{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P5XRJRCLEUMZ4GI5BK7ROXZ2KF","short_pith_number":"pith:P5XRJRCL","schema_version":"1.0","canonical_sha256":"7f6f14c44b25199e191d0abf175f3a5157b480246eef61c20c6cf17143f23b1d","source":{"kind":"arxiv","id":"2501.05030","version":1},"attestation_state":"computed","paper":{"title":"A General Retrieval-Augmented Generation Framework for Multimodal Case-Based Reasoning Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ofir Marom","submitted_at":"2025-01-09T07:41:22Z","abstract_excerpt":"Case-based reasoning (CBR) is an experience-based approach to problem solving, where a repository of solved cases is adapted to solve new cases. Recent research shows that Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) can support the Retrieve and Reuse stages of the CBR pipeline by retrieving similar cases and using them as additional context to an LLM query. Most studies have focused on text-only applications, however, in many real-world problems the components of a case are multimodal. In this paper we present MCBR-RAG, a general RAG framework for multimodal CBR appl"},"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":"2501.05030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-09T07:41:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"264f00dd94b8e0aae02890cf993ee2748b5f51256f695aabe417a1bee01e8941","abstract_canon_sha256":"726cd4adc4418c40fc10dc4e6a1b175eafe60f8bc32b8d39c5305e5bf6345466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:03.419919Z","signature_b64":"uQeFhZ2A7hplx28+nYXJPpreP5QHQXXIQZBqPKavLXTEUG9e7E2GbqygKRlOkz0Np2mGuzgSlekDnRqHWPGCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f6f14c44b25199e191d0abf175f3a5157b480246eef61c20c6cf17143f23b1d","last_reissued_at":"2026-07-05T09:59:03.419407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:03.419407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Retrieval-Augmented Generation Framework for Multimodal Case-Based Reasoning Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ofir Marom","submitted_at":"2025-01-09T07:41:22Z","abstract_excerpt":"Case-based reasoning (CBR) is an experience-based approach to problem solving, where a repository of solved cases is adapted to solve new cases. Recent research shows that Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) can support the Retrieve and Reuse stages of the CBR pipeline by retrieving similar cases and using them as additional context to an LLM query. Most studies have focused on text-only applications, however, in many real-world problems the components of a case are multimodal. In this paper we present MCBR-RAG, a general RAG framework for multimodal CBR appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05030","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/2501.05030/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":"2501.05030","created_at":"2026-07-05T09:59:03.419468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05030v1","created_at":"2026-07-05T09:59:03.419468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05030","created_at":"2026-07-05T09:59:03.419468+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5XRJRCLEUMZ","created_at":"2026-07-05T09:59:03.419468+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5XRJRCLEUMZ4GI5","created_at":"2026-07-05T09:59:03.419468+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5XRJRCL","created_at":"2026-07-05T09:59:03.419468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20963","citing_title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF","json":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF.json","graph_json":"https://pith.science/api/pith-number/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/graph.json","events_json":"https://pith.science/api/pith-number/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/events.json","paper":"https://pith.science/paper/P5XRJRCL"},"agent_actions":{"view_html":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF","download_json":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF.json","view_paper":"https://pith.science/paper/P5XRJRCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05030&json=true","fetch_graph":"https://pith.science/api/pith-number/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/graph.json","fetch_events":"https://pith.science/api/pith-number/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/action/storage_attestation","attest_author":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/action/author_attestation","sign_citation":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/action/citation_signature","submit_replication":"https://pith.science/pith/P5XRJRCLEUMZ4GI5BK7ROXZ2KF/action/replication_record"}},"created_at":"2026-07-05T09:59:03.419468+00:00","updated_at":"2026-07-05T09:59:03.419468+00:00"}