{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JXB7ILSLIHTDZIFYZHGMMMMRRX","short_pith_number":"pith:JXB7ILSL","schema_version":"1.0","canonical_sha256":"4dc3f42e4b41e63ca0b8c9ccc631918dea428d651dea3fde6e8792d640a6db84","source":{"kind":"arxiv","id":"2506.22050","version":1},"attestation_state":"computed","paper":{"title":"Decoding Machine Translationese in English-Chinese News: LLMs vs. NMTs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Delu Kong, Lieve Macken","submitted_at":"2025-06-27T09:45:37Z","abstract_excerpt":"This study explores Machine Translationese (MTese) -- the linguistic peculiarities of machine translation outputs -- focusing on the under-researched English-to-Chinese language pair in news texts. We construct a large dataset consisting of 4 sub-corpora and employ a comprehensive five-layer feature set. Then, a chi-square ranking algorithm is applied for feature selection in both classification and clustering tasks. Our findings confirm the presence of MTese in both Neural Machine Translation systems (NMTs) and Large Language Models (LLMs). Original Chinese texts are nearly perfectly distingu"},"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":"2506.22050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T09:45:37Z","cross_cats_sorted":[],"title_canon_sha256":"40bcc8b2b308bc4e6f7beda3093a22c12100643258d1acf2a78ff76af62e3cba","abstract_canon_sha256":"71b0f1f725988330abcb7fdce6f4ae2f4ab249ebce56294a53b169cc1c3b9664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:21.123078Z","signature_b64":"0lpGRN8v6ff7bGaxLOW72zcNgjSojx1w8NyGB74PekkHFmajgBwCIOSy/WVACEjEpe5A/8K0ELhvWea8/FQMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dc3f42e4b41e63ca0b8c9ccc631918dea428d651dea3fde6e8792d640a6db84","last_reissued_at":"2026-07-05T11:28:21.122633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:21.122633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoding Machine Translationese in English-Chinese News: LLMs vs. NMTs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Delu Kong, Lieve Macken","submitted_at":"2025-06-27T09:45:37Z","abstract_excerpt":"This study explores Machine Translationese (MTese) -- the linguistic peculiarities of machine translation outputs -- focusing on the under-researched English-to-Chinese language pair in news texts. We construct a large dataset consisting of 4 sub-corpora and employ a comprehensive five-layer feature set. Then, a chi-square ranking algorithm is applied for feature selection in both classification and clustering tasks. Our findings confirm the presence of MTese in both Neural Machine Translation systems (NMTs) and Large Language Models (LLMs). Original Chinese texts are nearly perfectly distingu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22050","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/2506.22050/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":"2506.22050","created_at":"2026-07-05T11:28:21.122690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22050v1","created_at":"2026-07-05T11:28:21.122690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22050","created_at":"2026-07-05T11:28:21.122690+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXB7ILSLIHTD","created_at":"2026-07-05T11:28:21.122690+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXB7ILSLIHTDZIFY","created_at":"2026-07-05T11:28:21.122690+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXB7ILSL","created_at":"2026-07-05T11:28:21.122690+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/JXB7ILSLIHTDZIFYZHGMMMMRRX","json":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX.json","graph_json":"https://pith.science/api/pith-number/JXB7ILSLIHTDZIFYZHGMMMMRRX/graph.json","events_json":"https://pith.science/api/pith-number/JXB7ILSLIHTDZIFYZHGMMMMRRX/events.json","paper":"https://pith.science/paper/JXB7ILSL"},"agent_actions":{"view_html":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX","download_json":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX.json","view_paper":"https://pith.science/paper/JXB7ILSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22050&json=true","fetch_graph":"https://pith.science/api/pith-number/JXB7ILSLIHTDZIFYZHGMMMMRRX/graph.json","fetch_events":"https://pith.science/api/pith-number/JXB7ILSLIHTDZIFYZHGMMMMRRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX/action/storage_attestation","attest_author":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX/action/author_attestation","sign_citation":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX/action/citation_signature","submit_replication":"https://pith.science/pith/JXB7ILSLIHTDZIFYZHGMMMMRRX/action/replication_record"}},"created_at":"2026-07-05T11:28:21.122690+00:00","updated_at":"2026-07-05T11:28:21.122690+00:00"}