{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZDTF25ZBYKCISMSKB43Q6HS6P","short_pith_number":"pith:TZDTF25Z","schema_version":"1.0","canonical_sha256":"9e4732ebb90e142449925079b878f2f3ebbd5bd84e685e378fab6bbb2936f8a1","source":{"kind":"arxiv","id":"2411.09837","version":2},"attestation_state":"computed","paper":{"title":"Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Ahmed E. Hassan, Dayi Lin, Kirill Vasilevski","submitted_at":"2024-11-14T23:02:30Z","abstract_excerpt":"To balance the quality and inference cost of a Foundation Model (FM, such as large language models (LLMs)) powered software, people often opt to train a routing model that routes requests to FMs with different sizes and capabilities. Existing routing models rely on learning the optimal routing decision from carefully curated data, require complex computations to be updated, and do not consider the potential evolution of weaker FMs. In this paper, we propose Real-time Adaptive Routing (RAR), an approach to continuously adapt FM routing decisions while using guided in-context learning to enhance"},"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":"2411.09837","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T23:02:30Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"4156e0c51a5b980524bc5e277907cc5865034ff596f78272f1fc48fce10a3dcd","abstract_canon_sha256":"d66f55bfde9540d88014b53dc7aefc718453d0f3eed7f5bf97cf0d8269e1403f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:59.857077Z","signature_b64":"VmJw0wo3OrQN5pseNLq5tqtv4Saz0Fgscd4YuehNcv8uzYRt7YMcc3R9mye7UjnLCnOhjzdIbTnm03H+/Hh3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e4732ebb90e142449925079b878f2f3ebbd5bd84e685e378fab6bbb2936f8a1","last_reissued_at":"2026-07-05T11:13:59.856562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:59.856562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Ahmed E. Hassan, Dayi Lin, Kirill Vasilevski","submitted_at":"2024-11-14T23:02:30Z","abstract_excerpt":"To balance the quality and inference cost of a Foundation Model (FM, such as large language models (LLMs)) powered software, people often opt to train a routing model that routes requests to FMs with different sizes and capabilities. Existing routing models rely on learning the optimal routing decision from carefully curated data, require complex computations to be updated, and do not consider the potential evolution of weaker FMs. In this paper, we propose Real-time Adaptive Routing (RAR), an approach to continuously adapt FM routing decisions while using guided in-context learning to enhance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09837","kind":"arxiv","version":2},"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/2411.09837/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":"2411.09837","created_at":"2026-07-05T11:13:59.856638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09837v2","created_at":"2026-07-05T11:13:59.856638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09837","created_at":"2026-07-05T11:13:59.856638+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZDTF25ZBYKC","created_at":"2026-07-05T11:13:59.856638+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZDTF25ZBYKCISMS","created_at":"2026-07-05T11:13:59.856638+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZDTF25Z","created_at":"2026-07-05T11:13:59.856638+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/TZDTF25ZBYKCISMSKB43Q6HS6P","json":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P.json","graph_json":"https://pith.science/api/pith-number/TZDTF25ZBYKCISMSKB43Q6HS6P/graph.json","events_json":"https://pith.science/api/pith-number/TZDTF25ZBYKCISMSKB43Q6HS6P/events.json","paper":"https://pith.science/paper/TZDTF25Z"},"agent_actions":{"view_html":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P","download_json":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P.json","view_paper":"https://pith.science/paper/TZDTF25Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09837&json=true","fetch_graph":"https://pith.science/api/pith-number/TZDTF25ZBYKCISMSKB43Q6HS6P/graph.json","fetch_events":"https://pith.science/api/pith-number/TZDTF25ZBYKCISMSKB43Q6HS6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P/action/storage_attestation","attest_author":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P/action/author_attestation","sign_citation":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P/action/citation_signature","submit_replication":"https://pith.science/pith/TZDTF25ZBYKCISMSKB43Q6HS6P/action/replication_record"}},"created_at":"2026-07-05T11:13:59.856638+00:00","updated_at":"2026-07-05T11:13:59.856638+00:00"}