{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IJMIHK6ZBE7BFAPF6EBV77JUXH","short_pith_number":"pith:IJMIHK6Z","schema_version":"1.0","canonical_sha256":"425883abd9093e1281e5f1035ffd34b9ded62bc25a54c7e3572b87cf69266a30","source":{"kind":"arxiv","id":"1612.06140","version":2},"attestation_state":"computed","paper":{"title":"Domain Control for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Catherine Kobus, Jean Senellart, Josep Crego","submitted_at":"2016-12-19T11:51:35Z","abstract_excerpt":"Machine translation systems are very sensitive to the domains they were trained on. Several domain adaptation techniques have been deeply studied. We propose a new technique for neural machine translation (NMT) that we call domain control which is performed at runtime using a unique neural network covering multiple domains. The presented approach shows quality improvements when compared to dedicated domains translating on any of the covered domains and even on out-of-domain data. In addition, model parameters do not need to be re-estimated for each domain, making this effective to real use cas"},"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":"1612.06140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-19T11:51:35Z","cross_cats_sorted":[],"title_canon_sha256":"92bd013f270393fd4a4b508c1739f6bb532bf9499ba3d06870f26270ca2ff1fa","abstract_canon_sha256":"6aed949e305ed9fcefdfaa9ca94371e2ebb9534b872690a1d7bc6256e76872c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:35.125096Z","signature_b64":"Wx9pxh51DM29R+8BJlW0kuJ6cxPWq1OZ92JSAIeSdRIV3eoiAYreyzqnT4nr7sRpDwx/iZKb16q6X8GgHEkqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"425883abd9093e1281e5f1035ffd34b9ded62bc25a54c7e3572b87cf69266a30","last_reissued_at":"2026-05-18T00:35:35.124600Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:35.124600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Control for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Catherine Kobus, Jean Senellart, Josep Crego","submitted_at":"2016-12-19T11:51:35Z","abstract_excerpt":"Machine translation systems are very sensitive to the domains they were trained on. Several domain adaptation techniques have been deeply studied. We propose a new technique for neural machine translation (NMT) that we call domain control which is performed at runtime using a unique neural network covering multiple domains. The presented approach shows quality improvements when compared to dedicated domains translating on any of the covered domains and even on out-of-domain data. In addition, model parameters do not need to be re-estimated for each domain, making this effective to real use cas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.06140","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":"1612.06140","created_at":"2026-05-18T00:35:35.124675+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.06140v2","created_at":"2026-05-18T00:35:35.124675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.06140","created_at":"2026-05-18T00:35:35.124675+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJMIHK6ZBE7B","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJMIHK6ZBE7BFAPF","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJMIHK6Z","created_at":"2026-05-18T12:30:22.444734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.05858","citing_title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH","json":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH.json","graph_json":"https://pith.science/api/pith-number/IJMIHK6ZBE7BFAPF6EBV77JUXH/graph.json","events_json":"https://pith.science/api/pith-number/IJMIHK6ZBE7BFAPF6EBV77JUXH/events.json","paper":"https://pith.science/paper/IJMIHK6Z"},"agent_actions":{"view_html":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH","download_json":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH.json","view_paper":"https://pith.science/paper/IJMIHK6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.06140&json=true","fetch_graph":"https://pith.science/api/pith-number/IJMIHK6ZBE7BFAPF6EBV77JUXH/graph.json","fetch_events":"https://pith.science/api/pith-number/IJMIHK6ZBE7BFAPF6EBV77JUXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH/action/storage_attestation","attest_author":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH/action/author_attestation","sign_citation":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH/action/citation_signature","submit_replication":"https://pith.science/pith/IJMIHK6ZBE7BFAPF6EBV77JUXH/action/replication_record"}},"created_at":"2026-05-18T00:35:35.124675+00:00","updated_at":"2026-05-18T00:35:35.124675+00:00"}