{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IIWHYHJBEETACBGT3VBOKABTNT","short_pith_number":"pith:IIWHYHJB","schema_version":"1.0","canonical_sha256":"422c7c1d2121260104d3dd42e500336cdcc3019b95dce08256ffd66bc0004151","source":{"kind":"arxiv","id":"2205.02293","version":3},"attestation_state":"computed","paper":{"title":"Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bernhard Sch\\\"olkopf, Jingwei Ni, Markus Freitag, Mrinmaya Sachan, Zhijing Jin","submitted_at":"2022-05-04T19:17:55Z","abstract_excerpt":"Human-translated text displays distinct features from naturally written text in the same language. This phenomena, known as translationese, has been argued to confound the machine translation (MT) evaluation. Yet, we find that existing work on translationese neglects some important factors and the conclusions are mostly correlational but not causal. In this work, we collect CausalMT, a dataset where the MT training data are also labeled with the human translation directions. We inspect two critical factors, the train-test direction match (whether the human translation directions in the trainin"},"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":"2205.02293","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-04T19:17:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f0901108f46b76d80229d395fdc4d345e0064d9b6d7756b5a7aab91340eef938","abstract_canon_sha256":"57b567187709d9993a43f77b0cfa2799fc0034fb13086be1cfa2e195a2d17893"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:22.140723Z","signature_b64":"LVNur9MzVCLL+Xzlxahsw0um4NvPWnsTxxVdrB1Nl2U96OF3smZYTRKK/oXYeSNxa7xuf+TCqNg7jykE2wwBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"422c7c1d2121260104d3dd42e500336cdcc3019b95dce08256ffd66bc0004151","last_reissued_at":"2026-07-05T04:30:22.140241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:22.140241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bernhard Sch\\\"olkopf, Jingwei Ni, Markus Freitag, Mrinmaya Sachan, Zhijing Jin","submitted_at":"2022-05-04T19:17:55Z","abstract_excerpt":"Human-translated text displays distinct features from naturally written text in the same language. This phenomena, known as translationese, has been argued to confound the machine translation (MT) evaluation. Yet, we find that existing work on translationese neglects some important factors and the conclusions are mostly correlational but not causal. In this work, we collect CausalMT, a dataset where the MT training data are also labeled with the human translation directions. We inspect two critical factors, the train-test direction match (whether the human translation directions in the trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02293","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/2205.02293/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":"2205.02293","created_at":"2026-07-05T04:30:22.140307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.02293v3","created_at":"2026-07-05T04:30:22.140307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02293","created_at":"2026-07-05T04:30:22.140307+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIWHYHJBEETA","created_at":"2026-07-05T04:30:22.140307+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIWHYHJBEETACBGT","created_at":"2026-07-05T04:30:22.140307+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIWHYHJB","created_at":"2026-07-05T04:30:22.140307+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/IIWHYHJBEETACBGT3VBOKABTNT","json":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT.json","graph_json":"https://pith.science/api/pith-number/IIWHYHJBEETACBGT3VBOKABTNT/graph.json","events_json":"https://pith.science/api/pith-number/IIWHYHJBEETACBGT3VBOKABTNT/events.json","paper":"https://pith.science/paper/IIWHYHJB"},"agent_actions":{"view_html":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT","download_json":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT.json","view_paper":"https://pith.science/paper/IIWHYHJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.02293&json=true","fetch_graph":"https://pith.science/api/pith-number/IIWHYHJBEETACBGT3VBOKABTNT/graph.json","fetch_events":"https://pith.science/api/pith-number/IIWHYHJBEETACBGT3VBOKABTNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT/action/storage_attestation","attest_author":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT/action/author_attestation","sign_citation":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT/action/citation_signature","submit_replication":"https://pith.science/pith/IIWHYHJBEETACBGT3VBOKABTNT/action/replication_record"}},"created_at":"2026-07-05T04:30:22.140307+00:00","updated_at":"2026-07-05T04:30:22.140307+00:00"}