{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7JGWWAXJVI4QGCOKQUJIWSS4EX","short_pith_number":"pith:7JGWWAXJ","canonical_record":{"source":{"id":"1712.03298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-08T22:26:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"46c91467e9b84d6fe18623af85bd80abf030ac0f59d5ec1822d1328ae4a24f64","abstract_canon_sha256":"df01f8443c10e1c96080360ac04b785270dbf5c4592910e85565a22ff57110c1"},"schema_version":"1.0"},"canonical_sha256":"fa4d6b02e9aa390309ca85128b4a5c25db9b3c26aece35e9dddc1f30cd0f47b1","source":{"kind":"arxiv","id":"1712.03298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03298","created_at":"2026-05-18T00:28:21Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03298v1","created_at":"2026-05-18T00:28:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03298","created_at":"2026-05-18T00:28:21Z"},{"alias_kind":"pith_short_12","alias_value":"7JGWWAXJVI4Q","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7JGWWAXJVI4QGCOK","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7JGWWAXJ","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7JGWWAXJVI4QGCOKQUJIWSS4EX","target":"record","payload":{"canonical_record":{"source":{"id":"1712.03298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-08T22:26:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"46c91467e9b84d6fe18623af85bd80abf030ac0f59d5ec1822d1328ae4a24f64","abstract_canon_sha256":"df01f8443c10e1c96080360ac04b785270dbf5c4592910e85565a22ff57110c1"},"schema_version":"1.0"},"canonical_sha256":"fa4d6b02e9aa390309ca85128b4a5c25db9b3c26aece35e9dddc1f30cd0f47b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:21.735181Z","signature_b64":"tDKAyEuJBT1CCy3hWcGqt3ZpgCmXnLykLxfOPUYHPaJvnXys+mIZctzN03fxeGRG2keaXg7B28WyAmpRYwt/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa4d6b02e9aa390309ca85128b4a5c25db9b3c26aece35e9dddc1f30cd0f47b1","last_reissued_at":"2026-05-18T00:28:21.734613Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:21.734613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.03298","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":"2026-05-18T00:28:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7X9gfbanb+Wn4roNYzMug4Po8CupSAXA0B95duCps/znSNImikCVyBI59drbO4c4XEhOf9QVMOThcD37WqwgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:51:58.495412Z"},"content_sha256":"1117f56106ca2a0387544b98285a3415a3ac799abd1a2cab492a8412be110d33","schema_version":"1.0","event_id":"sha256:1117f56106ca2a0387544b98285a3415a3ac799abd1a2cab492a8412be110d33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7JGWWAXJVI4QGCOKQUJIWSS4EX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rif A. Saurous, Shankar Krishnan, Ying Xiao","submitted_at":"2017-12-08T22:26:58Z","abstract_excerpt":"Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we present a large batch, stochastic optimization algorithm that is both faster than widely used algorithms for fixed amounts of computation, and also scales up substantially better as more computational resources become available. Our algorithm implicitly computes the inverse Hessian of each mini-batch to produce descent directions; we do so without either an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03298","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":"2026-05-18T00:28:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kvd7vmVENbVtdMPjj/hm5z13NQ0WNhU0QMyuO5ZFMxZ54zCklKFM8cUsXmus62i/l73XBCnMnQS9KdRfXT2TBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:51:58.496119Z"},"content_sha256":"e216a01d5a07c858bed4df5003044495384b0e446f24b3d2468e398349cc469c","schema_version":"1.0","event_id":"sha256:e216a01d5a07c858bed4df5003044495384b0e446f24b3d2468e398349cc469c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7JGWWAXJVI4QGCOKQUJIWSS4EX/bundle.json","state_url":"https://pith.science/pith/7JGWWAXJVI4QGCOKQUJIWSS4EX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7JGWWAXJVI4QGCOKQUJIWSS4EX/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":"2026-05-30T14:51:58Z","links":{"resolver":"https://pith.science/pith/7JGWWAXJVI4QGCOKQUJIWSS4EX","bundle":"https://pith.science/pith/7JGWWAXJVI4QGCOKQUJIWSS4EX/bundle.json","state":"https://pith.science/pith/7JGWWAXJVI4QGCOKQUJIWSS4EX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7JGWWAXJVI4QGCOKQUJIWSS4EX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7JGWWAXJVI4QGCOKQUJIWSS4EX","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":"df01f8443c10e1c96080360ac04b785270dbf5c4592910e85565a22ff57110c1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-08T22:26:58Z","title_canon_sha256":"46c91467e9b84d6fe18623af85bd80abf030ac0f59d5ec1822d1328ae4a24f64"},"schema_version":"1.0","source":{"id":"1712.03298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03298","created_at":"2026-05-18T00:28:21Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03298v1","created_at":"2026-05-18T00:28:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03298","created_at":"2026-05-18T00:28:21Z"},{"alias_kind":"pith_short_12","alias_value":"7JGWWAXJVI4Q","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7JGWWAXJVI4QGCOK","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7JGWWAXJ","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:e216a01d5a07c858bed4df5003044495384b0e446f24b3d2468e398349cc469c","target":"graph","created_at":"2026-05-18T00:28:21Z","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":"Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we present a large batch, stochastic optimization algorithm that is both faster than widely used algorithms for fixed amounts of computation, and also scales up substantially better as more computational resources become available. Our algorithm implicitly computes the inverse Hessian of each mini-batch to produce descent directions; we do so without either an ","authors_text":"Rif A. Saurous, Shankar Krishnan, Ying Xiao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-08T22:26:58Z","title":"Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03298","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":"sha256:1117f56106ca2a0387544b98285a3415a3ac799abd1a2cab492a8412be110d33","target":"record","created_at":"2026-05-18T00:28:21Z","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":"df01f8443c10e1c96080360ac04b785270dbf5c4592910e85565a22ff57110c1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-08T22:26:58Z","title_canon_sha256":"46c91467e9b84d6fe18623af85bd80abf030ac0f59d5ec1822d1328ae4a24f64"},"schema_version":"1.0","source":{"id":"1712.03298","kind":"arxiv","version":1}},"canonical_sha256":"fa4d6b02e9aa390309ca85128b4a5c25db9b3c26aece35e9dddc1f30cd0f47b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa4d6b02e9aa390309ca85128b4a5c25db9b3c26aece35e9dddc1f30cd0f47b1","first_computed_at":"2026-05-18T00:28:21.734613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:21.734613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tDKAyEuJBT1CCy3hWcGqt3ZpgCmXnLykLxfOPUYHPaJvnXys+mIZctzN03fxeGRG2keaXg7B28WyAmpRYwt/BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:21.735181Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.03298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1117f56106ca2a0387544b98285a3415a3ac799abd1a2cab492a8412be110d33","sha256:e216a01d5a07c858bed4df5003044495384b0e446f24b3d2468e398349cc469c"],"state_sha256":"2455e2074ed3484b72d12eed0f85092e5c84da3470c895cbe81fc35bc9aa651d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VFbiqi5zP8N7MMgT3WBhZEtXUgWt5jk/yZVmXl84smJEKFX7cnJwUS5uerkPisWCGcWj6pBvnSMpE9slixArAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:51:58.499781Z","bundle_sha256":"fd27929e2db9a72d43ab6f5dfec99e748f4afcef35b7b24866fb12f3d4998f61"}}