{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5XCC3MLWQZ263C3L2O54KO3NW6","short_pith_number":"pith:5XCC3MLW","schema_version":"1.0","canonical_sha256":"edc42db1768675ed8b6bd3bbc53b6db7a371452aa2537020f10df5ff4fe01fbc","source":{"kind":"arxiv","id":"1711.04291","version":2},"attestation_state":"computed","paper":{"title":"Scale out for large minibatch SGD: Residual network training on ImageNet-1K with improved accuracy and reduced time to train","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Damian Podareanu, Valeriu Codreanu, Vikram Saletore","submitted_at":"2017-11-12T13:26:31Z","abstract_excerpt":"For the past 5 years, the ILSVRC competition and the ImageNet dataset have attracted a lot of interest from the Computer Vision community, allowing for state-of-the-art accuracy to grow tremendously. This should be credited to the use of deep artificial neural network designs. As these became more complex, the storage, bandwidth, and compute requirements increased. This means that with a non-distributed approach, even when using the most high-density server available, the training process may take weeks, making it prohibitive. Furthermore, as datasets grow, the representation learning potentia"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1711.04291","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-12T13:26:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8bc92824a05fd137e0be22f7a6f515e44e9acfe3ba18d4fd5efc1a78586bf1ac","abstract_canon_sha256":"1e35d06f6d50ddd4e7cbaa12e98c10462940caa11202013b1d821e8fb8c698df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:27.509049Z","signature_b64":"un05EF4QqGumjYNvAwtz/BwxVOQIUsdEtjcSdz8A2h0Gxq0jJNnFaBKQzq9UoEfstVG4S/k5JUrlT5XvgIUeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc42db1768675ed8b6bd3bbc53b6db7a371452aa2537020f10df5ff4fe01fbc","last_reissued_at":"2026-05-18T00:30:27.508251Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:27.508251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale out for large minibatch SGD: Residual network training on ImageNet-1K with improved accuracy and reduced time to train","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Damian Podareanu, Valeriu Codreanu, Vikram Saletore","submitted_at":"2017-11-12T13:26:31Z","abstract_excerpt":"For the past 5 years, the ILSVRC competition and the ImageNet dataset have attracted a lot of interest from the Computer Vision community, allowing for state-of-the-art accuracy to grow tremendously. This should be credited to the use of deep artificial neural network designs. As these became more complex, the storage, bandwidth, and compute requirements increased. This means that with a non-distributed approach, even when using the most high-density server available, the training process may take weeks, making it prohibitive. Furthermore, as datasets grow, the representation learning potentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04291","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.04291","created_at":"2026-05-18T00:30:27.508435+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04291v2","created_at":"2026-05-18T00:30:27.508435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04291","created_at":"2026-05-18T00:30:27.508435+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XCC3MLWQZ26","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XCC3MLWQZ263C3L","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XCC3MLW","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10822","citing_title":"Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"1904.00962","citing_title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6","json":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6.json","graph_json":"https://pith.science/api/pith-number/5XCC3MLWQZ263C3L2O54KO3NW6/graph.json","events_json":"https://pith.science/api/pith-number/5XCC3MLWQZ263C3L2O54KO3NW6/events.json","paper":"https://pith.science/paper/5XCC3MLW"},"agent_actions":{"view_html":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6","download_json":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6.json","view_paper":"https://pith.science/paper/5XCC3MLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04291&json=true","fetch_graph":"https://pith.science/api/pith-number/5XCC3MLWQZ263C3L2O54KO3NW6/graph.json","fetch_events":"https://pith.science/api/pith-number/5XCC3MLWQZ263C3L2O54KO3NW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6/action/storage_attestation","attest_author":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6/action/author_attestation","sign_citation":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6/action/citation_signature","submit_replication":"https://pith.science/pith/5XCC3MLWQZ263C3L2O54KO3NW6/action/replication_record"}},"created_at":"2026-05-18T00:30:27.508435+00:00","updated_at":"2026-05-18T00:30:27.508435+00:00"}