{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NVXN6AHX3KCMNDF5MHALTPWY4U","short_pith_number":"pith:NVXN6AHX","canonical_record":{"source":{"id":"1901.08256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T07:10:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ffa2a8d9e282bbbc965231335e3c28a6dfe46f144c828d265925ed9c141d8335","abstract_canon_sha256":"b772176406a896fa060829877a270ffb9bbd53959c23814ce580be078bc54a53"},"schema_version":"1.0"},"canonical_sha256":"6d6edf00f7da84c68cbd61c0b9bed8e53dbaa5c5f01f66f9b46e49f92cdf1268","source":{"kind":"arxiv","id":"1901.08256","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08256","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08256v1","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08256","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"NVXN6AHX3KCM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NVXN6AHX3KCMNDF5","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NVXN6AHX","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NVXN6AHX3KCMNDF5MHALTPWY4U","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T07:10:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ffa2a8d9e282bbbc965231335e3c28a6dfe46f144c828d265925ed9c141d8335","abstract_canon_sha256":"b772176406a896fa060829877a270ffb9bbd53959c23814ce580be078bc54a53"},"schema_version":"1.0"},"canonical_sha256":"6d6edf00f7da84c68cbd61c0b9bed8e53dbaa5c5f01f66f9b46e49f92cdf1268","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:37.536401Z","signature_b64":"rnti/H4LijXYGzP5Q12HBwPvOT+1YyKSNowE8qBaTJKIIsEw1C4MZtaT1ttYgCioOXc6Ogm8Hvo0VaYur9GtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d6edf00f7da84c68cbd61c0b9bed8e53dbaa5c5f01f66f9b46e49f92cdf1268","last_reissued_at":"2026-05-17T23:55:37.535960Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:37.535960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08256","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HOT6rvgN2r3GVSUzu3U/2FFdClxQEG2IyjE3e7jrB1aEio9okiX6zFIRyPpbmAEedNsxV5KymkLdbIG4iisBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:58:41.142431Z"},"content_sha256":"5ca6beb08c5f5072ea549d2cbb68e79fdf959152d4d24adeac7e0eea4e4e8e7b","schema_version":"1.0","event_id":"sha256:5ca6beb08c5f5072ea549d2cbb68e79fdf959152d4d24adeac7e0eea4e4e8e7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NVXN6AHX3KCMNDF5MHALTPWY4U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Batch Training for LSTM and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Chris Ying, James Demmel, Jonathan Hseu, Kurt Keutzer, Yang You","submitted_at":"2019-01-24T07:10:33Z","abstract_excerpt":"Large-batch training approaches have enabled researchers to utilize large-scale distributed processing and greatly accelerate deep-neural net (DNN) training. For example, by scaling the batch size from 256 to 32K, researchers have been able to reduce the training time of ResNet50 on ImageNet from 29 hours to 2.2 minutes (Ying et al., 2018). In this paper, we propose a new approach called linear-epoch gradual-warmup (LEGW) for better large-batch training. With LEGW, we are able to conduct large-batch training for both CNNs and RNNs with the Sqrt Scaling scheme. LEGW enables Sqrt Scaling scheme "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08256","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/q5glrJmpholCdlyW7ugCkk29ke9DnrLMShn6EyT/pHrGyI4Pw7nd7ZbfIZ0tFEoizP+wlexeRdUtxbfJ+4iDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:58:41.143145Z"},"content_sha256":"a68c813e012a4a9c894e24db830b5cec37cb2028c228105cde706c31973993da","schema_version":"1.0","event_id":"sha256:a68c813e012a4a9c894e24db830b5cec37cb2028c228105cde706c31973993da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVXN6AHX3KCMNDF5MHALTPWY4U/bundle.json","state_url":"https://pith.science/pith/NVXN6AHX3KCMNDF5MHALTPWY4U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVXN6AHX3KCMNDF5MHALTPWY4U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T23:58:41Z","links":{"resolver":"https://pith.science/pith/NVXN6AHX3KCMNDF5MHALTPWY4U","bundle":"https://pith.science/pith/NVXN6AHX3KCMNDF5MHALTPWY4U/bundle.json","state":"https://pith.science/pith/NVXN6AHX3KCMNDF5MHALTPWY4U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVXN6AHX3KCMNDF5MHALTPWY4U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NVXN6AHX3KCMNDF5MHALTPWY4U","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":"b772176406a896fa060829877a270ffb9bbd53959c23814ce580be078bc54a53","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T07:10:33Z","title_canon_sha256":"ffa2a8d9e282bbbc965231335e3c28a6dfe46f144c828d265925ed9c141d8335"},"schema_version":"1.0","source":{"id":"1901.08256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08256","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08256v1","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08256","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"NVXN6AHX3KCM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NVXN6AHX3KCMNDF5","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NVXN6AHX","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:a68c813e012a4a9c894e24db830b5cec37cb2028c228105cde706c31973993da","target":"graph","created_at":"2026-05-17T23:55:37Z","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"},"paper":{"abstract_excerpt":"Large-batch training approaches have enabled researchers to utilize large-scale distributed processing and greatly accelerate deep-neural net (DNN) training. For example, by scaling the batch size from 256 to 32K, researchers have been able to reduce the training time of ResNet50 on ImageNet from 29 hours to 2.2 minutes (Ying et al., 2018). In this paper, we propose a new approach called linear-epoch gradual-warmup (LEGW) for better large-batch training. With LEGW, we are able to conduct large-batch training for both CNNs and RNNs with the Sqrt Scaling scheme. LEGW enables Sqrt Scaling scheme ","authors_text":"Cho-Jui Hsieh, Chris Ying, James Demmel, Jonathan Hseu, Kurt Keutzer, Yang You","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T07:10:33Z","title":"Large-Batch Training for LSTM and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08256","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":"sha256:5ca6beb08c5f5072ea549d2cbb68e79fdf959152d4d24adeac7e0eea4e4e8e7b","target":"record","created_at":"2026-05-17T23:55:37Z","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":"b772176406a896fa060829877a270ffb9bbd53959c23814ce580be078bc54a53","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T07:10:33Z","title_canon_sha256":"ffa2a8d9e282bbbc965231335e3c28a6dfe46f144c828d265925ed9c141d8335"},"schema_version":"1.0","source":{"id":"1901.08256","kind":"arxiv","version":1}},"canonical_sha256":"6d6edf00f7da84c68cbd61c0b9bed8e53dbaa5c5f01f66f9b46e49f92cdf1268","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d6edf00f7da84c68cbd61c0b9bed8e53dbaa5c5f01f66f9b46e49f92cdf1268","first_computed_at":"2026-05-17T23:55:37.535960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:37.535960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rnti/H4LijXYGzP5Q12HBwPvOT+1YyKSNowE8qBaTJKIIsEw1C4MZtaT1ttYgCioOXc6Ogm8Hvo0VaYur9GtBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:37.536401Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ca6beb08c5f5072ea549d2cbb68e79fdf959152d4d24adeac7e0eea4e4e8e7b","sha256:a68c813e012a4a9c894e24db830b5cec37cb2028c228105cde706c31973993da"],"state_sha256":"79dd1e973741bba79efa1a6eefafe691993f11cd9b09910b547f9d3bec36d0cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVc6f5bTJZC5TNZ+/EWgm/MEHGcG8a+el4ytm5JVAtXt5MpBpfnMm9uIRMz/77MnmHzOw3LLCg4JFeRx38/AAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T23:58:41.146795Z","bundle_sha256":"082a650e0211044e43aa8be09fa72207c19be3614ff29eea12ce263ac93c8dff"}}