{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O5KSVDFGSCLZ3JGRVGHTUDXYYO","short_pith_number":"pith:O5KSVDFG","schema_version":"1.0","canonical_sha256":"77552a8ca690979da4d1a98f3a0ef8c3943f76c89420ed0b2e285187bd479867","source":{"kind":"arxiv","id":"2605.28268","version":1},"attestation_state":"computed","paper":{"title":"Towards Cost-effective LLMs Routing with Batch Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Haotian Xu, Jiadong Xie, Kangfei Zhao","submitted_at":"2026-05-27T10:14:46Z","abstract_excerpt":"Large Language Model (LLM) serving systems must balance task performance against monetary cost. Two prominent optimization techniques have emerged independently: LLM routing, which directs each query to the most cost-effective model in a model pool, and batch prompting, which packs multiple queries into a single invocation to amortize the fixed cost of the shared system prompt. These two techniques are logically complementary; i.e., routing optimizes the model assignment dimension while batching optimizes the query aggregation dimension, jointly reshaping the landscape of model utility and mon"},"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":"2605.28268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-27T10:14:46Z","cross_cats_sorted":[],"title_canon_sha256":"d89a40db1774a8121b22f72e647bc81b76e28c0fe0587ac50b8a90e05d97f1ec","abstract_canon_sha256":"0d783e7435b9c165a4d3a926135fad7c9d8798df926051a9cda990b81c3706bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:04.672915Z","signature_b64":"5WUED8b40os5IpOG2UHUOr+ojJE9E5dOtuBh+WqDRKjh4ieLKLGsY2nfBIU/5fM9fn1uMmTBkT+PBOrJMByKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77552a8ca690979da4d1a98f3a0ef8c3943f76c89420ed0b2e285187bd479867","last_reissued_at":"2026-05-28T01:05:04.672447Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:04.672447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Cost-effective LLMs Routing with Batch Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Haotian Xu, Jiadong Xie, Kangfei Zhao","submitted_at":"2026-05-27T10:14:46Z","abstract_excerpt":"Large Language Model (LLM) serving systems must balance task performance against monetary cost. Two prominent optimization techniques have emerged independently: LLM routing, which directs each query to the most cost-effective model in a model pool, and batch prompting, which packs multiple queries into a single invocation to amortize the fixed cost of the shared system prompt. These two techniques are logically complementary; i.e., routing optimizes the model assignment dimension while batching optimizes the query aggregation dimension, jointly reshaping the landscape of model utility and mon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28268","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/2605.28268/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":"2605.28268","created_at":"2026-05-28T01:05:04.672515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28268v1","created_at":"2026-05-28T01:05:04.672515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28268","created_at":"2026-05-28T01:05:04.672515+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5KSVDFGSCLZ","created_at":"2026-05-28T01:05:04.672515+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5KSVDFGSCLZ3JGR","created_at":"2026-05-28T01:05:04.672515+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5KSVDFG","created_at":"2026-05-28T01:05:04.672515+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/O5KSVDFGSCLZ3JGRVGHTUDXYYO","json":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO.json","graph_json":"https://pith.science/api/pith-number/O5KSVDFGSCLZ3JGRVGHTUDXYYO/graph.json","events_json":"https://pith.science/api/pith-number/O5KSVDFGSCLZ3JGRVGHTUDXYYO/events.json","paper":"https://pith.science/paper/O5KSVDFG"},"agent_actions":{"view_html":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO","download_json":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO.json","view_paper":"https://pith.science/paper/O5KSVDFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28268&json=true","fetch_graph":"https://pith.science/api/pith-number/O5KSVDFGSCLZ3JGRVGHTUDXYYO/graph.json","fetch_events":"https://pith.science/api/pith-number/O5KSVDFGSCLZ3JGRVGHTUDXYYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO/action/storage_attestation","attest_author":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO/action/author_attestation","sign_citation":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO/action/citation_signature","submit_replication":"https://pith.science/pith/O5KSVDFGSCLZ3JGRVGHTUDXYYO/action/replication_record"}},"created_at":"2026-05-28T01:05:04.672515+00:00","updated_at":"2026-05-28T01:05:04.672515+00:00"}