{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DMNLJ6Y62I7FAE2FJDFAZ24ALN","short_pith_number":"pith:DMNLJ6Y6","canonical_record":{"source":{"id":"2407.00599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-06-30T05:55:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5c2c209cc2ea0820360a8fff807ffcf0980155cb6e9011ddecca998a4e5bb16","abstract_canon_sha256":"7ec4115563e9a6aff4222a304189546c9dced99181ce34f2f98bc321a095dbd0"},"schema_version":"1.0"},"canonical_sha256":"1b1ab4fb1ed23e50134548ca0ceb805b637dc44de6e826acaa4d6c68ac5aa1c5","source":{"kind":"arxiv","id":"2407.00599","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DMNLJ6Y62I7FAE2FJDFAZ24ALN","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-06-30T05:55:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5c2c209cc2ea0820360a8fff807ffcf0980155cb6e9011ddecca998a4e5bb16","abstract_canon_sha256":"7ec4115563e9a6aff4222a304189546c9dced99181ce34f2f98bc321a095dbd0"},"schema_version":"1.0"},"canonical_sha256":"1b1ab4fb1ed23e50134548ca0ceb805b637dc44de6e826acaa4d6c68ac5aa1c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:36.000609Z","signature_b64":"12LXnA/MBhIOrgTwt5zFD8i7bDpmKnQdmCF/CRGLnD3ORWF/taVJtA64jD+ZcqjE/Yz/MMRLDf2HIokMKU+PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b1ab4fb1ed23e50134548ca0ceb805b637dc44de6e826acaa4d6c68ac5aa1c5","last_reissued_at":"2026-07-05T08:39:36.000079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:36.000079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00599","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MbxSjRadueHJtHuCBiuDrw3DOuyfP2xiZHMYMpMO5zG3CeBqBX3U06C+8pLYk+0lE0CxDn+4dg3Vfvhjb4S6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:04:16.684628Z"},"content_sha256":"5274e7278fc2625274094109e28d1c765619cb0d61ae5b37f6d340d44927da73","schema_version":"1.0","event_id":"sha256:5274e7278fc2625274094109e28d1c765619cb0d61ae5b37f6d340d44927da73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DMNLJ6Y62I7FAE2FJDFAZ24ALN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Bo Li, Shaohuai Shi, Weinong Sun, Wenxiang Lin, Xiaowen Chu, Xinglin Pan","submitted_at":"2024-06-30T05:55:11Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00599","kind":"arxiv","version":2},"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/2407.00599/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XT/rUhPmlxKuhOPN8DMDKOOdfph+gJRv8PSMTI5s9RdglEsFkynD85Apo0EzBg1IFLGXMVGT8Aw7WMjDbrEyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:04:16.685132Z"},"content_sha256":"4bca872ba6c7a9819d1d79d78177f5255e6d4a49a3fcfa3e420b58bfe944fa97","schema_version":"1.0","event_id":"sha256:4bca872ba6c7a9819d1d79d78177f5255e6d4a49a3fcfa3e420b58bfe944fa97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DMNLJ6Y62I7FAE2FJDFAZ24ALN/bundle.json","state_url":"https://pith.science/pith/DMNLJ6Y62I7FAE2FJDFAZ24ALN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DMNLJ6Y62I7FAE2FJDFAZ24ALN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T03:04:16Z","links":{"resolver":"https://pith.science/pith/DMNLJ6Y62I7FAE2FJDFAZ24ALN","bundle":"https://pith.science/pith/DMNLJ6Y62I7FAE2FJDFAZ24ALN/bundle.json","state":"https://pith.science/pith/DMNLJ6Y62I7FAE2FJDFAZ24ALN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DMNLJ6Y62I7FAE2FJDFAZ24ALN/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xOR9GcPIPz3mWh0whkQgqBKYFX0bVocWO2LHUREMCsD4ST0K5x2pr3Wx75CtxgfqdRO17R5LpS+tJRfWVsMRDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:04:16.689773Z","bundle_sha256":"b04233e88d0ac9cf6fa3bce160974a27dbb3a6e66dcff5ca3efe0ba935464690"}}