{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:3ES5P3I5MWYJFU2ZRXKC6IYG2C","short_pith_number":"pith:3ES5P3I5","schema_version":"1.0","canonical_sha256":"d925d7ed1d65b092d3598dd42f2306d083c8ce74c59319e812599937cbf9c06a","source":{"kind":"arxiv","id":"1312.6186","version":1},"attestation_state":"computed","paper":{"title":"GPU Asynchronous Stochastic Gradient Descent to Speed Up Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Hailin Jin, Jianchao Yang, Thomas Huang, Thomas Paine, Zhe Lin","submitted_at":"2013-12-21T00:56:56Z","abstract_excerpt":"The ability to train large-scale neural networks has resulted in state-of-the-art performance in many areas of computer vision. These results have largely come from computational break throughs of two forms: model parallelism, e.g. GPU accelerated training, which has seen quick adoption in computer vision circles, and data parallelism, e.g. A-SGD, whose large scale has been used mostly in industry. We report early experiments with a system that makes use of both model parallelism and data parallelism, we call GPU A-SGD. We show using GPU A-SGD it is possible to speed up training of large convo"},"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":"1312.6186","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-12-21T00:56:56Z","cross_cats_sorted":["cs.DC","cs.LG","cs.NE"],"title_canon_sha256":"de7a9ae3034f0127366d42a131b23533463e160bca8f4a35fcb73305ad4777c7","abstract_canon_sha256":"091ee2276f519e4b02f2e6b1274a333e572fda910959ec3a201f9f5a221950fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:04:05.848211Z","signature_b64":"lBjxH1PoK2rXHXi0ZJHvj/eVAZlmRGb4r05a/brsh9EOHDrr4cRljf5uzGgvIjRtQb+r4AoC0qyuDH2AldRnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d925d7ed1d65b092d3598dd42f2306d083c8ce74c59319e812599937cbf9c06a","last_reissued_at":"2026-05-18T03:04:05.847744Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:04:05.847744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPU Asynchronous Stochastic Gradient Descent to Speed Up Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Hailin Jin, Jianchao Yang, Thomas Huang, Thomas Paine, Zhe Lin","submitted_at":"2013-12-21T00:56:56Z","abstract_excerpt":"The ability to train large-scale neural networks has resulted in state-of-the-art performance in many areas of computer vision. These results have largely come from computational break throughs of two forms: model parallelism, e.g. GPU accelerated training, which has seen quick adoption in computer vision circles, and data parallelism, e.g. A-SGD, whose large scale has been used mostly in industry. We report early experiments with a system that makes use of both model parallelism and data parallelism, we call GPU A-SGD. We show using GPU A-SGD it is possible to speed up training of large convo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.6186","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1312.6186","created_at":"2026-05-18T03:04:05.847812+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.6186v1","created_at":"2026-05-18T03:04:05.847812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.6186","created_at":"2026-05-18T03:04:05.847812+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ES5P3I5MWYJ","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ES5P3I5MWYJFU2Z","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ES5P3I5","created_at":"2026-05-18T12:27:32.513160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16208","citing_title":"Algorithmic Strategies for Sustainable Reuse of Neural Network Accelerators with Permanent Faults","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C","json":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C.json","graph_json":"https://pith.science/api/pith-number/3ES5P3I5MWYJFU2ZRXKC6IYG2C/graph.json","events_json":"https://pith.science/api/pith-number/3ES5P3I5MWYJFU2ZRXKC6IYG2C/events.json","paper":"https://pith.science/paper/3ES5P3I5"},"agent_actions":{"view_html":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C","download_json":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C.json","view_paper":"https://pith.science/paper/3ES5P3I5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.6186&json=true","fetch_graph":"https://pith.science/api/pith-number/3ES5P3I5MWYJFU2ZRXKC6IYG2C/graph.json","fetch_events":"https://pith.science/api/pith-number/3ES5P3I5MWYJFU2ZRXKC6IYG2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C/action/storage_attestation","attest_author":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C/action/author_attestation","sign_citation":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C/action/citation_signature","submit_replication":"https://pith.science/pith/3ES5P3I5MWYJFU2ZRXKC6IYG2C/action/replication_record"}},"created_at":"2026-05-18T03:04:05.847812+00:00","updated_at":"2026-05-18T03:04:05.847812+00:00"}