{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GM6SEGDPLQ5IXOTCWKUXOODNBR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"268802378f6fa4648fa52a15271df3c253ef69c436825e649e6a859eb97028e1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-22T23:06:42Z","title_canon_sha256":"c9b8872cbb2de58b8d7557181fec4a8c6ae29631ae5451135c9e703703c49d30"},"schema_version":"1.0","source":{"id":"2404.14618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14618","created_at":"2026-07-05T08:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14618v1","created_at":"2026-07-05T08:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14618","created_at":"2026-07-05T08:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"GM6SEGDPLQ5I","created_at":"2026-07-05T08:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"GM6SEGDPLQ5IXOTC","created_at":"2026-07-05T08:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"GM6SEGDP","created_at":"2026-07-05T08:11:07Z"}],"graph_snapshots":[{"event_id":"sha256:91cce303fafef7842b751f33fdc09d0eec29b2f0493f76d351a29e736b80cde6","target":"graph","created_at":"2026-07-05T08:11:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.14618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e.g., edge) devices, tend to lag behind in terms of response quality. Therefore in this work we propose a hybrid inference approach which combines their respective strengths to save cost and maintain quality. Our approach uses a router that assigns queries to the small or large model based on the predicted query difficulty and the desired quality level. The desired quality level can be tuned dynamically at test ","authors_text":"Ahmed Hassan Awadallah, Ankur Mallick, Chi Wang, Dujian Ding, Laks V.S. Lakshmanan, Robert Sim, Subhabrata Mukherjee, Victor Ruhle","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-22T23:06:42Z","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14618","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c3e0b7cdb4338ddf4be48b8f9bf3ddc837edcf3146d5c2b115ceba2ea9a878c","target":"record","created_at":"2026-07-05T08:11:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"268802378f6fa4648fa52a15271df3c253ef69c436825e649e6a859eb97028e1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-22T23:06:42Z","title_canon_sha256":"c9b8872cbb2de58b8d7557181fec4a8c6ae29631ae5451135c9e703703c49d30"},"schema_version":"1.0","source":{"id":"2404.14618","kind":"arxiv","version":1}},"canonical_sha256":"333d22186f5c3a8bba62b2a977386d0c5b3d90f931cc8074d9ddbfe15c49b048","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"333d22186f5c3a8bba62b2a977386d0c5b3d90f931cc8074d9ddbfe15c49b048","first_computed_at":"2026-07-05T08:11:07.744778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:07.744778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wn+W4XGAqcjVzlq2Y9WLHjt+3NY80E6VNnN5bp/miwfwhx8xfUUBnOlEaxilZqOgE4cJdlBCg/aUT5mPe2ldCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:07.745300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.14618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c3e0b7cdb4338ddf4be48b8f9bf3ddc837edcf3146d5c2b115ceba2ea9a878c","sha256:91cce303fafef7842b751f33fdc09d0eec29b2f0493f76d351a29e736b80cde6"],"state_sha256":"da2b7edd9f3b9cb2fe1f14f1ea98cd3705542dfc78c9a2bd3d0f380972cbf961"}