{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MABUVFA27T25GAGIVF43WJIDVG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"308e09d978c0c18d660fbe666d13bf4276f7baf42775834b0d2c6054f87b5479","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-03-28T12:32:25Z","title_canon_sha256":"e91f74307a75e4aa45f826e022631c2b3b55a1bad1d82563b74c4d721cc7f6b1"},"schema_version":"1.0","source":{"id":"2203.14685","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.14685","created_at":"2026-07-05T05:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2203.14685v3","created_at":"2026-07-05T05:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14685","created_at":"2026-07-05T05:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"MABUVFA27T25","created_at":"2026-07-05T05:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"MABUVFA27T25GAGI","created_at":"2026-07-05T05:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"MABUVFA2","created_at":"2026-07-05T05:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:67c960ce80694105fb20ec2714ef1a84375448d8a6ee5f906449cd2015451b6b","target":"graph","created_at":"2026-07-05T05:16:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.14685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As giant dense models advance quality but require large amounts of GPU budgets for training, the sparsely gated Mixture-of-Experts (MoE), a kind of conditional computation architecture, is proposed to scale models while keeping their computation constant. Specifically, the input tokens are routed by the gate network and only activates part of the expert network. Existing MoE training systems only support part of mainstream MoE models (e.g. Top k) training under expensive high-bandwidth GPU clusters. In this paper, we present HetuMoE, a high-performance large-scale sparse MoE training system bu","authors_text":"Bin Cui, Pinxue Zhao, Tong Zhao, Xiaonan Nie, Xupeng Miao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-03-28T12:32:25Z","title":"HetuMoE: An Efficient Trillion-scale Mixture-of-Expert Distributed Training System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14685","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:228da8231289dcb2bd364dbb7128ae1b88b393179a62bfc01b2ab400c861b17a","target":"record","created_at":"2026-07-05T05:16:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"308e09d978c0c18d660fbe666d13bf4276f7baf42775834b0d2c6054f87b5479","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-03-28T12:32:25Z","title_canon_sha256":"e91f74307a75e4aa45f826e022631c2b3b55a1bad1d82563b74c4d721cc7f6b1"},"schema_version":"1.0","source":{"id":"2203.14685","kind":"arxiv","version":3}},"canonical_sha256":"60034a941afcf5d300c8a979bb2503a994b7bc7fd3bad1fb89cdc40341290e0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60034a941afcf5d300c8a979bb2503a994b7bc7fd3bad1fb89cdc40341290e0c","first_computed_at":"2026-07-05T05:16:50.489055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:16:50.489055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i7sFhs7cwGDpQFB8/d9jZtvbedRgFCtXuHhsFmHz1P4xjwPGVympKEi3rUvip9Bsqf8EJlj4+Kr/3djQUSc4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:16:50.489459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.14685","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:228da8231289dcb2bd364dbb7128ae1b88b393179a62bfc01b2ab400c861b17a","sha256:67c960ce80694105fb20ec2714ef1a84375448d8a6ee5f906449cd2015451b6b"],"state_sha256":"de6306f6bafffa599d2d5b91b18cfabe4f0c5a8646244e2143f29accfa980d6d"}