{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SCKWSDFRL4P5H7GZ526FVX2FSN","short_pith_number":"pith:SCKWSDFR","schema_version":"1.0","canonical_sha256":"9095690cb15f1fd3fcd9eebc5adf45935b7a196c3290054c5161cc8d9ae373b2","source":{"kind":"arxiv","id":"2603.07770","version":2},"attestation_state":"computed","paper":{"title":"ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ArcLight achieves up to 46% higher LLM inference throughput on many-core CPUs by reducing cross-NUMA memory access overhead.","cross_cats":["cs.CL"],"primary_cat":"cs.DC","authors_text":"Wanxiang Che, Xu Han, Yuxuan Li, Yuzhuang Xu","submitted_at":"2026-03-08T19:20:25Z","abstract_excerpt":"Although existing frameworks for large language model (LLM) inference on CPUs are mature, they fail to fully exploit the computation potential of many-core CPU platforms. Many-core CPUs are widely deployed in web servers and high-end networking devices, and are typically organized into multiple NUMA nodes that group cores and memory. Current frameworks largely overlook the substantial overhead of cross-NUMA memory access, limiting inference scalability and intelligence enabling on such platforms. To address this limitation, we build ArcLight, a lightweight LLM inference architecture designed f"},"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":true},"canonical_record":{"source":{"id":"2603.07770","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-03-08T19:20:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"de3ee42c336be9f1c0388fd8927ce1400360eaf62d0d6c4152fddcb89492d115","abstract_canon_sha256":"02a41d23caec35c01cb1b6d0217851f0a3d956ddab321608b8f99480cd219915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:30.859872Z","signature_b64":"ppMtAdYokdb3FzvdrEicGgTJWBnl47AQGMMuPLwInflDOUMfYLmKl6CRqHdsUQ5HHfe4q0Z0wjlQqG2ESviKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9095690cb15f1fd3fcd9eebc5adf45935b7a196c3290054c5161cc8d9ae373b2","last_reissued_at":"2026-05-18T02:44:30.859438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:30.859438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ArcLight achieves up to 46% higher LLM inference throughput on many-core CPUs by reducing cross-NUMA memory access overhead.","cross_cats":["cs.CL"],"primary_cat":"cs.DC","authors_text":"Wanxiang Che, Xu Han, Yuxuan Li, Yuzhuang Xu","submitted_at":"2026-03-08T19:20:25Z","abstract_excerpt":"Although existing frameworks for large language model (LLM) inference on CPUs are mature, they fail to fully exploit the computation potential of many-core CPU platforms. Many-core CPUs are widely deployed in web servers and high-end networking devices, and are typically organized into multiple NUMA nodes that group cores and memory. Current frameworks largely overlook the substantial overhead of cross-NUMA memory access, limiting inference scalability and intelligence enabling on such platforms. To address this limitation, we build ArcLight, a lightweight LLM inference architecture designed f"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results show that ArcLight significantly surpasses the performance ceiling of mainstream frameworks, achieving up to 46% higher inference throughput.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that cross-NUMA memory access is the dominant scalability bottleneck on many-core CPUs and that the proposed memory management and tensor parallelism will generalize without major tuning across different CPU models and workloads.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ArcLight delivers up to 46% higher LLM inference throughput on many-core CPUs by addressing cross-NUMA memory access costs through efficient memory management, thread scheduling, and tensor parallelism.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ArcLight achieves up to 46% higher LLM inference throughput on many-core CPUs by reducing cross-NUMA memory access overhead.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a45589c49072c820dee5bf3a5a6d6a8863a59fa7555febe75c5c2a46a0589e54"},"source":{"id":"2603.07770","kind":"arxiv","version":2},"verdict":{"id":"41e0a5b9-8921-4190-95c5-8a8b9fc6ca18","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:38:44.706082Z","strongest_claim":"Experimental results show that ArcLight significantly surpasses the performance ceiling of mainstream frameworks, achieving up to 46% higher inference throughput.","one_line_summary":"ArcLight delivers up to 46% higher LLM inference throughput on many-core CPUs by addressing cross-NUMA memory access costs through efficient memory management, thread scheduling, and tensor parallelism.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that cross-NUMA memory access is the dominant scalability bottleneck on many-core CPUs and that the proposed memory management and tensor parallelism will generalize without major tuning across different CPU models and workloads.","pith_extraction_headline":"ArcLight achieves up to 46% higher LLM inference throughput on many-core CPUs by reducing cross-NUMA memory access overhead."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"dcfd7ceea22ed4b42af8d2b5e1dbb8cf7d79f41e3e3c8c441c60e8ca9c2e77ca"},"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":"2603.07770","created_at":"2026-05-18T02:44:30.859495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.07770v2","created_at":"2026-05-18T02:44:30.859495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07770","created_at":"2026-05-18T02:44:30.859495+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCKWSDFRL4P5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCKWSDFRL4P5H7GZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCKWSDFR","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN","json":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN.json","graph_json":"https://pith.science/api/pith-number/SCKWSDFRL4P5H7GZ526FVX2FSN/graph.json","events_json":"https://pith.science/api/pith-number/SCKWSDFRL4P5H7GZ526FVX2FSN/events.json","paper":"https://pith.science/paper/SCKWSDFR"},"agent_actions":{"view_html":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN","download_json":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN.json","view_paper":"https://pith.science/paper/SCKWSDFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.07770&json=true","fetch_graph":"https://pith.science/api/pith-number/SCKWSDFRL4P5H7GZ526FVX2FSN/graph.json","fetch_events":"https://pith.science/api/pith-number/SCKWSDFRL4P5H7GZ526FVX2FSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN/action/storage_attestation","attest_author":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN/action/author_attestation","sign_citation":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN/action/citation_signature","submit_replication":"https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN/action/replication_record"}},"created_at":"2026-05-18T02:44:30.859495+00:00","updated_at":"2026-05-18T02:44:30.859495+00:00"}