{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Q3LTR7DSQYEPTAYIAX45XJDNTZ","short_pith_number":"pith:Q3LTR7DS","schema_version":"1.0","canonical_sha256":"86d738fc728608f9830805f9dba46d9e4eba0a4453b1292713e9ba7baa0072db","source":{"kind":"arxiv","id":"2010.08265","version":1},"attestation_state":"computed","paper":{"title":"Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingbo Zhu, Qiang Wang, Tong Xiao","submitted_at":"2020-10-16T09:37:27Z","abstract_excerpt":"The standard neural machine translation model can only decode with the same depth configuration as training. Restricted by this feature, we have to deploy models of various sizes to maintain the same translation latency, because the hardware conditions on different terminal devices (e.g., mobile phones) may vary greatly. Such individual training leads to increased model maintenance costs and slower model iterations, especially for the industry. In this work, we propose to use multi-task learning to train a flexible depth model that can adapt to different depth configurations during inference. "},"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":"2010.08265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-16T09:37:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6ebf29f40a4479e65a034ca42b671429e9667bcec00488eb7cffa6d561717315","abstract_canon_sha256":"b1c305e24f0aa2b63f7f48ec785919d622791e0e3e295a6c096d2753d9b99dd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:33.062898Z","signature_b64":"NpQlgYgEhXTVPm4GFBqX75Cu77XmrckIH5G6j1NFCE3NV/XZSyp4NN2dHD1DsjDjunOS0aCQCbAZ4sYGGLlwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86d738fc728608f9830805f9dba46d9e4eba0a4453b1292713e9ba7baa0072db","last_reissued_at":"2026-07-05T01:43:33.062384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:33.062384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingbo Zhu, Qiang Wang, Tong Xiao","submitted_at":"2020-10-16T09:37:27Z","abstract_excerpt":"The standard neural machine translation model can only decode with the same depth configuration as training. Restricted by this feature, we have to deploy models of various sizes to maintain the same translation latency, because the hardware conditions on different terminal devices (e.g., mobile phones) may vary greatly. Such individual training leads to increased model maintenance costs and slower model iterations, especially for the industry. In this work, we propose to use multi-task learning to train a flexible depth model that can adapt to different depth configurations during inference. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08265","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/2010.08265/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":"2010.08265","created_at":"2026-07-05T01:43:33.062447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08265v1","created_at":"2026-07-05T01:43:33.062447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08265","created_at":"2026-07-05T01:43:33.062447+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3LTR7DSQYEP","created_at":"2026-07-05T01:43:33.062447+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3LTR7DSQYEPTAYI","created_at":"2026-07-05T01:43:33.062447+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3LTR7DS","created_at":"2026-07-05T01:43:33.062447+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/Q3LTR7DSQYEPTAYIAX45XJDNTZ","json":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ.json","graph_json":"https://pith.science/api/pith-number/Q3LTR7DSQYEPTAYIAX45XJDNTZ/graph.json","events_json":"https://pith.science/api/pith-number/Q3LTR7DSQYEPTAYIAX45XJDNTZ/events.json","paper":"https://pith.science/paper/Q3LTR7DS"},"agent_actions":{"view_html":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ","download_json":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ.json","view_paper":"https://pith.science/paper/Q3LTR7DS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08265&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3LTR7DSQYEPTAYIAX45XJDNTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3LTR7DSQYEPTAYIAX45XJDNTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ/action/storage_attestation","attest_author":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ/action/author_attestation","sign_citation":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ/action/citation_signature","submit_replication":"https://pith.science/pith/Q3LTR7DSQYEPTAYIAX45XJDNTZ/action/replication_record"}},"created_at":"2026-07-05T01:43:33.062447+00:00","updated_at":"2026-07-05T01:43:33.062447+00:00"}