{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I4XG5ZXLZOSVV4LWXKI7XR4TAL","short_pith_number":"pith:I4XG5ZXL","schema_version":"1.0","canonical_sha256":"472e6ee6ebcba55af176ba91fbc79302ec4aa853da7ae597e5d939b6a92920c0","source":{"kind":"arxiv","id":"1908.10940","version":2},"attestation_state":"computed","paper":{"title":"Learning a Multi-Domain Curriculum for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Isaac Caswell, Jiquan Ngiam, Wei Wang, Ye Tian, Yinfei Yang, Zarana Parekh","submitted_at":"2019-08-28T20:48:05Z","abstract_excerpt":"Most data selection research in machine translation focuses on improving a single domain. We perform data selection for multiple domains at once. This is achieved by carefully introducing instance-level domain-relevance features and automatically constructing a training curriculum to gradually concentrate on multi-domain relevant and noise-reduced data batches. Both the choice of features and the use of curriculum are crucial for balancing and improving all domains, including out-of-domain. In large-scale experiments, the multi-domain curriculum simultaneously reaches or outperforms the indivi"},"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":"1908.10940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-28T20:48:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e415a1cb40fd9146323c50a3e1cd5dba21101d6f22ee662c1ae16431aab0625f","abstract_canon_sha256":"14768a7c280e28abfb2ad9e8500f6e7e486f224b5a8baa97a321f514f0e1ad0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:42.543663Z","signature_b64":"Npn8mOPwSOxPSQ8IURzlNwZpON/DN/6P0l/GWI2TaV39uKE00uBlVRiYCbddmBWBex8ZVmIGaPusEz7yMlmRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"472e6ee6ebcba55af176ba91fbc79302ec4aa853da7ae597e5d939b6a92920c0","last_reissued_at":"2026-07-05T00:59:42.543187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:42.543187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Multi-Domain Curriculum for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Isaac Caswell, Jiquan Ngiam, Wei Wang, Ye Tian, Yinfei Yang, Zarana Parekh","submitted_at":"2019-08-28T20:48:05Z","abstract_excerpt":"Most data selection research in machine translation focuses on improving a single domain. We perform data selection for multiple domains at once. This is achieved by carefully introducing instance-level domain-relevance features and automatically constructing a training curriculum to gradually concentrate on multi-domain relevant and noise-reduced data batches. Both the choice of features and the use of curriculum are crucial for balancing and improving all domains, including out-of-domain. In large-scale experiments, the multi-domain curriculum simultaneously reaches or outperforms the indivi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10940","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.10940/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":"1908.10940","created_at":"2026-07-05T00:59:42.543244+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10940v2","created_at":"2026-07-05T00:59:42.543244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10940","created_at":"2026-07-05T00:59:42.543244+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4XG5ZXLZOSV","created_at":"2026-07-05T00:59:42.543244+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4XG5ZXLZOSVV4LW","created_at":"2026-07-05T00:59:42.543244+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4XG5ZXL","created_at":"2026-07-05T00:59:42.543244+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/I4XG5ZXLZOSVV4LWXKI7XR4TAL","json":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL.json","graph_json":"https://pith.science/api/pith-number/I4XG5ZXLZOSVV4LWXKI7XR4TAL/graph.json","events_json":"https://pith.science/api/pith-number/I4XG5ZXLZOSVV4LWXKI7XR4TAL/events.json","paper":"https://pith.science/paper/I4XG5ZXL"},"agent_actions":{"view_html":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL","download_json":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL.json","view_paper":"https://pith.science/paper/I4XG5ZXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10940&json=true","fetch_graph":"https://pith.science/api/pith-number/I4XG5ZXLZOSVV4LWXKI7XR4TAL/graph.json","fetch_events":"https://pith.science/api/pith-number/I4XG5ZXLZOSVV4LWXKI7XR4TAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL/action/storage_attestation","attest_author":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL/action/author_attestation","sign_citation":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL/action/citation_signature","submit_replication":"https://pith.science/pith/I4XG5ZXLZOSVV4LWXKI7XR4TAL/action/replication_record"}},"created_at":"2026-07-05T00:59:42.543244+00:00","updated_at":"2026-07-05T00:59:42.543244+00:00"}