{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DMNLJ6Y62I7FAE2FJDFAZ24ALN","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":"7ec4115563e9a6aff4222a304189546c9dced99181ce34f2f98bc321a095dbd0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-06-30T05:55:11Z","title_canon_sha256":"f5c2c209cc2ea0820360a8fff807ffcf0980155cb6e9011ddecca998a4e5bb16"},"schema_version":"1.0","source":{"id":"2407.00599","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00599","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00599v2","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00599","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"pith_short_12","alias_value":"DMNLJ6Y62I7F","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"pith_short_16","alias_value":"DMNLJ6Y62I7FAE2F","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"pith_short_8","alias_value":"DMNLJ6Y6","created_at":"2026-07-05T08:39:36Z"}],"graph_snapshots":[{"event_id":"sha256:4bca872ba6c7a9819d1d79d78177f5255e6d4a49a3fcfa3e420b58bfe944fa97","target":"graph","created_at":"2026-07-05T08:39:36Z","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/2407.00599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparsely-activated Mixture-of-Expert (MoE) layers have found practical applications in enlarging the model size of large-scale foundation models, with only a sub-linear increase in computation demands. Despite the wide adoption of hybrid parallel paradigms like model parallelism, expert parallelism, and expert-sharding parallelism (i.e., MP+EP+ESP) to support MoE model training on GPU clusters, the training efficiency is hindered by communication costs introduced by these parallel paradigms. To address this limitation, we propose Parm, a system that accelerates MP+EP+ESP training by designing ","authors_text":"Bo Li, Shaohuai Shi, Weinong Sun, Wenxiang Lin, Xiaowen Chu, Xinglin Pan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-06-30T05:55:11Z","title":"Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00599","kind":"arxiv","version":2},"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":"sha256:5274e7278fc2625274094109e28d1c765619cb0d61ae5b37f6d340d44927da73","target":"record","created_at":"2026-07-05T08:39:36Z","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":"7ec4115563e9a6aff4222a304189546c9dced99181ce34f2f98bc321a095dbd0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-06-30T05:55:11Z","title_canon_sha256":"f5c2c209cc2ea0820360a8fff807ffcf0980155cb6e9011ddecca998a4e5bb16"},"schema_version":"1.0","source":{"id":"2407.00599","kind":"arxiv","version":2}},"canonical_sha256":"1b1ab4fb1ed23e50134548ca0ceb805b637dc44de6e826acaa4d6c68ac5aa1c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b1ab4fb1ed23e50134548ca0ceb805b637dc44de6e826acaa4d6c68ac5aa1c5","first_computed_at":"2026-07-05T08:39:36.000079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:36.000079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"12LXnA/MBhIOrgTwt5zFD8i7bDpmKnQdmCF/CRGLnD3ORWF/taVJtA64jD+ZcqjE/Yz/MMRLDf2HIokMKU+PBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:36.000609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00599","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5274e7278fc2625274094109e28d1c765619cb0d61ae5b37f6d340d44927da73","sha256:4bca872ba6c7a9819d1d79d78177f5255e6d4a49a3fcfa3e420b58bfe944fa97"],"state_sha256":"f62774fc0d448f97a69b25799599bac67e7bdaaf45d013f6487e995610f802d1"}