{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G5YDV35UDELPZI7OVDQHYLBMMB","short_pith_number":"pith:G5YDV35U","schema_version":"1.0","canonical_sha256":"37703aefb41916fca3eea8e07c2c2c605dc7f0a14417896eb6cf6c18700d086d","source":{"kind":"arxiv","id":"2607.24554","version":1},"attestation_state":"computed","paper":{"title":"DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Fang Xi, Junming Su, Kai Zhang, Qing Wang, Shuo Wang, Wenyuan Huang, Xia Liao, Yizheng Yu","submitted_at":"2026-07-27T15:28:02Z","abstract_excerpt":"Advancing multimodal retrieval-augmented generation (RAG) for complex document understanding presents a formidable dual dilemma of accuracy and efficiency, particularly in graph RAG. Processing structurally sparse yet visually dense layouts, such as extracting a tiny data marker from a financial chart, often incurs computationally prohibitive token overhead while still triggering catastrophic hallucination. However, multimodal Graph RAG pipelines rely on graph-construction stages that assume Vision-Language Models (VLMs) can resolve sparse semantics within high-density layouts. We challenge th"},"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":"2607.24554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-27T15:28:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d4077038bcb52a6a438cba7cb11514c29aee1557106342b10f67ae367346af64","abstract_canon_sha256":"600287bd688eb855661f4317caf83a9f531c565a1ae6f9222dfb6cf9d1e2b357"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:09.951393Z","signature_b64":"OMDQ3I3alNNh4C45w1zZH+xQrhHuad06X+Y8aBWFrpp+TumLP6wG1PFow9flGAu2h0lXF/irm8RZGyr6J41FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37703aefb41916fca3eea8e07c2c2c605dc7f0a14417896eb6cf6c18700d086d","last_reissued_at":"2026-07-28T02:24:09.950594Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:09.950594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Fang Xi, Junming Su, Kai Zhang, Qing Wang, Shuo Wang, Wenyuan Huang, Xia Liao, Yizheng Yu","submitted_at":"2026-07-27T15:28:02Z","abstract_excerpt":"Advancing multimodal retrieval-augmented generation (RAG) for complex document understanding presents a formidable dual dilemma of accuracy and efficiency, particularly in graph RAG. Processing structurally sparse yet visually dense layouts, such as extracting a tiny data marker from a financial chart, often incurs computationally prohibitive token overhead while still triggering catastrophic hallucination. However, multimodal Graph RAG pipelines rely on graph-construction stages that assume Vision-Language Models (VLMs) can resolve sparse semantics within high-density layouts. We challenge th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24554","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/2607.24554/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":"2607.24554","created_at":"2026-07-28T02:24:09.950990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24554v1","created_at":"2026-07-28T02:24:09.950990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24554","created_at":"2026-07-28T02:24:09.950990+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5YDV35UDELP","created_at":"2026-07-28T02:24:09.950990+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5YDV35UDELPZI7O","created_at":"2026-07-28T02:24:09.950990+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5YDV35U","created_at":"2026-07-28T02:24:09.950990+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/G5YDV35UDELPZI7OVDQHYLBMMB","json":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB.json","graph_json":"https://pith.science/api/pith-number/G5YDV35UDELPZI7OVDQHYLBMMB/graph.json","events_json":"https://pith.science/api/pith-number/G5YDV35UDELPZI7OVDQHYLBMMB/events.json","paper":"https://pith.science/paper/G5YDV35U"},"agent_actions":{"view_html":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB","download_json":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB.json","view_paper":"https://pith.science/paper/G5YDV35U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24554&json=true","fetch_graph":"https://pith.science/api/pith-number/G5YDV35UDELPZI7OVDQHYLBMMB/graph.json","fetch_events":"https://pith.science/api/pith-number/G5YDV35UDELPZI7OVDQHYLBMMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB/action/storage_attestation","attest_author":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB/action/author_attestation","sign_citation":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB/action/citation_signature","submit_replication":"https://pith.science/pith/G5YDV35UDELPZI7OVDQHYLBMMB/action/replication_record"}},"created_at":"2026-07-28T02:24:09.950990+00:00","updated_at":"2026-07-28T02:24:09.950990+00:00"}