{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LM2NOVBIE76VHFEBJ3MRKBD3HH","short_pith_number":"pith:LM2NOVBI","schema_version":"1.0","canonical_sha256":"5b34d7542827fd5394814ed915047b39cff8abe45ebca68b669837f1738443bf","source":{"kind":"arxiv","id":"2608.00577","version":1},"attestation_state":"computed","paper":{"title":"HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.NI","authors_text":"Athanasios V. Vasilakos, Haijun Zhang, Ning Li, Song Guo, Wenchao Xu, Xin Yuan","submitted_at":"2026-08-01T10:30:01Z","abstract_excerpt":"Mixture-of-Experts (MoE) models have become a dominant architecture for large-scale AI services, yet deploying them over geo-distributed heterogeneous edge servers remains challenging. When the Top-k activated experts of a token are spread across multiple servers, the optimal routing depends jointly on cross-server link bandwidth, heterogeneous GPU computing capability, GPU-CPU expert loading delay, instantaneous queueing backlog, and replica-level quantization quality loss. Existing distributed inference and MoE serving methods address these factors separately and do not provide a unified fra"},"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":"2608.00577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2026-08-01T10:30:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6c75d058477810a4eb61fc51060980fc3e7f7a2c62689126ce13193d914a4494","abstract_canon_sha256":"ed6738da0cef0bbaa2d7a9dca680c37dea2481d85a281e27ea4a265777c6e5af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:37:29.176985Z","signature_b64":"th1f0BwUdRiEt8O9hE5qa9vwyUSJn0ZrdnsrZk/mljREyExmtMgYPl4Gdmh0G5RiVXmT22rIizi/meMIlZidCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b34d7542827fd5394814ed915047b39cff8abe45ebca68b669837f1738443bf","last_reissued_at":"2026-08-04T00:37:29.175499Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:37:29.175499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.NI","authors_text":"Athanasios V. Vasilakos, Haijun Zhang, Ning Li, Song Guo, Wenchao Xu, Xin Yuan","submitted_at":"2026-08-01T10:30:01Z","abstract_excerpt":"Mixture-of-Experts (MoE) models have become a dominant architecture for large-scale AI services, yet deploying them over geo-distributed heterogeneous edge servers remains challenging. When the Top-k activated experts of a token are spread across multiple servers, the optimal routing depends jointly on cross-server link bandwidth, heterogeneous GPU computing capability, GPU-CPU expert loading delay, instantaneous queueing backlog, and replica-level quantization quality loss. Existing distributed inference and MoE serving methods address these factors separately and do not provide a unified fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00577","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/2608.00577/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":"2608.00577","created_at":"2026-08-04T00:37:29.176720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00577v1","created_at":"2026-08-04T00:37:29.176720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00577","created_at":"2026-08-04T00:37:29.176720+00:00"},{"alias_kind":"pith_short_12","alias_value":"LM2NOVBIE76V","created_at":"2026-08-04T00:37:29.176720+00:00"},{"alias_kind":"pith_short_16","alias_value":"LM2NOVBIE76VHFEB","created_at":"2026-08-04T00:37:29.176720+00:00"},{"alias_kind":"pith_short_8","alias_value":"LM2NOVBI","created_at":"2026-08-04T00:37:29.176720+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/LM2NOVBIE76VHFEBJ3MRKBD3HH","json":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH.json","graph_json":"https://pith.science/api/pith-number/LM2NOVBIE76VHFEBJ3MRKBD3HH/graph.json","events_json":"https://pith.science/api/pith-number/LM2NOVBIE76VHFEBJ3MRKBD3HH/events.json","paper":"https://pith.science/paper/LM2NOVBI"},"agent_actions":{"view_html":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH","download_json":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH.json","view_paper":"https://pith.science/paper/LM2NOVBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00577&json=true","fetch_graph":"https://pith.science/api/pith-number/LM2NOVBIE76VHFEBJ3MRKBD3HH/graph.json","fetch_events":"https://pith.science/api/pith-number/LM2NOVBIE76VHFEBJ3MRKBD3HH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH/action/storage_attestation","attest_author":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH/action/author_attestation","sign_citation":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH/action/citation_signature","submit_replication":"https://pith.science/pith/LM2NOVBIE76VHFEBJ3MRKBD3HH/action/replication_record"}},"created_at":"2026-08-04T00:37:29.176720+00:00","updated_at":"2026-08-04T00:37:29.176720+00:00"}