{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XUIYFFGWLSUYVYZT22I3HFUDU5","short_pith_number":"pith:XUIYFFGW","schema_version":"1.0","canonical_sha256":"bd118294d65ca98ae333d691b39683a77629c9b101f3df0a8088e9719e67a749","source":{"kind":"arxiv","id":"2112.11642","version":1},"attestation_state":"computed","paper":{"title":"Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Su, Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Lizhi Lei, Minghan Wang, Min Zhang, Shimin Tao, Yimeng Chen, Yuxia Wang, Zhanglin Wu, Zhengzhe Yu, Zongyao Li","submitted_at":"2021-12-22T03:13:45Z","abstract_excerpt":"Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encoder layers exceeds 18. Worse still, deeper networks consume a lot of memory, making it impossible to train efficiently. In this paper, we present Symbiosis Networks, which include a full network as the Symbiosis Main Network (M-Net) and another shared sub-network with the same structure but less layers as the Symbiotic Sub Network (S-Net). We adopt Symbiosis Networks on Transformer-deep (m-n) architecture and define a"},"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":"2112.11642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T03:13:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"310e7d4f1f3f48a12100ca52a97427b0d95844ef0d4b57a6f408add7f92da893","abstract_canon_sha256":"fae9b0e6b97baa79add3dfb1572234c71f54807e388ad01f029e700a3ca62df9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:09.205877Z","signature_b64":"XT/mWfe1+KYy0dP7vTdy9wq85l8kbh7cJIXYpwvkNdBpjrfDU+Fx8O9gFL+QfdWyQEcR6pDZ4kXQfAWpNRzQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd118294d65ca98ae333d691b39683a77629c9b101f3df0a8088e9719e67a749","last_reissued_at":"2026-07-05T03:43:09.205407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:09.205407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Su, Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Lizhi Lei, Minghan Wang, Min Zhang, Shimin Tao, Yimeng Chen, Yuxia Wang, Zhanglin Wu, Zhengzhe Yu, Zongyao Li","submitted_at":"2021-12-22T03:13:45Z","abstract_excerpt":"Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encoder layers exceeds 18. Worse still, deeper networks consume a lot of memory, making it impossible to train efficiently. In this paper, we present Symbiosis Networks, which include a full network as the Symbiosis Main Network (M-Net) and another shared sub-network with the same structure but less layers as the Symbiotic Sub Network (S-Net). We adopt Symbiosis Networks on Transformer-deep (m-n) architecture and define a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11642","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/2112.11642/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":"2112.11642","created_at":"2026-07-05T03:43:09.205482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11642v1","created_at":"2026-07-05T03:43:09.205482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11642","created_at":"2026-07-05T03:43:09.205482+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUIYFFGWLSUY","created_at":"2026-07-05T03:43:09.205482+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUIYFFGWLSUYVYZT","created_at":"2026-07-05T03:43:09.205482+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUIYFFGW","created_at":"2026-07-05T03:43:09.205482+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/XUIYFFGWLSUYVYZT22I3HFUDU5","json":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5.json","graph_json":"https://pith.science/api/pith-number/XUIYFFGWLSUYVYZT22I3HFUDU5/graph.json","events_json":"https://pith.science/api/pith-number/XUIYFFGWLSUYVYZT22I3HFUDU5/events.json","paper":"https://pith.science/paper/XUIYFFGW"},"agent_actions":{"view_html":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5","download_json":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5.json","view_paper":"https://pith.science/paper/XUIYFFGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11642&json=true","fetch_graph":"https://pith.science/api/pith-number/XUIYFFGWLSUYVYZT22I3HFUDU5/graph.json","fetch_events":"https://pith.science/api/pith-number/XUIYFFGWLSUYVYZT22I3HFUDU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5/action/storage_attestation","attest_author":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5/action/author_attestation","sign_citation":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5/action/citation_signature","submit_replication":"https://pith.science/pith/XUIYFFGWLSUYVYZT22I3HFUDU5/action/replication_record"}},"created_at":"2026-07-05T03:43:09.205482+00:00","updated_at":"2026-07-05T03:43:09.205482+00:00"}