{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GFHD7S67HAJVTWHOC6ZXCMWPHZ","short_pith_number":"pith:GFHD7S67","schema_version":"1.0","canonical_sha256":"314e3fcbdf381359d8ee17b37132cf3e6aba6ae1f88dc848a1fbd4b4a0844d07","source":{"kind":"arxiv","id":"2606.29982","version":1},"attestation_state":"computed","paper":{"title":"Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hong Liu, Hui Zang, Jiajia Chu, Minghao Chen, Pengfei Xia, Rui Zhang, Tuo Hao, Ziyang Zhang","submitted_at":"2026-06-29T08:57:59Z","abstract_excerpt":"Mixture-of-Experts (MoE) architectures enable language models to achieve unprecedented scale via sparse activation. However, their inference performance is often limited by data movement bottlenecks. Two coupled challenges exacerbate this limtation: (1) Importance-Agnostic Cost: Low-contribution experts incur nearly uniform memory and transfer costs, resulting in a low cost-to-benefit ratio and wasting critical bandwidth; (2) System-Level Imbalance: Multi-device deployments are universally bottlenecked by the slowest device, meaning that local reductions on one device may yield no improvement "},"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":"2606.29982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-29T08:57:59Z","cross_cats_sorted":[],"title_canon_sha256":"6b90477436371fafe2062d81c326334f0da2d47f806e921cfc6df268c5621b94","abstract_canon_sha256":"4a92e35a6d758393c3159ffc725ea6ee7a5698df854de252646c1a7336cd41d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:43.982605Z","signature_b64":"QL4UobVkecKdApA24IJ+C4XlIQDVk2xZNawpNay9In4ZaxxGrFJRv3MxhisjK7pnd3e02tqj4oa6Ep6YtBA4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"314e3fcbdf381359d8ee17b37132cf3e6aba6ae1f88dc848a1fbd4b4a0844d07","last_reissued_at":"2026-06-30T02:17:43.981234Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:43.981234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hong Liu, Hui Zang, Jiajia Chu, Minghao Chen, Pengfei Xia, Rui Zhang, Tuo Hao, Ziyang Zhang","submitted_at":"2026-06-29T08:57:59Z","abstract_excerpt":"Mixture-of-Experts (MoE) architectures enable language models to achieve unprecedented scale via sparse activation. However, their inference performance is often limited by data movement bottlenecks. Two coupled challenges exacerbate this limtation: (1) Importance-Agnostic Cost: Low-contribution experts incur nearly uniform memory and transfer costs, resulting in a low cost-to-benefit ratio and wasting critical bandwidth; (2) System-Level Imbalance: Multi-device deployments are universally bottlenecked by the slowest device, meaning that local reductions on one device may yield no improvement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29982","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/2606.29982/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":"2606.29982","created_at":"2026-06-30T02:17:43.982134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29982v1","created_at":"2026-06-30T02:17:43.982134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29982","created_at":"2026-06-30T02:17:43.982134+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFHD7S67HAJV","created_at":"2026-06-30T02:17:43.982134+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFHD7S67HAJVTWHO","created_at":"2026-06-30T02:17:43.982134+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFHD7S67","created_at":"2026-06-30T02:17:43.982134+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/GFHD7S67HAJVTWHOC6ZXCMWPHZ","json":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ.json","graph_json":"https://pith.science/api/pith-number/GFHD7S67HAJVTWHOC6ZXCMWPHZ/graph.json","events_json":"https://pith.science/api/pith-number/GFHD7S67HAJVTWHOC6ZXCMWPHZ/events.json","paper":"https://pith.science/paper/GFHD7S67"},"agent_actions":{"view_html":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ","download_json":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ.json","view_paper":"https://pith.science/paper/GFHD7S67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29982&json=true","fetch_graph":"https://pith.science/api/pith-number/GFHD7S67HAJVTWHOC6ZXCMWPHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GFHD7S67HAJVTWHOC6ZXCMWPHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ/action/storage_attestation","attest_author":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ/action/author_attestation","sign_citation":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ/action/citation_signature","submit_replication":"https://pith.science/pith/GFHD7S67HAJVTWHOC6ZXCMWPHZ/action/replication_record"}},"created_at":"2026-06-30T02:17:43.982134+00:00","updated_at":"2026-06-30T02:17:43.982134+00:00"}