{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UBNEOXWT47XHT4FZGBTOFFTNBT","short_pith_number":"pith:UBNEOXWT","canonical_record":{"source":{"id":"1707.04822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-16T04:47:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abb761fda133eea2065de944dd2c6d60fd8b505a708a39d2e517c0dbafdcedb0","abstract_canon_sha256":"538006750f25fd3626b3c1b7fb8e65871aef1c96bafb3d9c391dc0568c9e97af"},"schema_version":"1.0"},"canonical_sha256":"a05a475ed3e7ee79f0b93066e2966d0cc8859a32367d0fbd3218fe2d8f75f055","source":{"kind":"arxiv","id":"1707.04822","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.04822","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"1707.04822v2","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04822","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"UBNEOXWT47XH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UBNEOXWT47XHT4FZ","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UBNEOXWT","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UBNEOXWT47XHT4FZGBTOFFTNBT","target":"record","payload":{"canonical_record":{"source":{"id":"1707.04822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-16T04:47:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abb761fda133eea2065de944dd2c6d60fd8b505a708a39d2e517c0dbafdcedb0","abstract_canon_sha256":"538006750f25fd3626b3c1b7fb8e65871aef1c96bafb3d9c391dc0568c9e97af"},"schema_version":"1.0"},"canonical_sha256":"a05a475ed3e7ee79f0b93066e2966d0cc8859a32367d0fbd3218fe2d8f75f055","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:54.657004Z","signature_b64":"dP37xeVRot00KoOzXXdw+8+/++ZvK9GigHyWY4V44BObHeKHeklD59ySd3cFiop0tHsFnrB4rxvkUpXY0qZKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a05a475ed3e7ee79f0b93066e2966d0cc8859a32367d0fbd3218fe2d8f75f055","last_reissued_at":"2026-05-18T00:17:54.656393Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:54.656393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.04822","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LuWDY1grOFNff/3D5lt1bkZNaOjbqfLz8kk+0zt7xAtUn2qQANyFSWz9z02CQCWc3SpkKQMBUDTV5uzjSuMJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T07:20:01.170223Z"},"content_sha256":"a06e732b6cc4fad3563699ea857f767d173bb2c9fe15577b2c0cc3d761e3569c","schema_version":"1.0","event_id":"sha256:a06e732b6cc4fad3563699ea857f767d173bb2c9fe15577b2c0cc3d761e3569c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UBNEOXWT47XHT4FZGBTOFFTNBT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Block-Normalized Gradient Method: An Empirical Study for Training Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adams Wei Yu, Jaime Carbonell, Lei Huang, Qihang Lin, Ruslan Salakhutdinov","submitted_at":"2017-07-16T04:47:22Z","abstract_excerpt":"In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block (layer) of the mini-batch stochastic gradient; 2) selecting appropriate step size to update the decision variable (parameter) towards the negative of the block-normalized gradient. We conduct extensive empirical studies on various non-convex neural network optimization problems, including multi-layer perceptron, convolution neural networks and recurrent neural ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04822","kind":"arxiv","version":2},"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":"2026-05-18T00:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOyGa7iNN0UG0S01TawGnQJ6U4pr5mGJRBGgATbDQ9rq27c4KNCzJLUWCGrJm4GoCt9ISKiShPlz8//1jUxhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T07:20:01.170588Z"},"content_sha256":"59ddeddebf3685658bf692616061f971ef8642e51e2c832f028437dfa37f5f29","schema_version":"1.0","event_id":"sha256:59ddeddebf3685658bf692616061f971ef8642e51e2c832f028437dfa37f5f29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBNEOXWT47XHT4FZGBTOFFTNBT/bundle.json","state_url":"https://pith.science/pith/UBNEOXWT47XHT4FZGBTOFFTNBT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBNEOXWT47XHT4FZGBTOFFTNBT/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":"2026-07-11T07:20:01Z","links":{"resolver":"https://pith.science/pith/UBNEOXWT47XHT4FZGBTOFFTNBT","bundle":"https://pith.science/pith/UBNEOXWT47XHT4FZGBTOFFTNBT/bundle.json","state":"https://pith.science/pith/UBNEOXWT47XHT4FZGBTOFFTNBT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBNEOXWT47XHT4FZGBTOFFTNBT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UBNEOXWT47XHT4FZGBTOFFTNBT","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":"538006750f25fd3626b3c1b7fb8e65871aef1c96bafb3d9c391dc0568c9e97af","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-16T04:47:22Z","title_canon_sha256":"abb761fda133eea2065de944dd2c6d60fd8b505a708a39d2e517c0dbafdcedb0"},"schema_version":"1.0","source":{"id":"1707.04822","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.04822","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"1707.04822v2","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04822","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"UBNEOXWT47XH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UBNEOXWT47XHT4FZ","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UBNEOXWT","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:59ddeddebf3685658bf692616061f971ef8642e51e2c832f028437dfa37f5f29","target":"graph","created_at":"2026-05-18T00:17:54Z","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":"In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block (layer) of the mini-batch stochastic gradient; 2) selecting appropriate step size to update the decision variable (parameter) towards the negative of the block-normalized gradient. We conduct extensive empirical studies on various non-convex neural network optimization problems, including multi-layer perceptron, convolution neural networks and recurrent neural ne","authors_text":"Adams Wei Yu, Jaime Carbonell, Lei Huang, Qihang Lin, Ruslan Salakhutdinov","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-16T04:47:22Z","title":"Block-Normalized Gradient Method: An Empirical Study for Training Deep Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04822","kind":"arxiv","version":2},"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:a06e732b6cc4fad3563699ea857f767d173bb2c9fe15577b2c0cc3d761e3569c","target":"record","created_at":"2026-05-18T00:17:54Z","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":"538006750f25fd3626b3c1b7fb8e65871aef1c96bafb3d9c391dc0568c9e97af","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-16T04:47:22Z","title_canon_sha256":"abb761fda133eea2065de944dd2c6d60fd8b505a708a39d2e517c0dbafdcedb0"},"schema_version":"1.0","source":{"id":"1707.04822","kind":"arxiv","version":2}},"canonical_sha256":"a05a475ed3e7ee79f0b93066e2966d0cc8859a32367d0fbd3218fe2d8f75f055","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a05a475ed3e7ee79f0b93066e2966d0cc8859a32367d0fbd3218fe2d8f75f055","first_computed_at":"2026-05-18T00:17:54.656393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:54.656393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dP37xeVRot00KoOzXXdw+8+/++ZvK9GigHyWY4V44BObHeKHeklD59ySd3cFiop0tHsFnrB4rxvkUpXY0qZKCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:54.657004Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.04822","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a06e732b6cc4fad3563699ea857f767d173bb2c9fe15577b2c0cc3d761e3569c","sha256:59ddeddebf3685658bf692616061f971ef8642e51e2c832f028437dfa37f5f29"],"state_sha256":"96d130d6e1212a6182567ce82524b4a29f1d8574c3825b011391cedddf4e5f12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PH6BFGEje2Sn8cW53miTx1z37H0R42Mh8qhRj5FYESRrymBe0BvFDm9RsidZEJuCFaSwX86dm7AmMPqJ2GCaAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T07:20:01.173045Z","bundle_sha256":"cdb4351758c3e96c85e4282a7a16de5249967501827bf5cab2e66716ffc6d997"}}