{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HYVBSZPY2VWFDPUHVLZHQRDLN6","short_pith_number":"pith:HYVBSZPY","schema_version":"1.0","canonical_sha256":"3e2a1965f8d56c51be87aaf278446b6fba777f03c7175ed71a7965d17235759c","source":{"kind":"arxiv","id":"2412.07210","version":2},"attestation_state":"computed","paper":{"title":"EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Jiadi Jiang, Jialiang Cheng, Jian Sha, Ning Gao, Yun Yue, Zhiling Ye","submitted_at":"2024-12-10T06:08:24Z","abstract_excerpt":"Distributed training methods are crucial for large language models (LLMs). However, existing distributed training methods often suffer from communication bottlenecks, stragglers, and limited elasticity, particularly in heterogeneous or large-scale environments. Local SGD methods have been proposed to address these issues, but their effectiveness remains limited to small-scale training due to additional memory overhead and lack of concerns on efficiency and stability. To tackle these issues, we propose EDiT, an innovative Efficient Distributed Training method that combines a tailored Local SGD "},"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":"2412.07210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-12-10T06:08:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6802a55af60cf26b857657a0c6d208b2aacb06c11ffb1ee2b45f962774c6b019","abstract_canon_sha256":"16b1625c4c958c2433d4f5f4af1c1c35d040aa4d61455b7b7d87baaf256f761f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:23.688292Z","signature_b64":"BZvmzVPUk/mhnCnqzshuaOiKR4fsv0E8D6ARcSq3bHWoFyiV9SthcpCj3X1/MQM1IRESpqQf34EhWfpbrVrbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e2a1965f8d56c51be87aaf278446b6fba777f03c7175ed71a7965d17235759c","last_reissued_at":"2026-07-05T10:15:23.687798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:23.687798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Jiadi Jiang, Jialiang Cheng, Jian Sha, Ning Gao, Yun Yue, Zhiling Ye","submitted_at":"2024-12-10T06:08:24Z","abstract_excerpt":"Distributed training methods are crucial for large language models (LLMs). However, existing distributed training methods often suffer from communication bottlenecks, stragglers, and limited elasticity, particularly in heterogeneous or large-scale environments. Local SGD methods have been proposed to address these issues, but their effectiveness remains limited to small-scale training due to additional memory overhead and lack of concerns on efficiency and stability. To tackle these issues, we propose EDiT, an innovative Efficient Distributed Training method that combines a tailored Local SGD "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07210","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/2412.07210/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":"2412.07210","created_at":"2026-07-05T10:15:23.687862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07210v2","created_at":"2026-07-05T10:15:23.687862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07210","created_at":"2026-07-05T10:15:23.687862+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYVBSZPY2VWF","created_at":"2026-07-05T10:15:23.687862+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYVBSZPY2VWFDPUH","created_at":"2026-07-05T10:15:23.687862+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYVBSZPY","created_at":"2026-07-05T10:15:23.687862+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/HYVBSZPY2VWFDPUHVLZHQRDLN6","json":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6.json","graph_json":"https://pith.science/api/pith-number/HYVBSZPY2VWFDPUHVLZHQRDLN6/graph.json","events_json":"https://pith.science/api/pith-number/HYVBSZPY2VWFDPUHVLZHQRDLN6/events.json","paper":"https://pith.science/paper/HYVBSZPY"},"agent_actions":{"view_html":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6","download_json":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6.json","view_paper":"https://pith.science/paper/HYVBSZPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07210&json=true","fetch_graph":"https://pith.science/api/pith-number/HYVBSZPY2VWFDPUHVLZHQRDLN6/graph.json","fetch_events":"https://pith.science/api/pith-number/HYVBSZPY2VWFDPUHVLZHQRDLN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6/action/storage_attestation","attest_author":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6/action/author_attestation","sign_citation":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6/action/citation_signature","submit_replication":"https://pith.science/pith/HYVBSZPY2VWFDPUHVLZHQRDLN6/action/replication_record"}},"created_at":"2026-07-05T10:15:23.687862+00:00","updated_at":"2026-07-05T10:15:23.687862+00:00"}