{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6OO5V5JUJM5PUE3KPSMKPDPSAR","short_pith_number":"pith:6OO5V5JU","schema_version":"1.0","canonical_sha256":"f39ddaf5344b3afa136a7c98a78df2045e29e3bdf24fe4dc19eeb3f2aa84967e","source":{"kind":"arxiv","id":"2406.13213","version":2},"attestation_state":"computed","paper":{"title":"Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Mykhailo Poliakov, Nadiya Shvai","submitted_at":"2024-06-19T04:53:48Z","abstract_excerpt":"The retrieval-augmented generation (RAG) enables retrieval of relevant information from an external knowledge source and allows large language models (LLMs) to answer queries over previously unseen document collections. However, it was demonstrated that traditional RAG applications perform poorly in answering multi-hop questions, which require retrieving and reasoning over multiple elements of supporting evidence. We introduce a new method called Multi-Meta-RAG, which uses database filtering with LLM-extracted metadata to improve the RAG selection of the relevant documents from various sources"},"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":"2406.13213","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T04:53:48Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"3b09c483e3bdc9f8cc3fce194d215e5f8bd28c4638c77dc8accedc08a021687f","abstract_canon_sha256":"653d9e7d001495d00cad58e8731bba73112801317373bd90560a24bc4c2b45d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:59.868810Z","signature_b64":"BBf5iInB0ecvkeBSMBalNzZASYaL6/6FV+UtPmFGetkw10N4XPCLYCfFB0cLZm3MeK256YYD3Xo/S2MGvQBqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f39ddaf5344b3afa136a7c98a78df2045e29e3bdf24fe4dc19eeb3f2aa84967e","last_reissued_at":"2026-07-05T10:42:59.868350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:59.868350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Mykhailo Poliakov, Nadiya Shvai","submitted_at":"2024-06-19T04:53:48Z","abstract_excerpt":"The retrieval-augmented generation (RAG) enables retrieval of relevant information from an external knowledge source and allows large language models (LLMs) to answer queries over previously unseen document collections. However, it was demonstrated that traditional RAG applications perform poorly in answering multi-hop questions, which require retrieving and reasoning over multiple elements of supporting evidence. We introduce a new method called Multi-Meta-RAG, which uses database filtering with LLM-extracted metadata to improve the RAG selection of the relevant documents from various sources"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13213","kind":"arxiv","version":2},"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/2406.13213/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":"2406.13213","created_at":"2026-07-05T10:42:59.868403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13213v2","created_at":"2026-07-05T10:42:59.868403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13213","created_at":"2026-07-05T10:42:59.868403+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OO5V5JUJM5P","created_at":"2026-07-05T10:42:59.868403+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OO5V5JUJM5PUE3K","created_at":"2026-07-05T10:42:59.868403+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OO5V5JU","created_at":"2026-07-05T10:42:59.868403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02522","citing_title":"Opal: Private Memory for Personal AI","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01970","citing_title":"Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR","json":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR.json","graph_json":"https://pith.science/api/pith-number/6OO5V5JUJM5PUE3KPSMKPDPSAR/graph.json","events_json":"https://pith.science/api/pith-number/6OO5V5JUJM5PUE3KPSMKPDPSAR/events.json","paper":"https://pith.science/paper/6OO5V5JU"},"agent_actions":{"view_html":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR","download_json":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR.json","view_paper":"https://pith.science/paper/6OO5V5JU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13213&json=true","fetch_graph":"https://pith.science/api/pith-number/6OO5V5JUJM5PUE3KPSMKPDPSAR/graph.json","fetch_events":"https://pith.science/api/pith-number/6OO5V5JUJM5PUE3KPSMKPDPSAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR/action/storage_attestation","attest_author":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR/action/author_attestation","sign_citation":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR/action/citation_signature","submit_replication":"https://pith.science/pith/6OO5V5JUJM5PUE3KPSMKPDPSAR/action/replication_record"}},"created_at":"2026-07-05T10:42:59.868403+00:00","updated_at":"2026-07-05T10:42:59.868403+00:00"}