{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GDMKE6GDP7FN2JJP5QXZBCVMRU","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":"6489cf17e874b5d2d533b73c5f43a41ea11647ff49108151d13bb607eddf325f","cross_cats_sorted":["cs.CV","cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-15T16:18:05Z","title_canon_sha256":"ac2474bdc60a30e08718c87c4c1295ef50d46e4162730cad3a1ed1a613230869"},"schema_version":"1.0","source":{"id":"2006.08517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08517","created_at":"2026-07-05T01:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08517v1","created_at":"2026-07-05T01:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08517","created_at":"2026-07-05T01:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"GDMKE6GDP7FN","created_at":"2026-07-05T01:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"GDMKE6GDP7FN2JJP","created_at":"2026-07-05T01:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"GDMKE6GD","created_at":"2026-07-05T01:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:e54b3e2232b11c3a3bdaba51a784954fc8c3a5cdc8520f41973896ef58843bea","target":"graph","created_at":"2026-07-05T01:10:22Z","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/2006.08517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-batch training is an efficient approach for current distributed deep learning systems. It has enabled researchers to reduce the ImageNet/ResNet-50 training from 29 hours to around 1 minute. In this paper, we focus on studying the limit of the batch size. We think it may provide a guidance to AI supercomputer and algorithm designers. We provide detailed numerical optimization instructions for step-by-step comparison. Moreover, it is important to understand the generalization and optimization performance of huge batch training. Hoffer et al. introduced \"ultra-slow diffusion\" theory to larg","authors_text":"Cho-Jui Hsieh, Huan Zhang, James Demmel, Yang You, Yuhui Wang, Zhao Zhang","cross_cats":["cs.CV","cs.DC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-15T16:18:05Z","title":"The Limit of the Batch Size"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08517","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":"sha256:7ebf6274bcab91e15857b035fbb7cff4e335e072aaa7ef41783df055b611b7c1","target":"record","created_at":"2026-07-05T01:10:22Z","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":"6489cf17e874b5d2d533b73c5f43a41ea11647ff49108151d13bb607eddf325f","cross_cats_sorted":["cs.CV","cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-15T16:18:05Z","title_canon_sha256":"ac2474bdc60a30e08718c87c4c1295ef50d46e4162730cad3a1ed1a613230869"},"schema_version":"1.0","source":{"id":"2006.08517","kind":"arxiv","version":1}},"canonical_sha256":"30d8a278c37fcadd252fec2f908aac8d116f8ebe5b973601da2d4e3ba4a523f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30d8a278c37fcadd252fec2f908aac8d116f8ebe5b973601da2d4e3ba4a523f0","first_computed_at":"2026-07-05T01:10:22.272211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:22.272211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TWhAC3kQlfHNSoRD91hLN5VQrm1q/ki/dSQjQVehoARDK/dpnRInW0pbZgqzt2xUi3UlN3qmKey1adlTqB9QDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:22.272573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.08517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ebf6274bcab91e15857b035fbb7cff4e335e072aaa7ef41783df055b611b7c1","sha256:e54b3e2232b11c3a3bdaba51a784954fc8c3a5cdc8520f41973896ef58843bea"],"state_sha256":"07d179b0d11d08e6e8317c29d4ea78471912691d8336864fede4afbac21b41a5"}