{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RN2L4NXCU5ONY4EZHH7ZARU3XU","short_pith_number":"pith:RN2L4NXC","schema_version":"1.0","canonical_sha256":"8b74be36e2a75cdc709939ff90469bbd1018e542b32657544e3359867c89dd97","source":{"kind":"arxiv","id":"1812.10624","version":2},"attestation_state":"computed","paper":{"title":"Stanza: Layer Separation for Distributed Training in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Hong Xu, Xiaorui Wu, Yongqiang Xiong","submitted_at":"2018-12-27T05:01:19Z","abstract_excerpt":"The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact on training time.\n  To tackle the problem, we design a new distributed training system called Stanza. Stanza exploits the fact that in many models such as convolution neural networks, most data exchange is attributed to the fully connected layers, while most computation is carried"},"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":"1812.10624","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-27T05:01:19Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"74fed21921050b563e34a4ecbfb96c4597b817b59079a66fa722594bfe30fefc","abstract_canon_sha256":"fd1356d7bf37ea5e25c5d0f325b866c7478fae0b40c0c2f7bcd142c330642614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:36.202025Z","signature_b64":"iSXxjiaYdASFx5NhDPhmLasYlhacRQ8prsmWuHUjvnP6Puvv66bLY8p83QXhyqNx+yjVdzmmvelHGCiS6TTADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b74be36e2a75cdc709939ff90469bbd1018e542b32657544e3359867c89dd97","last_reissued_at":"2026-05-17T23:56:36.201385Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:36.201385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stanza: Layer Separation for Distributed Training in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Hong Xu, Xiaorui Wu, Yongqiang Xiong","submitted_at":"2018-12-27T05:01:19Z","abstract_excerpt":"The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact on training time.\n  To tackle the problem, we design a new distributed training system called Stanza. Stanza exploits the fact that in many models such as convolution neural networks, most data exchange is attributed to the fully connected layers, while most computation is carried"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10624","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":"1812.10624","created_at":"2026-05-17T23:56:36.201490+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10624v2","created_at":"2026-05-17T23:56:36.201490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10624","created_at":"2026-05-17T23:56:36.201490+00:00"},{"alias_kind":"pith_short_12","alias_value":"RN2L4NXCU5ON","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RN2L4NXCU5ONY4EZ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RN2L4NXC","created_at":"2026-05-18T12:32:50.500415+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/RN2L4NXCU5ONY4EZHH7ZARU3XU","json":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU.json","graph_json":"https://pith.science/api/pith-number/RN2L4NXCU5ONY4EZHH7ZARU3XU/graph.json","events_json":"https://pith.science/api/pith-number/RN2L4NXCU5ONY4EZHH7ZARU3XU/events.json","paper":"https://pith.science/paper/RN2L4NXC"},"agent_actions":{"view_html":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU","download_json":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU.json","view_paper":"https://pith.science/paper/RN2L4NXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10624&json=true","fetch_graph":"https://pith.science/api/pith-number/RN2L4NXCU5ONY4EZHH7ZARU3XU/graph.json","fetch_events":"https://pith.science/api/pith-number/RN2L4NXCU5ONY4EZHH7ZARU3XU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU/action/storage_attestation","attest_author":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU/action/author_attestation","sign_citation":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU/action/citation_signature","submit_replication":"https://pith.science/pith/RN2L4NXCU5ONY4EZHH7ZARU3XU/action/replication_record"}},"created_at":"2026-05-17T23:56:36.201490+00:00","updated_at":"2026-05-17T23:56:36.201490+00:00"}