{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SPCTGQLWZVI42N7CQJYH5VQ47K","short_pith_number":"pith:SPCTGQLW","schema_version":"1.0","canonical_sha256":"93c5334176cd51cd37e282707ed61cfa886348f2585ee718861fe84a34152763","source":{"kind":"arxiv","id":"1808.09465","version":1},"attestation_state":"computed","paper":{"title":"The University of Cambridge's Machine Translation Systems for WMT18","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adria de Gispert, Bill Byrne, Felix Stahlberg","submitted_at":"2018-08-28T18:02:31Z","abstract_excerpt":"The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles."},"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":"1808.09465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T18:02:31Z","cross_cats_sorted":[],"title_canon_sha256":"45ca1fd978f0f694294c5102a9e7d40e01d2b174a9406d5b8ce4b997b2e058bc","abstract_canon_sha256":"024a633df80b8bbbce7a196632c85562ad904c6da46b7abab8d004b210e09160"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:55.522752Z","signature_b64":"Wv1bTS+24k6ZKb2tbakttBhTS+v0LER6KQFw629jKCySuRd2/vwdTgT64fEKA5j7YTrlWzzdgv9RhN0Up+ZJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93c5334176cd51cd37e282707ed61cfa886348f2585ee718861fe84a34152763","last_reissued_at":"2026-05-18T00:06:55.522177Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:55.522177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The University of Cambridge's Machine Translation Systems for WMT18","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adria de Gispert, Bill Byrne, Felix Stahlberg","submitted_at":"2018-08-28T18:02:31Z","abstract_excerpt":"The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09465","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":""},"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":"1808.09465","created_at":"2026-05-18T00:06:55.522273+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09465v1","created_at":"2026-05-18T00:06:55.522273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09465","created_at":"2026-05-18T00:06:55.522273+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPCTGQLWZVI4","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPCTGQLWZVI42N7C","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPCTGQLW","created_at":"2026-05-18T12:32:53.628368+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/SPCTGQLWZVI42N7CQJYH5VQ47K","json":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K.json","graph_json":"https://pith.science/api/pith-number/SPCTGQLWZVI42N7CQJYH5VQ47K/graph.json","events_json":"https://pith.science/api/pith-number/SPCTGQLWZVI42N7CQJYH5VQ47K/events.json","paper":"https://pith.science/paper/SPCTGQLW"},"agent_actions":{"view_html":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K","download_json":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K.json","view_paper":"https://pith.science/paper/SPCTGQLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09465&json=true","fetch_graph":"https://pith.science/api/pith-number/SPCTGQLWZVI42N7CQJYH5VQ47K/graph.json","fetch_events":"https://pith.science/api/pith-number/SPCTGQLWZVI42N7CQJYH5VQ47K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K/action/storage_attestation","attest_author":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K/action/author_attestation","sign_citation":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K/action/citation_signature","submit_replication":"https://pith.science/pith/SPCTGQLWZVI42N7CQJYH5VQ47K/action/replication_record"}},"created_at":"2026-05-18T00:06:55.522273+00:00","updated_at":"2026-05-18T00:06:55.522273+00:00"}