{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OYVDG44JNAODCTVWPOHHEJCYOK","short_pith_number":"pith:OYVDG44J","schema_version":"1.0","canonical_sha256":"762a337389681c314eb67b8e722458729495542a10be206ba86faf5ed97e9cf3","source":{"kind":"arxiv","id":"2102.00287","version":1},"attestation_state":"computed","paper":{"title":"Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Dimitar Shterionov, Eva Vanmassenhove, Matthew Gwilliam","submitted_at":"2021-01-30T18:49:11Z","abstract_excerpt":"Recent studies in the field of Machine Translation (MT) and Natural Language Processing (NLP) have shown that existing models amplify biases observed in the training data. The amplification of biases in language technology has mainly been examined with respect to specific phenomena, such as gender bias. In this work, we go beyond the study of gender in MT and investigate how bias amplification might affect language in a broader sense. We hypothesize that the 'algorithmic bias', i.e. an exacerbation of frequently observed patterns in combination with a loss of less frequent ones, not only exace"},"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":"2102.00287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-30T18:49:11Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"924f4d637006b0220ce63f8341fec7554de26a8d04948350a06ddbdaed221aa2","abstract_canon_sha256":"8ba85a1834c5d5fdf99a121685202f16f1df22d6758ec8e2a2d81513a0f9dc1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:10.124656Z","signature_b64":"Sug2zrVZDEQcPbzyiM7TYTZ/ks/WyfZS4vyVsjoZN43AEqTY1XYQ6p8XDyPyO9F+a0xRAii7WJzS6CbhKUD2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"762a337389681c314eb67b8e722458729495542a10be206ba86faf5ed97e9cf3","last_reissued_at":"2026-07-05T02:11:10.124197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:10.124197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Dimitar Shterionov, Eva Vanmassenhove, Matthew Gwilliam","submitted_at":"2021-01-30T18:49:11Z","abstract_excerpt":"Recent studies in the field of Machine Translation (MT) and Natural Language Processing (NLP) have shown that existing models amplify biases observed in the training data. The amplification of biases in language technology has mainly been examined with respect to specific phenomena, such as gender bias. In this work, we go beyond the study of gender in MT and investigate how bias amplification might affect language in a broader sense. We hypothesize that the 'algorithmic bias', i.e. an exacerbation of frequently observed patterns in combination with a loss of less frequent ones, not only exace"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00287","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.00287/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":"2102.00287","created_at":"2026-07-05T02:11:10.124255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.00287v1","created_at":"2026-07-05T02:11:10.124255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00287","created_at":"2026-07-05T02:11:10.124255+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYVDG44JNAOD","created_at":"2026-07-05T02:11:10.124255+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYVDG44JNAODCTVW","created_at":"2026-07-05T02:11:10.124255+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYVDG44J","created_at":"2026-07-05T02:11:10.124255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19799","citing_title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK","json":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK.json","graph_json":"https://pith.science/api/pith-number/OYVDG44JNAODCTVWPOHHEJCYOK/graph.json","events_json":"https://pith.science/api/pith-number/OYVDG44JNAODCTVWPOHHEJCYOK/events.json","paper":"https://pith.science/paper/OYVDG44J"},"agent_actions":{"view_html":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK","download_json":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK.json","view_paper":"https://pith.science/paper/OYVDG44J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.00287&json=true","fetch_graph":"https://pith.science/api/pith-number/OYVDG44JNAODCTVWPOHHEJCYOK/graph.json","fetch_events":"https://pith.science/api/pith-number/OYVDG44JNAODCTVWPOHHEJCYOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK/action/storage_attestation","attest_author":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK/action/author_attestation","sign_citation":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK/action/citation_signature","submit_replication":"https://pith.science/pith/OYVDG44JNAODCTVWPOHHEJCYOK/action/replication_record"}},"created_at":"2026-07-05T02:11:10.124255+00:00","updated_at":"2026-07-05T02:11:10.124255+00:00"}