{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PSO2OJVCZCLW67GU3D3NIWSSIG","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":"217e22e5a7952e223cc10ecd409cff4bad261d8834558fdc66dad3965061c131","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-13T17:52:38Z","title_canon_sha256":"1fc483b787cc3a48c58a2b9303e6535af2fcdc0902d7e0bb421a5d193806f0b3"},"schema_version":"1.0","source":{"id":"2206.06356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.06356","created_at":"2026-07-05T04:31:18Z"},{"alias_kind":"arxiv_version","alias_value":"2206.06356v1","created_at":"2026-07-05T04:31:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06356","created_at":"2026-07-05T04:31:18Z"},{"alias_kind":"pith_short_12","alias_value":"PSO2OJVCZCLW","created_at":"2026-07-05T04:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"PSO2OJVCZCLW67GU","created_at":"2026-07-05T04:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"PSO2OJVC","created_at":"2026-07-05T04:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:ff64642a7d2049e59dfaec3bc2c285dedf72d86312b133a207eb9cd149e9a3e3","target":"graph","created_at":"2026-07-05T04:31:18Z","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/2206.06356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributed deep learning is becoming increasingly popular due to the expanding demand for computing resources for deep learning models with a larger amount of parameters. Different from traditional training approaches, data-parallel training allows multiple compute nodes to train large deep learning models simultaneously in order to boost the training efficiency. In this paper, we present and compare six strategies for data-parallel training using PyTorch on the language model GPT-2 with 100M parameters using a qualitative approach. These strategies are Single GPU, Single Parameter Server, Di","authors_text":"Hao Bai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-13T17:52:38Z","title":"Modern Distributed Data-Parallel Large-Scale Pre-training Strategies For NLP models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06356","kind":"arxiv","version":1},"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":"sha256:269116361b6131635d15b5ea25bd82511c6bc8af7cb96faeb572ed8bec78295b","target":"record","created_at":"2026-07-05T04:31:18Z","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":"217e22e5a7952e223cc10ecd409cff4bad261d8834558fdc66dad3965061c131","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2022-06-13T17:52:38Z","title_canon_sha256":"1fc483b787cc3a48c58a2b9303e6535af2fcdc0902d7e0bb421a5d193806f0b3"},"schema_version":"1.0","source":{"id":"2206.06356","kind":"arxiv","version":1}},"canonical_sha256":"7c9da726a2c8976f7cd4d8f6d45a52419430bd620fcdda25455d6996f9a75f16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c9da726a2c8976f7cd4d8f6d45a52419430bd620fcdda25455d6996f9a75f16","first_computed_at":"2026-07-05T04:31:18.315946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:18.315946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RNOaipCU3bSjVw5Sye0iNV37FeQjfZN6SYjf7VoBjNrqtPegjLtlP8hcEhKHa2v1/fvzBcTOG/PS9D7K6MElCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:18.316369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.06356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:269116361b6131635d15b5ea25bd82511c6bc8af7cb96faeb572ed8bec78295b","sha256:ff64642a7d2049e59dfaec3bc2c285dedf72d86312b133a207eb9cd149e9a3e3"],"state_sha256":"a703e2f1cf625cc284b71aa198782f2b4dc036d32f335aefdd8451f6a8c08603"}