{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DCBNNXXPOJVC5BZDFWSTQDWYZW","short_pith_number":"pith:DCBNNXXP","schema_version":"1.0","canonical_sha256":"1882d6deef726a2e87232da5380ed8cd8845c032e6eef3a708a22088b4f696b5","source":{"kind":"arxiv","id":"2411.10003","version":2},"attestation_state":"computed","paper":{"title":"Pro-Prophet: A Systematic Load Balancing Method for Efficient Parallel Training of Large-scale MoE Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Ao Shen, Dongsheng Li, Huayou Su, Keshi Ge, Shengwei Li, Weijie Liu, Wei Wang, Zhiquan Lai","submitted_at":"2024-11-15T07:27:58Z","abstract_excerpt":"The size of deep learning models has been increasing to enhance model quality. The linear increase in training computation budget with model size means that training an extremely large-scale model is exceedingly time-consuming. Recently, the Mixture of Expert (MoE) has drawn significant attention as it can scale models to extra-large sizes with a stable computation budget. However, inefficient distributed training of large-scale MoE models hinders their broader application. Specifically, a considerable dynamic load imbalance occurs among devices during training, significantly reducing throughp"},"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":"2411.10003","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-15T07:27:58Z","cross_cats_sorted":[],"title_canon_sha256":"9db82667bbc93caa2fb1d66148937ee0fbc185300218dbd0b6cd4f04390392fa","abstract_canon_sha256":"6a27f5c2a3730c21b6130f7dbf12f78dfd37b2c069077a0f7573efb085a7c33a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:32.549536Z","signature_b64":"b5ZXlaqL9qQTcVQTSfQVAYJjo4mlBTbmBRqsr5S9xS3p15tK8W/mukGMaysCcriu3qV6oq54NUuwh9rVcGlWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1882d6deef726a2e87232da5380ed8cd8845c032e6eef3a708a22088b4f696b5","last_reissued_at":"2026-07-05T09:38:32.548886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:32.548886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pro-Prophet: A Systematic Load Balancing Method for Efficient Parallel Training of Large-scale MoE Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Ao Shen, Dongsheng Li, Huayou Su, Keshi Ge, Shengwei Li, Weijie Liu, Wei Wang, Zhiquan Lai","submitted_at":"2024-11-15T07:27:58Z","abstract_excerpt":"The size of deep learning models has been increasing to enhance model quality. The linear increase in training computation budget with model size means that training an extremely large-scale model is exceedingly time-consuming. Recently, the Mixture of Expert (MoE) has drawn significant attention as it can scale models to extra-large sizes with a stable computation budget. However, inefficient distributed training of large-scale MoE models hinders their broader application. Specifically, a considerable dynamic load imbalance occurs among devices during training, significantly reducing throughp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10003","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/2411.10003/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":"2411.10003","created_at":"2026-07-05T09:38:32.548960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10003v2","created_at":"2026-07-05T09:38:32.548960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10003","created_at":"2026-07-05T09:38:32.548960+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCBNNXXPOJVC","created_at":"2026-07-05T09:38:32.548960+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCBNNXXPOJVC5BZD","created_at":"2026-07-05T09:38:32.548960+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCBNNXXP","created_at":"2026-07-05T09:38:32.548960+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/DCBNNXXPOJVC5BZDFWSTQDWYZW","json":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW.json","graph_json":"https://pith.science/api/pith-number/DCBNNXXPOJVC5BZDFWSTQDWYZW/graph.json","events_json":"https://pith.science/api/pith-number/DCBNNXXPOJVC5BZDFWSTQDWYZW/events.json","paper":"https://pith.science/paper/DCBNNXXP"},"agent_actions":{"view_html":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW","download_json":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW.json","view_paper":"https://pith.science/paper/DCBNNXXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10003&json=true","fetch_graph":"https://pith.science/api/pith-number/DCBNNXXPOJVC5BZDFWSTQDWYZW/graph.json","fetch_events":"https://pith.science/api/pith-number/DCBNNXXPOJVC5BZDFWSTQDWYZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW/action/storage_attestation","attest_author":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW/action/author_attestation","sign_citation":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW/action/citation_signature","submit_replication":"https://pith.science/pith/DCBNNXXPOJVC5BZDFWSTQDWYZW/action/replication_record"}},"created_at":"2026-07-05T09:38:32.548960+00:00","updated_at":"2026-07-05T09:38:32.548960+00:00"}