{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B6LXSG3WKLCPUCAEEDXTCIYO2J","short_pith_number":"pith:B6LXSG3W","schema_version":"1.0","canonical_sha256":"0f97791b7652c4fa080420ef31230ed240056d2dabea1285766bf65db3bc4481","source":{"kind":"arxiv","id":"2010.04480","version":3},"attestation_state":"computed","paper":{"title":"MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Chrysoula Zerva, Erick Fonseca, Francisco Guzm\\'an, Fr\\'ed\\'eric Blain, Lucia Specia, Marina Fomicheva, Nina Lopatina, Shuo Sun, Vishrav Chaudhary","submitted_at":"2020-10-09T10:12:02Z","abstract_excerpt":"We present MLQE-PE, a new dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE). The dataset contains eleven language pairs, with human labels for up to 10,000 translations per language pair in the following formats: sentence-level direct assessments and post-editing effort, and word-level good/bad labels. It also contains the post-edited sentences, as well as titles of the articles where the sentences were extracted from, and the neural MT models used to translate the text."},"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":"2010.04480","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-09T10:12:02Z","cross_cats_sorted":[],"title_canon_sha256":"f61383a78e87bf249fe94ca3e3ba231ac8807d4ce2ba14831f11277cc2f73807","abstract_canon_sha256":"71a40a583298af1fd45b9a3bd0a25d1f4d53e26423cf39113f181882d119d5f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:06.708541Z","signature_b64":"Z5+bLDOWgmx4tUYBlm1sSPo7Re/Q7v0vqknUisMwa9+LTap8mKEYG/LC2MtQgRXpVO4yiT6fzt7nhnHmW1cPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f97791b7652c4fa080420ef31230ed240056d2dabea1285766bf65db3bc4481","last_reissued_at":"2026-07-05T03:21:06.708028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:06.708028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Chrysoula Zerva, Erick Fonseca, Francisco Guzm\\'an, Fr\\'ed\\'eric Blain, Lucia Specia, Marina Fomicheva, Nina Lopatina, Shuo Sun, Vishrav Chaudhary","submitted_at":"2020-10-09T10:12:02Z","abstract_excerpt":"We present MLQE-PE, a new dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE). The dataset contains eleven language pairs, with human labels for up to 10,000 translations per language pair in the following formats: sentence-level direct assessments and post-editing effort, and word-level good/bad labels. It also contains the post-edited sentences, as well as titles of the articles where the sentences were extracted from, and the neural MT models used to translate the text."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04480","kind":"arxiv","version":3},"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/2010.04480/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":"2010.04480","created_at":"2026-07-05T03:21:06.708104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04480v3","created_at":"2026-07-05T03:21:06.708104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04480","created_at":"2026-07-05T03:21:06.708104+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6LXSG3WKLCP","created_at":"2026-07-05T03:21:06.708104+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6LXSG3WKLCPUCAE","created_at":"2026-07-05T03:21:06.708104+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6LXSG3W","created_at":"2026-07-05T03:21:06.708104+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/B6LXSG3WKLCPUCAEEDXTCIYO2J","json":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J.json","graph_json":"https://pith.science/api/pith-number/B6LXSG3WKLCPUCAEEDXTCIYO2J/graph.json","events_json":"https://pith.science/api/pith-number/B6LXSG3WKLCPUCAEEDXTCIYO2J/events.json","paper":"https://pith.science/paper/B6LXSG3W"},"agent_actions":{"view_html":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J","download_json":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J.json","view_paper":"https://pith.science/paper/B6LXSG3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04480&json=true","fetch_graph":"https://pith.science/api/pith-number/B6LXSG3WKLCPUCAEEDXTCIYO2J/graph.json","fetch_events":"https://pith.science/api/pith-number/B6LXSG3WKLCPUCAEEDXTCIYO2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J/action/storage_attestation","attest_author":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J/action/author_attestation","sign_citation":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J/action/citation_signature","submit_replication":"https://pith.science/pith/B6LXSG3WKLCPUCAEEDXTCIYO2J/action/replication_record"}},"created_at":"2026-07-05T03:21:06.708104+00:00","updated_at":"2026-07-05T03:21:06.708104+00:00"}