{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VHMTXFXIGI36YZRUIHSRIQID3L","short_pith_number":"pith:VHMTXFXI","schema_version":"1.0","canonical_sha256":"a9d93b96e83237ec663441e5144103dad2e78b9737999adb66a34bc85c36cb36","source":{"kind":"arxiv","id":"2408.17308","version":1},"attestation_state":"computed","paper":{"title":"Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonio Toral, Esther Ploeger, Huiyuan Lai, Rik van Noord","submitted_at":"2024-08-30T14:12:04Z","abstract_excerpt":"Machine translations are found to be lexically poorer than human translations. The loss of lexical diversity through MT poses an issue in the automatic translation of literature, where it matters not only what is written, but also how it is written. Current methods for increasing lexical diversity in MT are rigid. Yet, as we demonstrate, the degree of lexical diversity can vary considerably across different novels. Thus, rather than aiming for the rigid increase of lexical diversity, we reframe the task as recovering what is lost in the machine translation process. We propose a novel approach "},"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":"2408.17308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-30T14:12:04Z","cross_cats_sorted":[],"title_canon_sha256":"23358100886c6501267bdebaa834d0025775527e4ca62a11c3beb15f5035d010","abstract_canon_sha256":"cc250fb9257b5cd05131f7a349f69e278ae936a7c5f2f51b27683d7dffff8e55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:13.546900Z","signature_b64":"ClNsoy32+KXbDDsOvEZYtiOR4uBLpiyD/25s4WGdzHcDQvYFEQiBhZfr8ywxmCCdlKNQvnT2L9fNGvQ5f9iHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9d93b96e83237ec663441e5144103dad2e78b9737999adb66a34bc85c36cb36","last_reissued_at":"2026-07-05T09:01:13.546444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:13.546444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonio Toral, Esther Ploeger, Huiyuan Lai, Rik van Noord","submitted_at":"2024-08-30T14:12:04Z","abstract_excerpt":"Machine translations are found to be lexically poorer than human translations. The loss of lexical diversity through MT poses an issue in the automatic translation of literature, where it matters not only what is written, but also how it is written. Current methods for increasing lexical diversity in MT are rigid. Yet, as we demonstrate, the degree of lexical diversity can vary considerably across different novels. Thus, rather than aiming for the rigid increase of lexical diversity, we reframe the task as recovering what is lost in the machine translation process. We propose a novel approach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.17308","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/2408.17308/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":"2408.17308","created_at":"2026-07-05T09:01:13.546500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.17308v1","created_at":"2026-07-05T09:01:13.546500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.17308","created_at":"2026-07-05T09:01:13.546500+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHMTXFXIGI36","created_at":"2026-07-05T09:01:13.546500+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHMTXFXIGI36YZRU","created_at":"2026-07-05T09:01:13.546500+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHMTXFXI","created_at":"2026-07-05T09:01:13.546500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22038","citing_title":"Can Peter Pan Survive MT? A Stylometric Study of LLMs, NMTs, and HTs in Children's Literature Translation","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L","json":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L.json","graph_json":"https://pith.science/api/pith-number/VHMTXFXIGI36YZRUIHSRIQID3L/graph.json","events_json":"https://pith.science/api/pith-number/VHMTXFXIGI36YZRUIHSRIQID3L/events.json","paper":"https://pith.science/paper/VHMTXFXI"},"agent_actions":{"view_html":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L","download_json":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L.json","view_paper":"https://pith.science/paper/VHMTXFXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.17308&json=true","fetch_graph":"https://pith.science/api/pith-number/VHMTXFXIGI36YZRUIHSRIQID3L/graph.json","fetch_events":"https://pith.science/api/pith-number/VHMTXFXIGI36YZRUIHSRIQID3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L/action/storage_attestation","attest_author":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L/action/author_attestation","sign_citation":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L/action/citation_signature","submit_replication":"https://pith.science/pith/VHMTXFXIGI36YZRUIHSRIQID3L/action/replication_record"}},"created_at":"2026-07-05T09:01:13.546500+00:00","updated_at":"2026-07-05T09:01:13.546500+00:00"}