{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JIF2FLP5PLQA7RR7UO2HW6GIGR","short_pith_number":"pith:JIF2FLP5","schema_version":"1.0","canonical_sha256":"4a0ba2adfd7ae00fc63fa3b47b78c83467e90f309a833211a6d67c028a517d13","source":{"kind":"arxiv","id":"1611.04581","version":1},"attestation_state":"computed","paper":{"title":"How to scale distributed deep learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Forrest Iandola, Kurt Keutzer, Peter H. Jin, Qiaochu Yuan","submitted_at":"2016-11-14T20:59:54Z","abstract_excerpt":"Training time on large datasets for deep neural networks is the principal workflow bottleneck in a number of important applications of deep learning, such as object classification and detection in automatic driver assistance systems (ADAS). To minimize training time, the training of a deep neural network must be scaled beyond a single machine to as many machines as possible by distributing the optimization method used for training. While a number of approaches have been proposed for distributed stochastic gradient descent (SGD), at the current time synchronous approaches to distributed SGD app"},"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":"1611.04581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-14T20:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"36f6ab8c78eab5d9ec98a1e255585bfd3c148d9bbaed01c6aec8b3605e946792","abstract_canon_sha256":"3285bf3e12cd1a256d5219ad4273857358bab719abb0d5ee5ea9b9b8738e28f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:12.752814Z","signature_b64":"45/Hi7+vzoOnF7IsbOwEW/P4M053qIpzdKld7RENlDPiCCn12gJ146VRa5uJ6dLQPPXOvaJhihf0Ob3XegRiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a0ba2adfd7ae00fc63fa3b47b78c83467e90f309a833211a6d67c028a517d13","last_reissued_at":"2026-05-18T00:59:12.752130Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:12.752130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to scale distributed deep learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Forrest Iandola, Kurt Keutzer, Peter H. Jin, Qiaochu Yuan","submitted_at":"2016-11-14T20:59:54Z","abstract_excerpt":"Training time on large datasets for deep neural networks is the principal workflow bottleneck in a number of important applications of deep learning, such as object classification and detection in automatic driver assistance systems (ADAS). To minimize training time, the training of a deep neural network must be scaled beyond a single machine to as many machines as possible by distributing the optimization method used for training. While a number of approaches have been proposed for distributed stochastic gradient descent (SGD), at the current time synchronous approaches to distributed SGD app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04581","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":"1611.04581","created_at":"2026-05-18T00:59:12.752251+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04581v1","created_at":"2026-05-18T00:59:12.752251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04581","created_at":"2026-05-18T00:59:12.752251+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIF2FLP5PLQA","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIF2FLP5PLQA7RR7","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIF2FLP5","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR","json":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR.json","graph_json":"https://pith.science/api/pith-number/JIF2FLP5PLQA7RR7UO2HW6GIGR/graph.json","events_json":"https://pith.science/api/pith-number/JIF2FLP5PLQA7RR7UO2HW6GIGR/events.json","paper":"https://pith.science/paper/JIF2FLP5"},"agent_actions":{"view_html":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR","download_json":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR.json","view_paper":"https://pith.science/paper/JIF2FLP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04581&json=true","fetch_graph":"https://pith.science/api/pith-number/JIF2FLP5PLQA7RR7UO2HW6GIGR/graph.json","fetch_events":"https://pith.science/api/pith-number/JIF2FLP5PLQA7RR7UO2HW6GIGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR/action/storage_attestation","attest_author":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR/action/author_attestation","sign_citation":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR/action/citation_signature","submit_replication":"https://pith.science/pith/JIF2FLP5PLQA7RR7UO2HW6GIGR/action/replication_record"}},"created_at":"2026-05-18T00:59:12.752251+00:00","updated_at":"2026-05-18T00:59:12.752251+00:00"}