{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2M7L5AKVW3WCNHX32YTP2OXI4Q","short_pith_number":"pith:2M7L5AKV","schema_version":"1.0","canonical_sha256":"d33ebe8155b6ec269efbd626fd3ae8e41fa50f38844de11c3413adaf7fae362b","source":{"kind":"arxiv","id":"2112.05387","version":1},"attestation_state":"computed","paper":{"title":"Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS"],"primary_cat":"cs.LG","authors_text":"Bin Dong, Hexin Dong, Jiacheng Sun, Qi Sun, Zewei Chen, Zhenguo Li","submitted_at":"2021-12-10T08:45:35Z","abstract_excerpt":"Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradient to update model parameters, which becomes time-consuming as the network goes deeper. To break the algorithmic locking and exploit synchronous module parallelism in both the forward and backward modes, auxiliary-variable methods have attracted much interest lately but suffer from significant communication overhead and lack of data augmentation. In this work, a novel joint learning framework for training realistic R"},"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":"2112.05387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-10T08:45:35Z","cross_cats_sorted":["cs.AI","math.DS"],"title_canon_sha256":"49057fe761afe20b743b2ed420776d6b65cd865bcabdf2f5c8ce0fdc35f034bb","abstract_canon_sha256":"1f91e3a6522fb9c14356e38b7f411708ee409fccbbe1c98cc2177fa4c55a9079"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:40.787254Z","signature_b64":"rwxdATekh8N0LxzfQvsWoLHe5Y1hZNFsn0iVkpjERcnYK+nq3jRzLc3vqvNDOnBikgQSsAItCWUQnL0OXPQjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d33ebe8155b6ec269efbd626fd3ae8e41fa50f38844de11c3413adaf7fae362b","last_reissued_at":"2026-07-05T03:39:40.786835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:40.786835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS"],"primary_cat":"cs.LG","authors_text":"Bin Dong, Hexin Dong, Jiacheng Sun, Qi Sun, Zewei Chen, Zhenguo Li","submitted_at":"2021-12-10T08:45:35Z","abstract_excerpt":"Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradient to update model parameters, which becomes time-consuming as the network goes deeper. To break the algorithmic locking and exploit synchronous module parallelism in both the forward and backward modes, auxiliary-variable methods have attracted much interest lately but suffer from significant communication overhead and lack of data augmentation. In this work, a novel joint learning framework for training realistic R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05387","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.05387/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2112.05387","created_at":"2026-07-05T03:39:40.786893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.05387v1","created_at":"2026-07-05T03:39:40.786893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05387","created_at":"2026-07-05T03:39:40.786893+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M7L5AKVW3WC","created_at":"2026-07-05T03:39:40.786893+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M7L5AKVW3WCNHX3","created_at":"2026-07-05T03:39:40.786893+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M7L5AKV","created_at":"2026-07-05T03:39:40.786893+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/2M7L5AKVW3WCNHX32YTP2OXI4Q","json":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q.json","graph_json":"https://pith.science/api/pith-number/2M7L5AKVW3WCNHX32YTP2OXI4Q/graph.json","events_json":"https://pith.science/api/pith-number/2M7L5AKVW3WCNHX32YTP2OXI4Q/events.json","paper":"https://pith.science/paper/2M7L5AKV"},"agent_actions":{"view_html":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q","download_json":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q.json","view_paper":"https://pith.science/paper/2M7L5AKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.05387&json=true","fetch_graph":"https://pith.science/api/pith-number/2M7L5AKVW3WCNHX32YTP2OXI4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/2M7L5AKVW3WCNHX32YTP2OXI4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q/action/storage_attestation","attest_author":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q/action/author_attestation","sign_citation":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q/action/citation_signature","submit_replication":"https://pith.science/pith/2M7L5AKVW3WCNHX32YTP2OXI4Q/action/replication_record"}},"created_at":"2026-07-05T03:39:40.786893+00:00","updated_at":"2026-07-05T03:39:40.786893+00:00"}