{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QTXLMH3ZHMLTYLCLVP4EHZ6I3P","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":"9ab7c55fb279fbe7b4dfc1266a9b39d6b8668d72c6b7af217a801a4d852916ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-02T08:06:57Z","title_canon_sha256":"b513831fea558367f1ae74d06a4a7e894f47f73da0852d28e8a8b9fd3e4a0c17"},"schema_version":"1.0","source":{"id":"2607.01844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01844","created_at":"2026-07-03T01:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01844v1","created_at":"2026-07-03T01:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01844","created_at":"2026-07-03T01:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"QTXLMH3ZHMLT","created_at":"2026-07-03T01:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"QTXLMH3ZHMLTYLCL","created_at":"2026-07-03T01:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"QTXLMH3Z","created_at":"2026-07-03T01:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:64abf7d8b92e97ac96991c641be9f924937b23ee66a245fb3a9a63a7a0f4773d","target":"graph","created_at":"2026-07-03T01:17:31Z","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/2607.01844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes various existing and novel parallelism techniques at different layers and stages of the Mixture-of-Experts (MoE) model training pipeline. It leverages these techniques to achieve maximal efficiency given the physical constraints of CPU, CPU memory, GPU HBM memory, and the CPU-GPU, GPU-GPU, and node-node communication bandwidth of the GPU cluster. It also contains a novel strategy for the optimizer step to achieve high throughput and memory efficien","authors_text":"Semih Yavuz, Shafiq Joty, Shrey Pandit, Silvio Savarese, Xuan-Phi Nguyen, Yiran Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-02T08:06:57Z","title":"Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01844","kind":"arxiv","version":1},"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":"sha256:76c3322a7f94df5f260c4b20ef6608ab330204ff6841b34db6ebfe334e909b53","target":"record","created_at":"2026-07-03T01:17:31Z","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":"9ab7c55fb279fbe7b4dfc1266a9b39d6b8668d72c6b7af217a801a4d852916ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-02T08:06:57Z","title_canon_sha256":"b513831fea558367f1ae74d06a4a7e894f47f73da0852d28e8a8b9fd3e4a0c17"},"schema_version":"1.0","source":{"id":"2607.01844","kind":"arxiv","version":1}},"canonical_sha256":"84eeb61f793b173c2c4babf843e7c8dbe0c92731dd416cd2759b2f117bcb95a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84eeb61f793b173c2c4babf843e7c8dbe0c92731dd416cd2759b2f117bcb95a0","first_computed_at":"2026-07-03T01:17:31.449259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:31.449259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fYyce7O3h1B8h95x7pZmE0vm2I//iMRvqh8mAhomOQWSEfdXVWWpbGuqXgvoJXfSsTUrH6FTQw/anmikGIqCCQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:31.449961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76c3322a7f94df5f260c4b20ef6608ab330204ff6841b34db6ebfe334e909b53","sha256:64abf7d8b92e97ac96991c641be9f924937b23ee66a245fb3a9a63a7a0f4773d"],"state_sha256":"05c2dca38727704292a2df203a690b9922c4ece095bf71f8ceab6e1da1a08738"}