{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZP6SGHJILGDY6HKK77A45D6HTX","short_pith_number":"pith:ZP6SGHJI","schema_version":"1.0","canonical_sha256":"cbfd231d2859878f1d4affc1ce8fc79dc5354ddfcc20fb061f6b9c58cdd503d2","source":{"kind":"arxiv","id":"2303.10868","version":3},"attestation_state":"computed","paper":{"title":"Retrieving Multimodal Information for Augmented Generation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bosheng Ding, Chengwei Qin, Fangkai Jiao, Hailin Chen, Minzhi Li, Ruochen Zhao, Shafiq Joty, Weishi Wang, Xiaobao Guo, Xingxuan Li, Xuan Long Do","submitted_at":"2023-03-20T05:07:41Z","abstract_excerpt":"As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs' generation ability, which enables LLMs to better interact with the world. However, there lacks a unified perception of at which stage and how to incorporate different modalities. In this survey, we review methods that assist and augment generative models by retrieving multimodal knowledge, whose formats range from images, codes, tables, graphs, to audio. Such methods offer a promising solution to important concerns such as factuality, reasoning, interpretability, and rob"},"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":"2303.10868","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-20T05:07:41Z","cross_cats_sorted":[],"title_canon_sha256":"3538a5f5824c5ea4390f4972e7ddb3657e553c3f03b3463b4630abc27e9675c9","abstract_canon_sha256":"e4625b21f6262732ab5f13675e36ff4d31142230eefd7ae628f9ac62dd91fd20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:56.835502Z","signature_b64":"fYqrzBQKTx8pShIBmZVi8xAjGxYvqXRItXacqtYqv/G73V6wANXf7AMO5Gf/vli6MLh+3CrQ+PZEyyOC5C18DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbfd231d2859878f1d4affc1ce8fc79dc5354ddfcc20fb061f6b9c58cdd503d2","last_reissued_at":"2026-07-05T07:18:56.835018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:56.835018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieving Multimodal Information for Augmented Generation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bosheng Ding, Chengwei Qin, Fangkai Jiao, Hailin Chen, Minzhi Li, Ruochen Zhao, Shafiq Joty, Weishi Wang, Xiaobao Guo, Xingxuan Li, Xuan Long Do","submitted_at":"2023-03-20T05:07:41Z","abstract_excerpt":"As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs' generation ability, which enables LLMs to better interact with the world. However, there lacks a unified perception of at which stage and how to incorporate different modalities. In this survey, we review methods that assist and augment generative models by retrieving multimodal knowledge, whose formats range from images, codes, tables, graphs, to audio. Such methods offer a promising solution to important concerns such as factuality, reasoning, interpretability, and rob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10868","kind":"arxiv","version":3},"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/2303.10868/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":"2303.10868","created_at":"2026-07-05T07:18:56.835076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10868v3","created_at":"2026-07-05T07:18:56.835076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10868","created_at":"2026-07-05T07:18:56.835076+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZP6SGHJILGDY","created_at":"2026-07-05T07:18:56.835076+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZP6SGHJILGDY6HKK","created_at":"2026-07-05T07:18:56.835076+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZP6SGHJI","created_at":"2026-07-05T07:18:56.835076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.22095","citing_title":"Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19689","citing_title":"A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX","json":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX.json","graph_json":"https://pith.science/api/pith-number/ZP6SGHJILGDY6HKK77A45D6HTX/graph.json","events_json":"https://pith.science/api/pith-number/ZP6SGHJILGDY6HKK77A45D6HTX/events.json","paper":"https://pith.science/paper/ZP6SGHJI"},"agent_actions":{"view_html":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX","download_json":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX.json","view_paper":"https://pith.science/paper/ZP6SGHJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10868&json=true","fetch_graph":"https://pith.science/api/pith-number/ZP6SGHJILGDY6HKK77A45D6HTX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZP6SGHJILGDY6HKK77A45D6HTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX/action/storage_attestation","attest_author":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX/action/author_attestation","sign_citation":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX/action/citation_signature","submit_replication":"https://pith.science/pith/ZP6SGHJILGDY6HKK77A45D6HTX/action/replication_record"}},"created_at":"2026-07-05T07:18:56.835076+00:00","updated_at":"2026-07-05T07:18:56.835076+00:00"}