{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SD42LFS32EEIL2HOKGECSL3FL4","short_pith_number":"pith:SD42LFS3","schema_version":"1.0","canonical_sha256":"90f9a5965bd10885e8ee5188292f655f3664dcaae2784fb7fce8802e3a39031a","source":{"kind":"arxiv","id":"2311.05610","version":3},"attestation_state":"computed","paper":{"title":"Efficient Parallelization Layouts for Large-Scale Distributed Model Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Gerard de Melo, Johannes Hagemann, Konstantin Dobler, Maximilian Schall, Samuel Weinbach","submitted_at":"2023-11-09T18:59:38Z","abstract_excerpt":"Efficiently training large language models requires parallelizing across hundreds of hardware accelerators and invoking various compute and memory optimizations. When combined, many of these strategies have complex interactions regarding the final training efficiency. Prior work tackling this problem did not have access to the latest set of optimizations, such as FlashAttention or sequence parallelism. In this work, we conduct a comprehensive ablation study of possible training configurations for large language models. We distill this large study into several key recommendations for the most e"},"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":"2311.05610","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-09T18:59:38Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"70ce2a80815324b621803fb6a4ac64535445aadda16ccb9bd282af7e6f0e4f91","abstract_canon_sha256":"cd2ba0831c32828a41b3dd3d0d714ae9781be05dbe6a1ecec0f1d02415cb5fb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:43.897426Z","signature_b64":"j7J91MPLNpNMPJuCySjpTuoFQqixE8PYsPhR20uq+IOY/jkEzDudtxLaCp7lklOdOMZ2Ua1aKYPVMVEvwM64AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90f9a5965bd10885e8ee5188292f655f3664dcaae2784fb7fce8802e3a39031a","last_reissued_at":"2026-07-05T09:10:43.896885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:43.896885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Parallelization Layouts for Large-Scale Distributed Model Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Gerard de Melo, Johannes Hagemann, Konstantin Dobler, Maximilian Schall, Samuel Weinbach","submitted_at":"2023-11-09T18:59:38Z","abstract_excerpt":"Efficiently training large language models requires parallelizing across hundreds of hardware accelerators and invoking various compute and memory optimizations. When combined, many of these strategies have complex interactions regarding the final training efficiency. Prior work tackling this problem did not have access to the latest set of optimizations, such as FlashAttention or sequence parallelism. In this work, we conduct a comprehensive ablation study of possible training configurations for large language models. We distill this large study into several key recommendations for the most e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05610","kind":"arxiv","version":3},"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/2311.05610/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":"2311.05610","created_at":"2026-07-05T09:10:43.896935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05610v3","created_at":"2026-07-05T09:10:43.896935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05610","created_at":"2026-07-05T09:10:43.896935+00:00"},{"alias_kind":"pith_short_12","alias_value":"SD42LFS32EEI","created_at":"2026-07-05T09:10:43.896935+00:00"},{"alias_kind":"pith_short_16","alias_value":"SD42LFS32EEIL2HO","created_at":"2026-07-05T09:10:43.896935+00:00"},{"alias_kind":"pith_short_8","alias_value":"SD42LFS3","created_at":"2026-07-05T09:10:43.896935+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/SD42LFS32EEIL2HOKGECSL3FL4","json":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4.json","graph_json":"https://pith.science/api/pith-number/SD42LFS32EEIL2HOKGECSL3FL4/graph.json","events_json":"https://pith.science/api/pith-number/SD42LFS32EEIL2HOKGECSL3FL4/events.json","paper":"https://pith.science/paper/SD42LFS3"},"agent_actions":{"view_html":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4","download_json":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4.json","view_paper":"https://pith.science/paper/SD42LFS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05610&json=true","fetch_graph":"https://pith.science/api/pith-number/SD42LFS32EEIL2HOKGECSL3FL4/graph.json","fetch_events":"https://pith.science/api/pith-number/SD42LFS32EEIL2HOKGECSL3FL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4/action/storage_attestation","attest_author":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4/action/author_attestation","sign_citation":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4/action/citation_signature","submit_replication":"https://pith.science/pith/SD42LFS32EEIL2HOKGECSL3FL4/action/replication_record"}},"created_at":"2026-07-05T09:10:43.896935+00:00","updated_at":"2026-07-05T09:10:43.896935+00:00"}