{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JOXOJ3SDS4TX6XEI4YWBWRLGXD","short_pith_number":"pith:JOXOJ3SD","schema_version":"1.0","canonical_sha256":"4baee4ee4397277f5c88e62c1b4566b8f997d4c53bc6ee2bc27067a52685e0a5","source":{"kind":"arxiv","id":"2411.11560","version":1},"attestation_state":"computed","paper":{"title":"Topology-aware Preemptive Scheduling for Co-located LLM Workloads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Jinjie Yang, Lei Su, Ping Zhang, Xin Chen","submitted_at":"2024-11-18T13:26:09Z","abstract_excerpt":"Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-location of batch jobs to fulfill resource valleys between successive peaks, and thus to saturate resource allocation in cluster-wide scope. These heterogeneous workloads often have different business priorities, and therefore preemption can be leveraged for resource elasticity. However, workloads often have distinct topology preferences as well. The resources released by lower-priori"},"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":"2411.11560","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-18T13:26:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b6ca83b40f6715977de0c95a77ce619507a79cce2c040f2509721d5010682ae2","abstract_canon_sha256":"394aacdd27e14612cdf366293f1995e8211d1116704daa67a29982e0da95a571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:57.938149Z","signature_b64":"EcJICvcoLbt2h2UkBeyGHDzYYNShZ9qHnUtjI7m0NI/DEGBLJo6BnvP5cy5rHznVVNPmVLLXl7oX6Pjr4IDVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4baee4ee4397277f5c88e62c1b4566b8f997d4c53bc6ee2bc27067a52685e0a5","last_reissued_at":"2026-07-05T09:36:57.937792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:57.937792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topology-aware Preemptive Scheduling for Co-located LLM Workloads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Jinjie Yang, Lei Su, Ping Zhang, Xin Chen","submitted_at":"2024-11-18T13:26:09Z","abstract_excerpt":"Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-location of batch jobs to fulfill resource valleys between successive peaks, and thus to saturate resource allocation in cluster-wide scope. These heterogeneous workloads often have different business priorities, and therefore preemption can be leveraged for resource elasticity. However, workloads often have distinct topology preferences as well. The resources released by lower-priori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11560","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/2411.11560/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":"2411.11560","created_at":"2026-07-05T09:36:57.937845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11560v1","created_at":"2026-07-05T09:36:57.937845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11560","created_at":"2026-07-05T09:36:57.937845+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOXOJ3SDS4TX","created_at":"2026-07-05T09:36:57.937845+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOXOJ3SDS4TX6XEI","created_at":"2026-07-05T09:36:57.937845+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOXOJ3SD","created_at":"2026-07-05T09:36:57.937845+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/JOXOJ3SDS4TX6XEI4YWBWRLGXD","json":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD.json","graph_json":"https://pith.science/api/pith-number/JOXOJ3SDS4TX6XEI4YWBWRLGXD/graph.json","events_json":"https://pith.science/api/pith-number/JOXOJ3SDS4TX6XEI4YWBWRLGXD/events.json","paper":"https://pith.science/paper/JOXOJ3SD"},"agent_actions":{"view_html":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD","download_json":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD.json","view_paper":"https://pith.science/paper/JOXOJ3SD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11560&json=true","fetch_graph":"https://pith.science/api/pith-number/JOXOJ3SDS4TX6XEI4YWBWRLGXD/graph.json","fetch_events":"https://pith.science/api/pith-number/JOXOJ3SDS4TX6XEI4YWBWRLGXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD/action/storage_attestation","attest_author":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD/action/author_attestation","sign_citation":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD/action/citation_signature","submit_replication":"https://pith.science/pith/JOXOJ3SDS4TX6XEI4YWBWRLGXD/action/replication_record"}},"created_at":"2026-07-05T09:36:57.937845+00:00","updated_at":"2026-07-05T09:36:57.937845+00:00"}