{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5C7AUSEONIR5FYSPWEADX22SAE","short_pith_number":"pith:5C7AUSEO","schema_version":"1.0","canonical_sha256":"e8be0a488e6a23d2e24fb1003beb520133b0d5ab160bdd78a3680ed95aadaa05","source":{"kind":"arxiv","id":"2504.03444","version":2},"attestation_state":"computed","paper":{"title":"LLMSched: Uncertainty-Aware Workload Scheduling for Compound LLM Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Botao Zhu, Chen Chen, Xiaoyi Fan, Yifei Zhu","submitted_at":"2025-04-04T13:37:29Z","abstract_excerpt":"Developing compound Large Language Model (LLM) applications is becoming an increasingly prevalent approach to solving real-world problems. In these applications, an LLM collaborates with various external modules, including APIs and even other LLMs, to realize complex intelligent services. However, we reveal that the intrinsic duration and structural uncertainty in compound LLM applications pose great challenges for LLM service providers in serving and scheduling them efficiently. In this paper, we propose LLMSched, an uncertainty-aware scheduling framework for emerging compound LLM application"},"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":"2504.03444","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-04T13:37:29Z","cross_cats_sorted":[],"title_canon_sha256":"d75aa9e8f79b257072a046dca8e5e2a06409e13e8c88708d67c3f002fec7067c","abstract_canon_sha256":"fac4985cfb6291976f0dc89cb808911a6797c542a8a9a9b7fc3bdbb212c02d91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:21.183503Z","signature_b64":"Z2iCGuKmuBAI+/SVsqzqvl2DfeGZHo8qDNDL9UxxwQtbJaqKNtA5BIiK9JI436snzW21Tdmo7fNQzaOvR1rWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8be0a488e6a23d2e24fb1003beb520133b0d5ab160bdd78a3680ed95aadaa05","last_reissued_at":"2026-07-05T10:45:21.182963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:21.182963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMSched: Uncertainty-Aware Workload Scheduling for Compound LLM Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Botao Zhu, Chen Chen, Xiaoyi Fan, Yifei Zhu","submitted_at":"2025-04-04T13:37:29Z","abstract_excerpt":"Developing compound Large Language Model (LLM) applications is becoming an increasingly prevalent approach to solving real-world problems. In these applications, an LLM collaborates with various external modules, including APIs and even other LLMs, to realize complex intelligent services. However, we reveal that the intrinsic duration and structural uncertainty in compound LLM applications pose great challenges for LLM service providers in serving and scheduling them efficiently. In this paper, we propose LLMSched, an uncertainty-aware scheduling framework for emerging compound LLM application"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03444","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/2504.03444/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":"2504.03444","created_at":"2026-07-05T10:45:21.183034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03444v2","created_at":"2026-07-05T10:45:21.183034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03444","created_at":"2026-07-05T10:45:21.183034+00:00"},{"alias_kind":"pith_short_12","alias_value":"5C7AUSEONIR5","created_at":"2026-07-05T10:45:21.183034+00:00"},{"alias_kind":"pith_short_16","alias_value":"5C7AUSEONIR5FYSP","created_at":"2026-07-05T10:45:21.183034+00:00"},{"alias_kind":"pith_short_8","alias_value":"5C7AUSEO","created_at":"2026-07-05T10:45:21.183034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02025","citing_title":"Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Scheduling","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE","json":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE.json","graph_json":"https://pith.science/api/pith-number/5C7AUSEONIR5FYSPWEADX22SAE/graph.json","events_json":"https://pith.science/api/pith-number/5C7AUSEONIR5FYSPWEADX22SAE/events.json","paper":"https://pith.science/paper/5C7AUSEO"},"agent_actions":{"view_html":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE","download_json":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE.json","view_paper":"https://pith.science/paper/5C7AUSEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03444&json=true","fetch_graph":"https://pith.science/api/pith-number/5C7AUSEONIR5FYSPWEADX22SAE/graph.json","fetch_events":"https://pith.science/api/pith-number/5C7AUSEONIR5FYSPWEADX22SAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE/action/storage_attestation","attest_author":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE/action/author_attestation","sign_citation":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE/action/citation_signature","submit_replication":"https://pith.science/pith/5C7AUSEONIR5FYSPWEADX22SAE/action/replication_record"}},"created_at":"2026-07-05T10:45:21.183034+00:00","updated_at":"2026-07-05T10:45:21.183034+00:00"}