{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ENQCD42Q5NMB3SVHNMTOGTDARJ","short_pith_number":"pith:ENQCD42Q","schema_version":"1.0","canonical_sha256":"236021f350eb581dcaa76b26e34c608a73386de819bfe27c1b167b9e3de7405c","source":{"kind":"arxiv","id":"1906.04040","version":1},"attestation_state":"computed","paper":{"title":"The University of Helsinki submissions to the WMT19 news translation task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aarne Talman, Alessandro Raganato, Arvi Hurskainen, J\\\"org Tiedemann, Ra\\'ul V\\'azquez, Sami Virpioja, Umut Sulubacak, Yves Scherrer","submitted_at":"2019-06-10T14:48:10Z","abstract_excerpt":"In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation in three language pairs: English-German, English-Finnish and Finnish-English. This year, we focused first on cleaning and filtering the training data using multiple data-filtering approaches, resulting in much smaller and cleaner training sets. For English-German, we trained both sentence-level transformer models and compared different document-level translation approaches. For Finnish-English and English-Finnish we focused on different segmentation approaches, and we also included "},"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":"1906.04040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-10T14:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"ec33d5ef2c1daf153e8cc9c5d3c30316f8c017951274b3ad9ea245519f72d91c","abstract_canon_sha256":"49aa20b3f79748c80663321dd2316ae83bfd65b1460c9abad96cf6b0347cd0f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:44.092076Z","signature_b64":"BtwDYv/Zx42JEtBawTUn0PqhUHjEUtX0xJO1BV6KGqiBd2enwQ2S9jhpJwUyZaSn7pntVDCy4TDPpafbvnowAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236021f350eb581dcaa76b26e34c608a73386de819bfe27c1b167b9e3de7405c","last_reissued_at":"2026-05-17T23:43:44.091391Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:44.091391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The University of Helsinki submissions to the WMT19 news translation task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aarne Talman, Alessandro Raganato, Arvi Hurskainen, J\\\"org Tiedemann, Ra\\'ul V\\'azquez, Sami Virpioja, Umut Sulubacak, Yves Scherrer","submitted_at":"2019-06-10T14:48:10Z","abstract_excerpt":"In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation in three language pairs: English-German, English-Finnish and Finnish-English. This year, we focused first on cleaning and filtering the training data using multiple data-filtering approaches, resulting in much smaller and cleaner training sets. For English-German, we trained both sentence-level transformer models and compared different document-level translation approaches. For Finnish-English and English-Finnish we focused on different segmentation approaches, and we also included "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04040","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":"1906.04040","created_at":"2026-05-17T23:43:44.091490+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04040v1","created_at":"2026-05-17T23:43:44.091490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04040","created_at":"2026-05-17T23:43:44.091490+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENQCD42Q5NMB","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENQCD42Q5NMB3SVH","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENQCD42Q","created_at":"2026-05-18T12:33:15.570797+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/ENQCD42Q5NMB3SVHNMTOGTDARJ","json":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ.json","graph_json":"https://pith.science/api/pith-number/ENQCD42Q5NMB3SVHNMTOGTDARJ/graph.json","events_json":"https://pith.science/api/pith-number/ENQCD42Q5NMB3SVHNMTOGTDARJ/events.json","paper":"https://pith.science/paper/ENQCD42Q"},"agent_actions":{"view_html":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ","download_json":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ.json","view_paper":"https://pith.science/paper/ENQCD42Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04040&json=true","fetch_graph":"https://pith.science/api/pith-number/ENQCD42Q5NMB3SVHNMTOGTDARJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ENQCD42Q5NMB3SVHNMTOGTDARJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ/action/storage_attestation","attest_author":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ/action/author_attestation","sign_citation":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ/action/citation_signature","submit_replication":"https://pith.science/pith/ENQCD42Q5NMB3SVHNMTOGTDARJ/action/replication_record"}},"created_at":"2026-05-17T23:43:44.091490+00:00","updated_at":"2026-05-17T23:43:44.091490+00:00"}