{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MRWVZ6PGGH2BOQVIO7QC3NLKIK","short_pith_number":"pith:MRWVZ6PG","schema_version":"1.0","canonical_sha256":"646d5cf9e631f41742a877e02db56a429f6df8ec8995617fe6449c477e35bbbb","source":{"kind":"arxiv","id":"2605.25030","version":1},"attestation_state":"computed","paper":{"title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Magnus Samuelsen, Mansoor Hussain, Mikkel Strange, Somnath Mazumdar, Wilmer Nystr\\\"om","submitted_at":"2026-05-24T12:15:27Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (LLMs), a requirement for reliable, financial analysis where answers must be grounded in verifiable evidence from filings rather than generated from model priors. However, designing RAG systems that extract meaningful insights from mixed financial documents and integrate into analyst workflows remains challenging. This paper introduces MimirRAG (Metadata-Integrated Multi-Agent Information Retrieval), a multi-agent RAG system developed iteratively"},"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":"2605.25030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T12:15:27Z","cross_cats_sorted":[],"title_canon_sha256":"17d63d0dc6f475f907b171cbe67ebfbea39a66abfccc369fbcfed343a679a6d3","abstract_canon_sha256":"0747460fad01ae246361e961afc69ddaa9e1acf48935c25b83a70f8e1d9198d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:11.237992Z","signature_b64":"KKufesIn+w1nqFsws0oBZCNAOxAejzssUvnZnuCUgvyykLzzHL4FqL+t3sIuz9AxnYYkhgbpxiVqYrqxroNrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"646d5cf9e631f41742a877e02db56a429f6df8ec8995617fe6449c477e35bbbb","last_reissued_at":"2026-05-26T01:04:11.237487Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:11.237487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Magnus Samuelsen, Mansoor Hussain, Mikkel Strange, Somnath Mazumdar, Wilmer Nystr\\\"om","submitted_at":"2026-05-24T12:15:27Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (LLMs), a requirement for reliable, financial analysis where answers must be grounded in verifiable evidence from filings rather than generated from model priors. However, designing RAG systems that extract meaningful insights from mixed financial documents and integrate into analyst workflows remains challenging. This paper introduces MimirRAG (Metadata-Integrated Multi-Agent Information Retrieval), a multi-agent RAG system developed iteratively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25030","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/2605.25030/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":"2605.25030","created_at":"2026-05-26T01:04:11.237563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25030v1","created_at":"2026-05-26T01:04:11.237563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25030","created_at":"2026-05-26T01:04:11.237563+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRWVZ6PGGH2B","created_at":"2026-05-26T01:04:11.237563+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRWVZ6PGGH2BOQVI","created_at":"2026-05-26T01:04:11.237563+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRWVZ6PG","created_at":"2026-05-26T01:04:11.237563+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/MRWVZ6PGGH2BOQVIO7QC3NLKIK","json":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK.json","graph_json":"https://pith.science/api/pith-number/MRWVZ6PGGH2BOQVIO7QC3NLKIK/graph.json","events_json":"https://pith.science/api/pith-number/MRWVZ6PGGH2BOQVIO7QC3NLKIK/events.json","paper":"https://pith.science/paper/MRWVZ6PG"},"agent_actions":{"view_html":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK","download_json":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK.json","view_paper":"https://pith.science/paper/MRWVZ6PG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25030&json=true","fetch_graph":"https://pith.science/api/pith-number/MRWVZ6PGGH2BOQVIO7QC3NLKIK/graph.json","fetch_events":"https://pith.science/api/pith-number/MRWVZ6PGGH2BOQVIO7QC3NLKIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK/action/storage_attestation","attest_author":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK/action/author_attestation","sign_citation":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK/action/citation_signature","submit_replication":"https://pith.science/pith/MRWVZ6PGGH2BOQVIO7QC3NLKIK/action/replication_record"}},"created_at":"2026-05-26T01:04:11.237563+00:00","updated_at":"2026-05-26T01:04:11.237563+00:00"}