{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OIQ6RXMI6G6QMDAQDKJRGBAAIO","short_pith_number":"pith:OIQ6RXMI","schema_version":"1.0","canonical_sha256":"7221e8dd88f1bd060c101a931304004394cc58dbd2b20bcfd095b47dd1ae73cb","source":{"kind":"arxiv","id":"2508.09229","version":1},"attestation_state":"computed","paper":{"title":"Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.NI","authors_text":"Aleksandr Katrutsa, Danil Sivtsov, Ivan Oseledets","submitted_at":"2025-08-12T07:08:48Z","abstract_excerpt":"Efficient deployment of a pre-trained LLM to a cluster with multiple servers is a critical step for providing fast responses to users' queries. The recent success of Mixture-of-Experts (MoE) LLMs raises the question of how to deploy them efficiently, considering their underlying structure. During the inference in MoE LLMs, only a small part of the experts is selected to process a given token. Moreover, in practice, the experts' load is highly imbalanced. For efficient deployment, one has to distribute the model across a large number of servers using a model placement algorithm. Thus, to improv"},"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":"2508.09229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NI","submitted_at":"2025-08-12T07:08:48Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"451c00275f897f264966b111ff5cf0fcf39d221cbe39a2037b30ab5e0fb09b57","abstract_canon_sha256":"bda24e2b1b82bbb89ae0cb0792da35bc7e8ae356d1b73420ec0655252b7d6e5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:10.641665Z","signature_b64":"qau05PVQF9pGslcnnoZf9ktv6kk3gK9GQo4kkkZNIRtsCic5yWu0V6IDQHDQhdn9kl4f1NWp9oDhu/r6s1QpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7221e8dd88f1bd060c101a931304004394cc58dbd2b20bcfd095b47dd1ae73cb","last_reissued_at":"2026-07-05T11:53:10.641152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:10.641152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.NI","authors_text":"Aleksandr Katrutsa, Danil Sivtsov, Ivan Oseledets","submitted_at":"2025-08-12T07:08:48Z","abstract_excerpt":"Efficient deployment of a pre-trained LLM to a cluster with multiple servers is a critical step for providing fast responses to users' queries. The recent success of Mixture-of-Experts (MoE) LLMs raises the question of how to deploy them efficiently, considering their underlying structure. During the inference in MoE LLMs, only a small part of the experts is selected to process a given token. Moreover, in practice, the experts' load is highly imbalanced. For efficient deployment, one has to distribute the model across a large number of servers using a model placement algorithm. Thus, to improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09229","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/2508.09229/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":"2508.09229","created_at":"2026-07-05T11:53:10.641212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09229v1","created_at":"2026-07-05T11:53:10.641212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09229","created_at":"2026-07-05T11:53:10.641212+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIQ6RXMI6G6Q","created_at":"2026-07-05T11:53:10.641212+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIQ6RXMI6G6QMDAQ","created_at":"2026-07-05T11:53:10.641212+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIQ6RXMI","created_at":"2026-07-05T11:53:10.641212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00515","citing_title":"SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00515","citing_title":"SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networks","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO","json":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO.json","graph_json":"https://pith.science/api/pith-number/OIQ6RXMI6G6QMDAQDKJRGBAAIO/graph.json","events_json":"https://pith.science/api/pith-number/OIQ6RXMI6G6QMDAQDKJRGBAAIO/events.json","paper":"https://pith.science/paper/OIQ6RXMI"},"agent_actions":{"view_html":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO","download_json":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO.json","view_paper":"https://pith.science/paper/OIQ6RXMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09229&json=true","fetch_graph":"https://pith.science/api/pith-number/OIQ6RXMI6G6QMDAQDKJRGBAAIO/graph.json","fetch_events":"https://pith.science/api/pith-number/OIQ6RXMI6G6QMDAQDKJRGBAAIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO/action/storage_attestation","attest_author":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO/action/author_attestation","sign_citation":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO/action/citation_signature","submit_replication":"https://pith.science/pith/OIQ6RXMI6G6QMDAQDKJRGBAAIO/action/replication_record"}},"created_at":"2026-07-05T11:53:10.641212+00:00","updated_at":"2026-07-05T11:53:10.641212+00:00"}