{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4VYFJAUTGOFEKMETN6EBFSAKNU","short_pith_number":"pith:4VYFJAUT","schema_version":"1.0","canonical_sha256":"e570548293338a4530936f8812c80a6d1d72784ba75779abb3adf3c6220ad931","source":{"kind":"arxiv","id":"2509.09721","version":1},"attestation_state":"computed","paper":{"title":"A Multimodal RAG Framework for Housing Damage Assessment: Collaborative Optimization of Image Encoding and Policy Vector Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dingxin Lu, Jiayi Miao, Zhuqi Wang","submitted_at":"2025-09-10T01:58:07Z","abstract_excerpt":"After natural disasters, accurate evaluations of damage to housing are important for insurance claims response and planning of resources. In this work, we introduce a novel multimodal retrieval-augmented generation (MM-RAG) framework. On top of classical RAG architecture, we further the framework to devise a two-branch multimodal encoder structure that the image branch employs a visual encoder composed of ResNet and Transformer to extract the characteristic of building damage after disaster, and the text branch harnesses a BERT retriever for the text vectorization of posts as well as insurance"},"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":"2509.09721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T01:58:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aef94f47e094dc7471714903721bb3a4a9bc5f319ca581196710332a8b01b88f","abstract_canon_sha256":"ab644906f7417461e70853719f3fc97a191ecb10853dfc7b93c4e0be4e0dbfa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:47.840301Z","signature_b64":"qxoG71ymnK4oTnpu4yestkp0xLkSVdA8DgM77QBhcHKlwvr5XWOCwY4YiR350j6V2yP1jlNhSI1ZH46h98t6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e570548293338a4530936f8812c80a6d1d72784ba75779abb3adf3c6220ad931","last_reissued_at":"2026-07-05T12:09:47.839727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:47.839727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multimodal RAG Framework for Housing Damage Assessment: Collaborative Optimization of Image Encoding and Policy Vector Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dingxin Lu, Jiayi Miao, Zhuqi Wang","submitted_at":"2025-09-10T01:58:07Z","abstract_excerpt":"After natural disasters, accurate evaluations of damage to housing are important for insurance claims response and planning of resources. In this work, we introduce a novel multimodal retrieval-augmented generation (MM-RAG) framework. On top of classical RAG architecture, we further the framework to devise a two-branch multimodal encoder structure that the image branch employs a visual encoder composed of ResNet and Transformer to extract the characteristic of building damage after disaster, and the text branch harnesses a BERT retriever for the text vectorization of posts as well as insurance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09721","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/2509.09721/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":"2509.09721","created_at":"2026-07-05T12:09:47.839806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09721v1","created_at":"2026-07-05T12:09:47.839806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09721","created_at":"2026-07-05T12:09:47.839806+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VYFJAUTGOFE","created_at":"2026-07-05T12:09:47.839806+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VYFJAUTGOFEKMET","created_at":"2026-07-05T12:09:47.839806+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VYFJAUT","created_at":"2026-07-05T12:09:47.839806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18844","citing_title":"Graph-Driven Cross-Industry Real-Time Monitoring Framework for Anti-Money Laundering Detection in Converged Mobility-Energy Supply Chain Networks","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU","json":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU.json","graph_json":"https://pith.science/api/pith-number/4VYFJAUTGOFEKMETN6EBFSAKNU/graph.json","events_json":"https://pith.science/api/pith-number/4VYFJAUTGOFEKMETN6EBFSAKNU/events.json","paper":"https://pith.science/paper/4VYFJAUT"},"agent_actions":{"view_html":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU","download_json":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU.json","view_paper":"https://pith.science/paper/4VYFJAUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09721&json=true","fetch_graph":"https://pith.science/api/pith-number/4VYFJAUTGOFEKMETN6EBFSAKNU/graph.json","fetch_events":"https://pith.science/api/pith-number/4VYFJAUTGOFEKMETN6EBFSAKNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU/action/storage_attestation","attest_author":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU/action/author_attestation","sign_citation":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU/action/citation_signature","submit_replication":"https://pith.science/pith/4VYFJAUTGOFEKMETN6EBFSAKNU/action/replication_record"}},"created_at":"2026-07-05T12:09:47.839806+00:00","updated_at":"2026-07-05T12:09:47.839806+00:00"}