{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O5SRPBHEWLWMYXTGWJAACCTKMH","short_pith_number":"pith:O5SRPBHE","schema_version":"1.0","canonical_sha256":"77651784e4b2eccc5e66b240010a6a61cabd5dccda8801b6da48c1e960c2c2f8","source":{"kind":"arxiv","id":"2606.02581","version":1},"attestation_state":"computed","paper":{"title":"Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Sanjay Mishra","submitted_at":"2026-03-26T02:53:39Z","abstract_excerpt":"Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and end-to-end latency. Static retrieval configurations cannot resolve this tension across heterogeneous query workloads -- simple definitional queries waste budget on unnecessary context, while complex analytical prompts are underserved by shallow retrieval. This paper introduces \\emph{Cost-Aware RAG} (CA-RAG), a per-query routing framework that selects from a discrete catalog of \\emph{strategy bundles} -- each coupling a retrieval depth (from retrie"},"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":"2606.02581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-03-26T02:53:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0c9b061b9cc5ebc43067d2ae66f0668fa5229859df509fc50b9a6e93202b611","abstract_canon_sha256":"a88e38454eed02c30fe3b8e74bd5f75329eb040f2aa50c363cb20a9de901decb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T00:05:03.700911Z","signature_b64":"W4Ex8Q5/fkDjVp8tdx+UBHYLBLRCrxJXHIJViDtIdzvduLt3eiSUo0p6ULIO3c1y5+Vqd4amLdUs24Mx9UGIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77651784e4b2eccc5e66b240010a6a61cabd5dccda8801b6da48c1e960c2c2f8","last_reissued_at":"2026-06-03T00:05:03.700406Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T00:05:03.700406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Sanjay Mishra","submitted_at":"2026-03-26T02:53:39Z","abstract_excerpt":"Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and end-to-end latency. Static retrieval configurations cannot resolve this tension across heterogeneous query workloads -- simple definitional queries waste budget on unnecessary context, while complex analytical prompts are underserved by shallow retrieval. This paper introduces \\emph{Cost-Aware RAG} (CA-RAG), a per-query routing framework that selects from a discrete catalog of \\emph{strategy bundles} -- each coupling a retrieval depth (from retrie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02581","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/2606.02581/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":"2606.02581","created_at":"2026-06-03T00:05:03.700466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02581v1","created_at":"2026-06-03T00:05:03.700466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02581","created_at":"2026-06-03T00:05:03.700466+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5SRPBHEWLWM","created_at":"2026-06-03T00:05:03.700466+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5SRPBHEWLWMYXTG","created_at":"2026-06-03T00:05:03.700466+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5SRPBHE","created_at":"2026-06-03T00:05:03.700466+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/O5SRPBHEWLWMYXTGWJAACCTKMH","json":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH.json","graph_json":"https://pith.science/api/pith-number/O5SRPBHEWLWMYXTGWJAACCTKMH/graph.json","events_json":"https://pith.science/api/pith-number/O5SRPBHEWLWMYXTGWJAACCTKMH/events.json","paper":"https://pith.science/paper/O5SRPBHE"},"agent_actions":{"view_html":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH","download_json":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH.json","view_paper":"https://pith.science/paper/O5SRPBHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02581&json=true","fetch_graph":"https://pith.science/api/pith-number/O5SRPBHEWLWMYXTGWJAACCTKMH/graph.json","fetch_events":"https://pith.science/api/pith-number/O5SRPBHEWLWMYXTGWJAACCTKMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH/action/storage_attestation","attest_author":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH/action/author_attestation","sign_citation":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH/action/citation_signature","submit_replication":"https://pith.science/pith/O5SRPBHEWLWMYXTGWJAACCTKMH/action/replication_record"}},"created_at":"2026-06-03T00:05:03.700466+00:00","updated_at":"2026-06-03T00:05:03.700466+00:00"}