{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHMQDZ7UQHJSIXYAIWQDETJ6DU","short_pith_number":"pith:EHMQDZ7U","schema_version":"1.0","canonical_sha256":"21d901e7f481d3245f0045a0324d3e1d002fe412e5dac0573cc4774539edc61b","source":{"kind":"arxiv","id":"2409.13992","version":1},"attestation_state":"computed","paper":{"title":"SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiatao Li, Xiaojun Wan, Xinyu Hu","submitted_at":"2024-09-21T03:03:09Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has greatly improved large language models (LLMs) by enabling them to generate accurate, contextually grounded responses through the integration of external information. However, conventional RAG approaches, which prioritize top-ranked documents based solely on query-context relevance, often introduce redundancy and conflicting information. This issue is particularly evident in unsupervised retrieval settings, where there are no mechanisms to effectively mitigate these problems, leading to suboptimal context selection. To address this, we propose Selection "},"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":"2409.13992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-21T03:03:09Z","cross_cats_sorted":[],"title_canon_sha256":"7ab007ff23a45a30bbf82fd9fc3df6562b6b948d77d481c3b5f8d9cc5209d0c9","abstract_canon_sha256":"820d974a26c59a61dd22b732e3a08514ce7c7b5918ce646bcf99e0efd67da412"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:10.065308Z","signature_b64":"BFqdJ3/Choj9J1+0kEhtq5QNklEBFmc49zJU2xfmeHGBl2QLAWvr7YIJPXK4RkjtwFbsSt7l3FER+v5uFDOQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21d901e7f481d3245f0045a0324d3e1d002fe412e5dac0573cc4774539edc61b","last_reissued_at":"2026-07-05T09:10:10.064824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:10.064824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiatao Li, Xiaojun Wan, Xinyu Hu","submitted_at":"2024-09-21T03:03:09Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has greatly improved large language models (LLMs) by enabling them to generate accurate, contextually grounded responses through the integration of external information. However, conventional RAG approaches, which prioritize top-ranked documents based solely on query-context relevance, often introduce redundancy and conflicting information. This issue is particularly evident in unsupervised retrieval settings, where there are no mechanisms to effectively mitigate these problems, leading to suboptimal context selection. To address this, we propose Selection "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13992","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/2409.13992/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":"2409.13992","created_at":"2026-07-05T09:10:10.064883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13992v1","created_at":"2026-07-05T09:10:10.064883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13992","created_at":"2026-07-05T09:10:10.064883+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHMQDZ7UQHJS","created_at":"2026-07-05T09:10:10.064883+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHMQDZ7UQHJSIXYA","created_at":"2026-07-05T09:10:10.064883+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHMQDZ7U","created_at":"2026-07-05T09:10:10.064883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07235","citing_title":"FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29328","citing_title":"Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19899","citing_title":"A Reproducibility Study of Metacognitive Retrieval-Augmented Generation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU","json":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU.json","graph_json":"https://pith.science/api/pith-number/EHMQDZ7UQHJSIXYAIWQDETJ6DU/graph.json","events_json":"https://pith.science/api/pith-number/EHMQDZ7UQHJSIXYAIWQDETJ6DU/events.json","paper":"https://pith.science/paper/EHMQDZ7U"},"agent_actions":{"view_html":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU","download_json":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU.json","view_paper":"https://pith.science/paper/EHMQDZ7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13992&json=true","fetch_graph":"https://pith.science/api/pith-number/EHMQDZ7UQHJSIXYAIWQDETJ6DU/graph.json","fetch_events":"https://pith.science/api/pith-number/EHMQDZ7UQHJSIXYAIWQDETJ6DU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU/action/storage_attestation","attest_author":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU/action/author_attestation","sign_citation":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU/action/citation_signature","submit_replication":"https://pith.science/pith/EHMQDZ7UQHJSIXYAIWQDETJ6DU/action/replication_record"}},"created_at":"2026-07-05T09:10:10.064883+00:00","updated_at":"2026-07-05T09:10:10.064883+00:00"}