{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LOW6CW4E2ZD5DRLGWFTEKNODGK","short_pith_number":"pith:LOW6CW4E","schema_version":"1.0","canonical_sha256":"5bade15b84d647d1c566b1664535c332a68d06a9476a84f6c250b183c73e781f","source":{"kind":"arxiv","id":"1905.13354","version":1},"attestation_state":"computed","paper":{"title":"DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Bilinski, Rachel Bawden, Sophie Rosset, Thomas Lavergne","submitted_at":"2019-05-30T23:41:35Z","abstract_excerpt":"We present a new English-French test set for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue. The test set contains 144 spontaneous dialogues (5,700+ sentences) between native English and French speakers, mediated by one of two neural MT systems in a range of role-play settings. The dialogues are accompanied by fine-grained sentence-level judgments of MT quality, produced by the dialogue participants themselves, as well as by manually normalised versions and reference translations produced a posteriori. The motivation for the corpus is two-fold: to provide ("},"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":"1905.13354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-30T23:41:35Z","cross_cats_sorted":[],"title_canon_sha256":"a525bb1d73be6bb4a97aee7eb456ae427232cef65f14464a3cc4811e694412dc","abstract_canon_sha256":"80c2c6b76fec5c777ce7a827de6305756fec6f09aa93b5d3c4aac85dc45cd308"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.200794Z","signature_b64":"7Y5E23jo4tEstg57UmxkwIxAXQh+Ms452ZL7AOkNAjhPCYQybt70rQb3Eqti9r4SuVnJjtSwfurmmitD8qYCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bade15b84d647d1c566b1664535c332a68d06a9476a84f6c250b183c73e781f","last_reissued_at":"2026-05-17T23:44:35.200230Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.200230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Bilinski, Rachel Bawden, Sophie Rosset, Thomas Lavergne","submitted_at":"2019-05-30T23:41:35Z","abstract_excerpt":"We present a new English-French test set for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue. The test set contains 144 spontaneous dialogues (5,700+ sentences) between native English and French speakers, mediated by one of two neural MT systems in a range of role-play settings. The dialogues are accompanied by fine-grained sentence-level judgments of MT quality, produced by the dialogue participants themselves, as well as by manually normalised versions and reference translations produced a posteriori. The motivation for the corpus is two-fold: to provide ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13354","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":"1905.13354","created_at":"2026-05-17T23:44:35.200327+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13354v1","created_at":"2026-05-17T23:44:35.200327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13354","created_at":"2026-05-17T23:44:35.200327+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOW6CW4E2ZD5","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOW6CW4E2ZD5DRLG","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOW6CW4E","created_at":"2026-05-18T12:33:21.387695+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/LOW6CW4E2ZD5DRLGWFTEKNODGK","json":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK.json","graph_json":"https://pith.science/api/pith-number/LOW6CW4E2ZD5DRLGWFTEKNODGK/graph.json","events_json":"https://pith.science/api/pith-number/LOW6CW4E2ZD5DRLGWFTEKNODGK/events.json","paper":"https://pith.science/paper/LOW6CW4E"},"agent_actions":{"view_html":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK","download_json":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK.json","view_paper":"https://pith.science/paper/LOW6CW4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13354&json=true","fetch_graph":"https://pith.science/api/pith-number/LOW6CW4E2ZD5DRLGWFTEKNODGK/graph.json","fetch_events":"https://pith.science/api/pith-number/LOW6CW4E2ZD5DRLGWFTEKNODGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK/action/storage_attestation","attest_author":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK/action/author_attestation","sign_citation":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK/action/citation_signature","submit_replication":"https://pith.science/pith/LOW6CW4E2ZD5DRLGWFTEKNODGK/action/replication_record"}},"created_at":"2026-05-17T23:44:35.200327+00:00","updated_at":"2026-05-17T23:44:35.200327+00:00"}