{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OUCESMLIZWTYDRI3WDF2MVULB7","short_pith_number":"pith:OUCESMLI","schema_version":"1.0","canonical_sha256":"7504493168cda781c51bb0cba6568b0fc5a5285d28f88c3531edd7856712b961","source":{"kind":"arxiv","id":"2608.00573","version":1},"attestation_state":"computed","paper":{"title":"TrimMoE A communication aware and adaptive depth framework for distributed edge 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, Shuting Bai, Song Guo, Wenchao Xu, Xin Yuan","submitted_at":"2026-08-01T10:19:02Z","abstract_excerpt":"Serving Mixture-of-Experts (MoE) large language models across distributed edge servers is bottlenecked by the cross-server expert transmission. The existing approaches mainly focus on how to reach a remote expert faster. However, in this paper, we instead consider whether a given layer, and the layers after it, need to be executed at all. To this end, a communication-aware adaptive-depth framework is proposed in this paper, termed TrimMoE, which couples layer skipping and confidence-based early exit with substitute execution and server-expert selection under a unified quality budget. Specifica"},"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":"2608.00573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2026-08-01T10:19:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"05092ff81df6027e44bcfd776e6cb57e11b85992187adea6dd02c7233d0a565e","abstract_canon_sha256":"491b0c676bcc739bb055df8bb076bd349efe1da234331ff75c326782112e30ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:37:27.664598Z","signature_b64":"P2KMOGOcPMjiYLV6OPHIDGRMEhWpoAQ9Y/6rYeCntqwVCHhHloh2RgLgdP+VMDD/qA0/P3qSzMYeDusLylEbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7504493168cda781c51bb0cba6568b0fc5a5285d28f88c3531edd7856712b961","last_reissued_at":"2026-08-04T00:37:27.663165Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:37:27.663165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrimMoE A communication aware and adaptive depth framework for distributed edge 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, Shuting Bai, Song Guo, Wenchao Xu, Xin Yuan","submitted_at":"2026-08-01T10:19:02Z","abstract_excerpt":"Serving Mixture-of-Experts (MoE) large language models across distributed edge servers is bottlenecked by the cross-server expert transmission. The existing approaches mainly focus on how to reach a remote expert faster. However, in this paper, we instead consider whether a given layer, and the layers after it, need to be executed at all. To this end, a communication-aware adaptive-depth framework is proposed in this paper, termed TrimMoE, which couples layer skipping and confidence-based early exit with substitute execution and server-expert selection under a unified quality budget. Specifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00573","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/2608.00573/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":"2608.00573","created_at":"2026-08-04T00:37:27.664336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00573v1","created_at":"2026-08-04T00:37:27.664336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00573","created_at":"2026-08-04T00:37:27.664336+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUCESMLIZWTY","created_at":"2026-08-04T00:37:27.664336+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUCESMLIZWTYDRI3","created_at":"2026-08-04T00:37:27.664336+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUCESMLI","created_at":"2026-08-04T00:37:27.664336+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/OUCESMLIZWTYDRI3WDF2MVULB7","json":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7.json","graph_json":"https://pith.science/api/pith-number/OUCESMLIZWTYDRI3WDF2MVULB7/graph.json","events_json":"https://pith.science/api/pith-number/OUCESMLIZWTYDRI3WDF2MVULB7/events.json","paper":"https://pith.science/paper/OUCESMLI"},"agent_actions":{"view_html":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7","download_json":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7.json","view_paper":"https://pith.science/paper/OUCESMLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00573&json=true","fetch_graph":"https://pith.science/api/pith-number/OUCESMLIZWTYDRI3WDF2MVULB7/graph.json","fetch_events":"https://pith.science/api/pith-number/OUCESMLIZWTYDRI3WDF2MVULB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7/action/storage_attestation","attest_author":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7/action/author_attestation","sign_citation":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7/action/citation_signature","submit_replication":"https://pith.science/pith/OUCESMLIZWTYDRI3WDF2MVULB7/action/replication_record"}},"created_at":"2026-08-04T00:37:27.664336+00:00","updated_at":"2026-08-04T00:37:27.664336+00:00"}