{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RLQGKPNABFAYRP7MMPII5LB6NP","short_pith_number":"pith:RLQGKPNA","schema_version":"1.0","canonical_sha256":"8ae0653da0094188bfec63d08eac3e6bff27b5920206cd14eb0013109f0b1a6d","source":{"kind":"arxiv","id":"2508.03258","version":1},"attestation_state":"computed","paper":{"title":"SmartLLMs Scheduler: A Framework for Cost-Effective LLMs Utilization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Yuantian Miao, Yueyue Liu","submitted_at":"2025-08-05T09:35:52Z","abstract_excerpt":"Large Language Models (LLMs) such as GPT-4 and Llama have shown remarkable capabilities in a variety of software engineering tasks. Despite the advancements, their practical deployment faces challenges, including high financial costs, long response time, and varying performance, especially when handling a large number of queries (jobs). Existing optimization strategies for deploying LLMs for diverse tasks focus on static scheduling, which requires extensive training data for performance prediction, increasing the computational costs and limiting the applicability and flexibility. In this paper"},"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":"2508.03258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-08-05T09:35:52Z","cross_cats_sorted":[],"title_canon_sha256":"e605b33990e8f23ece45f2dbb7e972fe972f53527f177d8af82ceb7870c0208d","abstract_canon_sha256":"b398c640a6f6bad2df543cdb0d672391af021f9fcef5d22de2b474feb43fcc73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:52.736576Z","signature_b64":"/WcTCHjrmlmTLTM+0K5RWyYG3EVQJ1EyMId7x6YES7k+IcbU4Yi1A/hQ95L7zvvf1xKXXwthgz2k+oAP/BQVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ae0653da0094188bfec63d08eac3e6bff27b5920206cd14eb0013109f0b1a6d","last_reissued_at":"2026-07-05T11:48:52.736072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:52.736072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmartLLMs Scheduler: A Framework for Cost-Effective LLMs Utilization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Yuantian Miao, Yueyue Liu","submitted_at":"2025-08-05T09:35:52Z","abstract_excerpt":"Large Language Models (LLMs) such as GPT-4 and Llama have shown remarkable capabilities in a variety of software engineering tasks. Despite the advancements, their practical deployment faces challenges, including high financial costs, long response time, and varying performance, especially when handling a large number of queries (jobs). Existing optimization strategies for deploying LLMs for diverse tasks focus on static scheduling, which requires extensive training data for performance prediction, increasing the computational costs and limiting the applicability and flexibility. In this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03258","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/2508.03258/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":"2508.03258","created_at":"2026-07-05T11:48:52.736131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03258v1","created_at":"2026-07-05T11:48:52.736131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03258","created_at":"2026-07-05T11:48:52.736131+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLQGKPNABFAY","created_at":"2026-07-05T11:48:52.736131+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLQGKPNABFAYRP7M","created_at":"2026-07-05T11:48:52.736131+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLQGKPNA","created_at":"2026-07-05T11:48:52.736131+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/RLQGKPNABFAYRP7MMPII5LB6NP","json":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP.json","graph_json":"https://pith.science/api/pith-number/RLQGKPNABFAYRP7MMPII5LB6NP/graph.json","events_json":"https://pith.science/api/pith-number/RLQGKPNABFAYRP7MMPII5LB6NP/events.json","paper":"https://pith.science/paper/RLQGKPNA"},"agent_actions":{"view_html":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP","download_json":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP.json","view_paper":"https://pith.science/paper/RLQGKPNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03258&json=true","fetch_graph":"https://pith.science/api/pith-number/RLQGKPNABFAYRP7MMPII5LB6NP/graph.json","fetch_events":"https://pith.science/api/pith-number/RLQGKPNABFAYRP7MMPII5LB6NP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP/action/storage_attestation","attest_author":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP/action/author_attestation","sign_citation":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP/action/citation_signature","submit_replication":"https://pith.science/pith/RLQGKPNABFAYRP7MMPII5LB6NP/action/replication_record"}},"created_at":"2026-07-05T11:48:52.736131+00:00","updated_at":"2026-07-05T11:48:52.736131+00:00"}