{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUSHDWQL5TT6B3X6HTDYYZ3WUF","short_pith_number":"pith:NUSHDWQL","schema_version":"1.0","canonical_sha256":"6d2471da0bece7e0eefe3cc78c6776a1567e97bb7539ec271f3e532d076563eb","source":{"kind":"arxiv","id":"2608.08237","version":1},"attestation_state":"computed","paper":{"title":"SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DC","cs.IR"],"primary_cat":"cs.LG","authors_text":"Muhammad Faizan Raza, Satish Mahadevan Srinivasan, Shuo (Luna) Yang","submitted_at":"2026-08-08T17:05:36Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems in production operate under strict service level objectives (SLOs) on tail latency and infrastructure cost. However, standard retrieval pipelines rely on fixed retrieval budgets that ignore query difficulty, over-retrieving for easy queries and under-serving hard ones, forcing operators to trade answer quality against SLO compliance. This paper proposes SAGE, a learned SLO-aware adaptive retrieval policy that dynamically selects the number of passages k per query. SAGE uses lightweight features derived from initial retrieval (e.g., score distributio"},"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":"2608.08237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-08T17:05:36Z","cross_cats_sorted":["cs.CL","cs.DC","cs.IR"],"title_canon_sha256":"85c711add1b8a0380c69f4644137c650502fe0d53b8236958ffe8db4debce900","abstract_canon_sha256":"995f865851f6c00f79224bca152897cc95d45db69e92123b3924dfa85d77be0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:05.718157Z","signature_b64":"MNBAMtti3pZK+Kt3QPVgXEzfnQW1iiiSCc+wm/N80lvlPRwHsTWz+QoKyM+gfWEGiy0+P7TNgF7vGP3u/QwmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d2471da0bece7e0eefe3cc78c6776a1567e97bb7539ec271f3e532d076563eb","last_reissued_at":"2026-08-11T01:22:05.715628Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:05.715628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DC","cs.IR"],"primary_cat":"cs.LG","authors_text":"Muhammad Faizan Raza, Satish Mahadevan Srinivasan, Shuo (Luna) Yang","submitted_at":"2026-08-08T17:05:36Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems in production operate under strict service level objectives (SLOs) on tail latency and infrastructure cost. However, standard retrieval pipelines rely on fixed retrieval budgets that ignore query difficulty, over-retrieving for easy queries and under-serving hard ones, forcing operators to trade answer quality against SLO compliance. This paper proposes SAGE, a learned SLO-aware adaptive retrieval policy that dynamically selects the number of passages k per query. SAGE uses lightweight features derived from initial retrieval (e.g., score distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08237","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/2608.08237/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":"2608.08237","created_at":"2026-08-11T01:22:05.716482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08237v1","created_at":"2026-08-11T01:22:05.716482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08237","created_at":"2026-08-11T01:22:05.716482+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUSHDWQL5TT6","created_at":"2026-08-11T01:22:05.716482+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUSHDWQL5TT6B3X6","created_at":"2026-08-11T01:22:05.716482+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUSHDWQL","created_at":"2026-08-11T01:22:05.716482+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/NUSHDWQL5TT6B3X6HTDYYZ3WUF","json":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF.json","graph_json":"https://pith.science/api/pith-number/NUSHDWQL5TT6B3X6HTDYYZ3WUF/graph.json","events_json":"https://pith.science/api/pith-number/NUSHDWQL5TT6B3X6HTDYYZ3WUF/events.json","paper":"https://pith.science/paper/NUSHDWQL"},"agent_actions":{"view_html":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF","download_json":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF.json","view_paper":"https://pith.science/paper/NUSHDWQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08237&json=true","fetch_graph":"https://pith.science/api/pith-number/NUSHDWQL5TT6B3X6HTDYYZ3WUF/graph.json","fetch_events":"https://pith.science/api/pith-number/NUSHDWQL5TT6B3X6HTDYYZ3WUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF/action/storage_attestation","attest_author":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF/action/author_attestation","sign_citation":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF/action/citation_signature","submit_replication":"https://pith.science/pith/NUSHDWQL5TT6B3X6HTDYYZ3WUF/action/replication_record"}},"created_at":"2026-08-11T01:22:05.716482+00:00","updated_at":"2026-08-11T01:22:05.716482+00:00"}