{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TAP4YWSKDXWYYBEBERBIEZZTUH","short_pith_number":"pith:TAP4YWSK","schema_version":"1.0","canonical_sha256":"981fcc5a4a1ded8c04812442826733a1fc4227f6c64b7a73f14e199c68408880","source":{"kind":"arxiv","id":"2605.27361","version":1},"attestation_state":"computed","paper":{"title":"Natural Language Query to Configuration for Retrieval Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Esha Choukse, Fiodar Kazhamiaka, Matei Zaharia, Mathew Jacob, Melissa Z. Pan, Negar Arabzadeh","submitted_at":"2026-05-26T17:58:47Z","abstract_excerpt":"Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping both answer quality and serving cost. Today, these pipelines are typically hand-tuned once per workload, leaving substantial per-query optimization untapped. We formulate the problem: given a natural-language query and either an accuracy or a budget target, select from a predefined pipeline catalog the configuration that minimizes cost or maximizes accuracy at inference time. We propose **BRANE**, which uses an LLM to convert each query into w"},"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":"2605.27361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T17:58:47Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"2a637c22d9ccbdcb9b5ef71b16d593d70d642c9c991028a22238e214f5de9c51","abstract_canon_sha256":"b7056f4c000a214e35241c6bf7bb792b95954c5bcd70dcccb7d1af083f7373c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:20.066913Z","signature_b64":"mGRiPxNSTKgOt9U5MhprpE3HJlGtFjAc4VTkGwjgTGR/TbDMHS6BnFDtxJ2HGkkpjggGTv623DRE1PfT06IJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"981fcc5a4a1ded8c04812442826733a1fc4227f6c64b7a73f14e199c68408880","last_reissued_at":"2026-05-27T02:06:20.066208Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:20.066208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural Language Query to Configuration for Retrieval Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Esha Choukse, Fiodar Kazhamiaka, Matei Zaharia, Mathew Jacob, Melissa Z. Pan, Negar Arabzadeh","submitted_at":"2026-05-26T17:58:47Z","abstract_excerpt":"Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping both answer quality and serving cost. Today, these pipelines are typically hand-tuned once per workload, leaving substantial per-query optimization untapped. We formulate the problem: given a natural-language query and either an accuracy or a budget target, select from a predefined pipeline catalog the configuration that minimizes cost or maximizes accuracy at inference time. We propose **BRANE**, which uses an LLM to convert each query into w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27361","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/2605.27361/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":"2605.27361","created_at":"2026-05-27T02:06:20.066327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27361v1","created_at":"2026-05-27T02:06:20.066327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27361","created_at":"2026-05-27T02:06:20.066327+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAP4YWSKDXWY","created_at":"2026-05-27T02:06:20.066327+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAP4YWSKDXWYYBEB","created_at":"2026-05-27T02:06:20.066327+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAP4YWSK","created_at":"2026-05-27T02:06:20.066327+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/TAP4YWSKDXWYYBEBERBIEZZTUH","json":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH.json","graph_json":"https://pith.science/api/pith-number/TAP4YWSKDXWYYBEBERBIEZZTUH/graph.json","events_json":"https://pith.science/api/pith-number/TAP4YWSKDXWYYBEBERBIEZZTUH/events.json","paper":"https://pith.science/paper/TAP4YWSK"},"agent_actions":{"view_html":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH","download_json":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH.json","view_paper":"https://pith.science/paper/TAP4YWSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27361&json=true","fetch_graph":"https://pith.science/api/pith-number/TAP4YWSKDXWYYBEBERBIEZZTUH/graph.json","fetch_events":"https://pith.science/api/pith-number/TAP4YWSKDXWYYBEBERBIEZZTUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH/action/storage_attestation","attest_author":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH/action/author_attestation","sign_citation":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH/action/citation_signature","submit_replication":"https://pith.science/pith/TAP4YWSKDXWYYBEBERBIEZZTUH/action/replication_record"}},"created_at":"2026-05-27T02:06:20.066327+00:00","updated_at":"2026-05-27T02:06:20.066327+00:00"}