{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PFUDG73R3WYXK47GXVKCGSEMBW","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":"58c3a7914493e4661672f97e3bb4e93ababbe6455be76af9c8c0fd402cdc0697","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T12:05:45Z","title_canon_sha256":"74992aa76a4a3372071cffecde14de83dfaa3fd8512416edf4942b81b58e1914"},"schema_version":"1.0","source":{"id":"2311.08105","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08105","created_at":"2026-07-05T09:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08105v3","created_at":"2026-07-05T09:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08105","created_at":"2026-07-05T09:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"PFUDG73R3WYX","created_at":"2026-07-05T09:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"PFUDG73R3WYXK47G","created_at":"2026-07-05T09:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"PFUDG73R","created_at":"2026-07-05T09:09:54Z"}],"graph_snapshots":[{"event_id":"sha256:706a9d8e0ec8051b782144f47fdabdfe049600374c23c88814daf4ffd7c3494f","target":"graph","created_at":"2026-07-05T09:09:54Z","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/2311.08105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLM) have become a critical component in many applications of machine learning. However, standard approaches to training LLM require a large number of tightly interconnected accelerators, with devices exchanging gradients and other intermediate states at each optimization step. While it is difficult to build and maintain a single computing cluster hosting many accelerators, it might be easier to find several computing clusters each hosting a smaller number of devices. In this work, we propose a distributed optimization algorithm, Distributed Low-Communication (DiLoCo), t","authors_text":"Adhiguna Kuncoro, Andrei A. Rusu, Arthur Douillard, Arthur Szlam, Jiajun Shen, Marc'Aurelio Ranzato, Qixuan Feng, Rachita Chhaparia, Yani Donchev","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T12:05:45Z","title":"DiLoCo: Distributed Low-Communication Training of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08105","kind":"arxiv","version":3},"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":"sha256:3bb5d42058b9dbc7e3aacac1ef3d1f8a18a937682c7e3809e66e6d0024458861","target":"record","created_at":"2026-07-05T09:09:54Z","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":"58c3a7914493e4661672f97e3bb4e93ababbe6455be76af9c8c0fd402cdc0697","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T12:05:45Z","title_canon_sha256":"74992aa76a4a3372071cffecde14de83dfaa3fd8512416edf4942b81b58e1914"},"schema_version":"1.0","source":{"id":"2311.08105","kind":"arxiv","version":3}},"canonical_sha256":"7968337f71ddb17573e6bd5423488c0db65900e368dc889d0a9c41be8d370c77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7968337f71ddb17573e6bd5423488c0db65900e368dc889d0a9c41be8d370c77","first_computed_at":"2026-07-05T09:09:54.367288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:54.367288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j2M8Rz9NCMNp9he5PVODN9MZpiDag5qbWU+dMB/pZmKcJ57QOok+CUkKxz9ez5TIXH0tH/cppgSuNEbLKageAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:54.367867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08105","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bb5d42058b9dbc7e3aacac1ef3d1f8a18a937682c7e3809e66e6d0024458861","sha256:706a9d8e0ec8051b782144f47fdabdfe049600374c23c88814daf4ffd7c3494f"],"state_sha256":"b3faa8819e54f3dc7db87402e5608539827c14d4edf885a6458a0a95eb4acb1c"}