, Yifan Zhu, Yue Lu, Yu Mi, Zhixuan Chu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-18T05:04:49Z","title":"LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22829","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b758f006700a9668c72adfac5a7482ceb07742341645822e65673a0cf50035c2","target":"record","created_at":"2026-05-25T00:00:58Z","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":"43fe07d93ac3300e3050ac54c596ce11cac865fac7dbe3f36aedd8e1179d559a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-18T05:04:49Z","title_canon_sha256":"650188c2e3565218f8b72d977b4e6dad79ab4e32a1c7dbb357bc93e6ad6d7ce1"},"schema_version":"1.0","source":{"id":"2605.22829","kind":"arxiv","version":1}},"canonical_sha256":"1ebab9dcd9a34312b3be438d0dad52e72c041b60bc2dbae6ef810325a83b5651","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ebab9dcd9a34312b3be438d0dad52e72c041b60bc2dbae6ef810325a83b5651","first_computed_at":"2026-05-25T00:00:58.107120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T00:00:58.107120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xr9UMecxjedCtbqRoFp4Op72tIWwUuPz8TJbyhgCS1lj3m3Y0e/MQDsQN7mv7WQ0SYkD1UyzllAEuMHzmjpKAQ==","signature_status":"signed_v1","signed_at":"2026-05-25T00:00:58.108981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b758f006700a9668c72adfac5a7482ceb07742341645822e65673a0cf50035c2","sha256:8275dbc41fd9aa8468c95c7eaf0071dabcd64ae3ed38899b263e8d062540eab4"],"state_sha256":"e1b374c4aadf349d318e65e1878e6343d6688138cf5806732b3489d1c1d14d01"}