{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LTFJHQLBMHTUZPUTURSIAIYJVM","short_pith_number":"pith:LTFJHQLB","schema_version":"1.0","canonical_sha256":"5cca93c16161e74cbe93a464802309ab3e39c1f54cf2cc52eb3ceca99d6e1f12","source":{"kind":"arxiv","id":"1702.01802","version":2},"attestation_state":"computed","paper":{"title":"Ensemble Distillation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baskaran Sankaran, Markus Freitag, Yaser Al-Onaizan","submitted_at":"2017-02-06T21:49:12Z","abstract_excerpt":"Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a smaller model speeds up this process. We demonstrate how to transfer the translation quality of an ensemble and an oracle BLEU teacher network into a single NMT system. Further, we present translation improvements from a teacher network that has the same architecture and dimensions of the student network. As the training of the student model is still expensive"},"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":"1702.01802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-06T21:49:12Z","cross_cats_sorted":[],"title_canon_sha256":"d11ec81be3e3e5d4ce5bbc8b15f2b5a15855053728dd8d5185d6a52a04b97ab5","abstract_canon_sha256":"8cc6e179c4e5fe575b648605cb8ad52210ce575409bbb5810fff444f45607f5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:30.427120Z","signature_b64":"oRqzk05XajhG9lzWQzUspPZ6pY1nxX7kNCZFR6sAmIk4TVUdJJHINXl2injjaHtV+jiNiQe2qBUksvwOJBsYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cca93c16161e74cbe93a464802309ab3e39c1f54cf2cc52eb3ceca99d6e1f12","last_reissued_at":"2026-05-18T00:38:30.426589Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:30.426589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Distillation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baskaran Sankaran, Markus Freitag, Yaser Al-Onaizan","submitted_at":"2017-02-06T21:49:12Z","abstract_excerpt":"Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a smaller model speeds up this process. We demonstrate how to transfer the translation quality of an ensemble and an oracle BLEU teacher network into a single NMT system. Further, we present translation improvements from a teacher network that has the same architecture and dimensions of the student network. As the training of the student model is still expensive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01802","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":"1702.01802","created_at":"2026-05-18T00:38:30.426670+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.01802v2","created_at":"2026-05-18T00:38:30.426670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01802","created_at":"2026-05-18T00:38:30.426670+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTFJHQLBMHTU","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTFJHQLBMHTUZPUT","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTFJHQLB","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2305.15717","citing_title":"The False Promise of Imitating Proprietary LLMs","ref_index":149,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM","json":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM.json","graph_json":"https://pith.science/api/pith-number/LTFJHQLBMHTUZPUTURSIAIYJVM/graph.json","events_json":"https://pith.science/api/pith-number/LTFJHQLBMHTUZPUTURSIAIYJVM/events.json","paper":"https://pith.science/paper/LTFJHQLB"},"agent_actions":{"view_html":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM","download_json":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM.json","view_paper":"https://pith.science/paper/LTFJHQLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.01802&json=true","fetch_graph":"https://pith.science/api/pith-number/LTFJHQLBMHTUZPUTURSIAIYJVM/graph.json","fetch_events":"https://pith.science/api/pith-number/LTFJHQLBMHTUZPUTURSIAIYJVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM/action/storage_attestation","attest_author":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM/action/author_attestation","sign_citation":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM/action/citation_signature","submit_replication":"https://pith.science/pith/LTFJHQLBMHTUZPUTURSIAIYJVM/action/replication_record"}},"created_at":"2026-05-18T00:38:30.426670+00:00","updated_at":"2026-05-18T00:38:30.426670+00:00"}