{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:INECM3GUU23EUR36Y3M4YRRSAA","short_pith_number":"pith:INECM3GU","schema_version":"1.0","canonical_sha256":"4348266cd4a6b64a477ec6d9cc4632000eb75ea8d35e290e089d748e13b3ed74","source":{"kind":"arxiv","id":"2411.07396","version":1},"attestation_state":"computed","paper":{"title":"Toward Optimal Search and Retrieval for RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandria Leto, Cecilia Aguerrebere, Ishwar Bhati, Mariano Tepper, Ted Willke, Vy Ai Vo","submitted_at":"2024-11-11T22:06:51Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a promising method for addressing some of the memory-related challenges associated with Large Language Models (LLMs). Two separate systems form the RAG pipeline, the retriever and the reader, and the impact of each on downstream task performance is not well-understood. Here, we work towards the goal of understanding how retrievers can be optimized for RAG pipelines for common tasks such as Question Answering (QA). We conduct experiments focused on the relationship between retrieval and RAG performance on QA and attributed QA and unveil a number of insigh"},"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":"2411.07396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T22:06:51Z","cross_cats_sorted":[],"title_canon_sha256":"6a2d2c8d9ebf220fc1df69e5c80edf31b49a879ebfc06c506ae21bba6fafcb83","abstract_canon_sha256":"27b1b283152f29e7b540d03c7aa4dd1b49fd10e34acaff78927077905bc0856f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:03.035462Z","signature_b64":"bN5XXFCdGWoVKj/LUUxn5tgR6UEMFQipu9uxSE9izdycbmFVzibj56IKafks1urCFTBwFsdiNacS4w1Q6YGXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4348266cd4a6b64a477ec6d9cc4632000eb75ea8d35e290e089d748e13b3ed74","last_reissued_at":"2026-07-05T09:34:03.034394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:03.034394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Optimal Search and Retrieval for RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandria Leto, Cecilia Aguerrebere, Ishwar Bhati, Mariano Tepper, Ted Willke, Vy Ai Vo","submitted_at":"2024-11-11T22:06:51Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a promising method for addressing some of the memory-related challenges associated with Large Language Models (LLMs). Two separate systems form the RAG pipeline, the retriever and the reader, and the impact of each on downstream task performance is not well-understood. Here, we work towards the goal of understanding how retrievers can be optimized for RAG pipelines for common tasks such as Question Answering (QA). We conduct experiments focused on the relationship between retrieval and RAG performance on QA and attributed QA and unveil a number of insigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07396","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/2411.07396/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":"2411.07396","created_at":"2026-07-05T09:34:03.034974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07396v1","created_at":"2026-07-05T09:34:03.034974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07396","created_at":"2026-07-05T09:34:03.034974+00:00"},{"alias_kind":"pith_short_12","alias_value":"INECM3GUU23E","created_at":"2026-07-05T09:34:03.034974+00:00"},{"alias_kind":"pith_short_16","alias_value":"INECM3GUU23EUR36","created_at":"2026-07-05T09:34:03.034974+00:00"},{"alias_kind":"pith_short_8","alias_value":"INECM3GU","created_at":"2026-07-05T09:34:03.034974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04522","citing_title":"ANN Search: Recall What Matters","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13666","citing_title":"Automatically Inferring Teachers' Geometric Content Knowledge: A Skills Based Approach","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA","json":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA.json","graph_json":"https://pith.science/api/pith-number/INECM3GUU23EUR36Y3M4YRRSAA/graph.json","events_json":"https://pith.science/api/pith-number/INECM3GUU23EUR36Y3M4YRRSAA/events.json","paper":"https://pith.science/paper/INECM3GU"},"agent_actions":{"view_html":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA","download_json":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA.json","view_paper":"https://pith.science/paper/INECM3GU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07396&json=true","fetch_graph":"https://pith.science/api/pith-number/INECM3GUU23EUR36Y3M4YRRSAA/graph.json","fetch_events":"https://pith.science/api/pith-number/INECM3GUU23EUR36Y3M4YRRSAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA/action/storage_attestation","attest_author":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA/action/author_attestation","sign_citation":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA/action/citation_signature","submit_replication":"https://pith.science/pith/INECM3GUU23EUR36Y3M4YRRSAA/action/replication_record"}},"created_at":"2026-07-05T09:34:03.034974+00:00","updated_at":"2026-07-05T09:34:03.034974+00:00"}