{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GBWPVJTUSPAND2PW27LMQXGUSC","short_pith_number":"pith:GBWPVJTU","schema_version":"1.0","canonical_sha256":"306cfaa67493c0d1e9f6d7d6c85cd4908ad1a84e3b39ba33b297ca5b29278593","source":{"kind":"arxiv","id":"2004.14021","version":3},"attestation_state":"computed","paper":{"title":"Multiscale Collaborative Deep Models for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heng Yu, Rongxiang Weng, Weihua Luo, Xiangpeng Wei, Yue Hu, Yue Zhang","submitted_at":"2020-04-29T08:36:08Z","abstract_excerpt":"Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train. In this paper, we present a MultiScale Collaborative (MSC) framework to ease the training of NMT models that are substantially deeper than those used previously. We explicitly boost the gradient back-propagation from top to bottom levels by introducing a block-scale collaboration mechanism into deep NMT models. Then, instead of forcing the whole encoder stack directly learns a desired representation, we let each encoder block learns a fine-grained 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":"2004.14021","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T08:36:08Z","cross_cats_sorted":[],"title_canon_sha256":"73550ea83c474bdb85c1bd7a2c4a081cc34b2ecd451550ce783625e7666523d8","abstract_canon_sha256":"8846f5bef0c4b7cc878582f26ca6138877ba1f3d3b528d96358ea89f75dd9751"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:40.660372Z","signature_b64":"/D3aV5aeO/aO5hLoB7yacJ8ZBdLEF7QY6jrH3FOXP/Ng6++XgVEcz8sjvludFT+co/zYiRbws134yXl+C+IVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"306cfaa67493c0d1e9f6d7d6c85cd4908ad1a84e3b39ba33b297ca5b29278593","last_reissued_at":"2026-07-05T01:01:40.659880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:40.659880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiscale Collaborative Deep Models for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heng Yu, Rongxiang Weng, Weihua Luo, Xiangpeng Wei, Yue Hu, Yue Zhang","submitted_at":"2020-04-29T08:36:08Z","abstract_excerpt":"Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train. In this paper, we present a MultiScale Collaborative (MSC) framework to ease the training of NMT models that are substantially deeper than those used previously. We explicitly boost the gradient back-propagation from top to bottom levels by introducing a block-scale collaboration mechanism into deep NMT models. Then, instead of forcing the whole encoder stack directly learns a desired representation, we let each encoder block learns a fine-grained r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14021","kind":"arxiv","version":3},"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/2004.14021/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":"2004.14021","created_at":"2026-07-05T01:01:40.659942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14021v3","created_at":"2026-07-05T01:01:40.659942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14021","created_at":"2026-07-05T01:01:40.659942+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBWPVJTUSPAN","created_at":"2026-07-05T01:01:40.659942+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBWPVJTUSPAND2PW","created_at":"2026-07-05T01:01:40.659942+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBWPVJTU","created_at":"2026-07-05T01:01:40.659942+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/GBWPVJTUSPAND2PW27LMQXGUSC","json":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC.json","graph_json":"https://pith.science/api/pith-number/GBWPVJTUSPAND2PW27LMQXGUSC/graph.json","events_json":"https://pith.science/api/pith-number/GBWPVJTUSPAND2PW27LMQXGUSC/events.json","paper":"https://pith.science/paper/GBWPVJTU"},"agent_actions":{"view_html":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC","download_json":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC.json","view_paper":"https://pith.science/paper/GBWPVJTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14021&json=true","fetch_graph":"https://pith.science/api/pith-number/GBWPVJTUSPAND2PW27LMQXGUSC/graph.json","fetch_events":"https://pith.science/api/pith-number/GBWPVJTUSPAND2PW27LMQXGUSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC/action/storage_attestation","attest_author":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC/action/author_attestation","sign_citation":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC/action/citation_signature","submit_replication":"https://pith.science/pith/GBWPVJTUSPAND2PW27LMQXGUSC/action/replication_record"}},"created_at":"2026-07-05T01:01:40.659942+00:00","updated_at":"2026-07-05T01:01:40.659942+00:00"}