{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IPZIX56FVQVL2OXHZHMS2OHRNT","short_pith_number":"pith:IPZIX56F","schema_version":"1.0","canonical_sha256":"43f28bf7c5ac2abd3ae7c9d92d38f16cc78ab49d2e0a413c186acacf0aa539b1","source":{"kind":"arxiv","id":"2605.13596","version":1},"attestation_state":"computed","paper":{"title":"Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Automatic evaluation metrics and LLM judges correlate poorly with professional translators on creativity in literary texts and bias toward machine outputs.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Guerberof Arenas, Kyo Gerrits, Rik van Noord","submitted_at":"2026-05-13T14:30:41Z","abstract_excerpt":"This article investigates the performance of automatic evaluation metrics (AEMs) and LLM-as-a-judge evaluation on literary translation across multiple languages, genres, and translation modalities. The aim is to assess how well these tools align with professionals when evaluating translation, creativity (creative shifts & errors), and see if they can substitute laborious manual annotations. A dataset of literary translations across three modalities (human translation, machine translation, and post-editing), three genres and three language pairs was created and annotated in detail for creativit"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13596","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T14:30:41Z","cross_cats_sorted":[],"title_canon_sha256":"965d6650c7305554093d64c14df732b393b9e6c0db1a64ced164742a9d2176c8","abstract_canon_sha256":"118075b308bfe2d85f63508597282bc4489f77d3f7d7cc990bd032ea4eb9ba70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:23.010692Z","signature_b64":"WcTCVhBAhlAtGDhKGw2XUNtgx85zy/D3joqxgp1GUzd9hlmYWnkBNOkG0J0iHU9icR0MKPX52kZcQms74ZUrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43f28bf7c5ac2abd3ae7c9d92d38f16cc78ab49d2e0a413c186acacf0aa539b1","last_reissued_at":"2026-05-18T02:44:23.010234Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:23.010234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Automatic evaluation metrics and LLM judges correlate poorly with professional translators on creativity in literary texts and bias toward machine outputs.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Guerberof Arenas, Kyo Gerrits, Rik van Noord","submitted_at":"2026-05-13T14:30:41Z","abstract_excerpt":"This article investigates the performance of automatic evaluation metrics (AEMs) and LLM-as-a-judge evaluation on literary translation across multiple languages, genres, and translation modalities. The aim is to assess how well these tools align with professionals when evaluating translation, creativity (creative shifts & errors), and see if they can substitute laborious manual annotations. A dataset of literary translations across three modalities (human translation, machine translation, and post-editing), three genres and three language pairs was created and annotated in detail for creativit"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"both AEMs and LLM-as-a-judge evaluations correlate poorly with professional evaluations on creativity, with LLM-as-a-judge showing a systematic bias in favour of machine-translated texts and penalising creative and culturally appropriate solutions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That detailed annotations by experienced professional literary translators constitute an objective and reliable ground truth for measuring creativity and translation quality across genres and modalities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Automatic evaluation tools for literary translations correlate poorly with expert human judgments on creativity and exhibit bias favoring machine-translated texts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Automatic evaluation metrics and LLM judges correlate poorly with professional translators on creativity in literary texts and bias toward machine outputs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0f55518bf682a68175241d0a9116fc2265d3e705ad605523ef6c62f1f069aa88"},"source":{"id":"2605.13596","kind":"arxiv","version":1},"verdict":{"id":"f076e1eb-f3a1-43df-ab63-f0e1a5031fc1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:02:14.689918Z","strongest_claim":"both AEMs and LLM-as-a-judge evaluations correlate poorly with professional evaluations on creativity, with LLM-as-a-judge showing a systematic bias in favour of machine-translated texts and penalising creative and culturally appropriate solutions.","one_line_summary":"Automatic evaluation tools for literary translations correlate poorly with expert human judgments on creativity and exhibit bias favoring machine-translated texts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That detailed annotations by experienced professional literary translators constitute an objective and reliable ground truth for measuring creativity and translation quality across genres and modalities.","pith_extraction_headline":"Automatic evaluation metrics and LLM judges correlate poorly with professional translators on creativity in literary texts and bias toward machine outputs."},"references":{"count":130,"sample":[{"doi":"","year":1972,"title":"and Ullman, Jeffrey D","work_id":"9f4d095b-5cc6-4ad8-a102-3e3ec582f2e1","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"Interspeech 2006 --- Ninth International Conference on Spoken Language Processing , address=","work_id":"dca1746a-b0f4-4744-96a6-703b6c190994","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1983,"title":"Publications. 1983 , publisher=","work_id":"653ffea5-4aac-4cbc-ac57-775ffd7e5df3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1981,"title":"Chandra and Dexter C","work_id":"30e59c52-947d-4f04-ac44-aa8b8453b2b3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"Coling 2008, 22nd International Conference on Computational Linguistics , address=","work_id":"5e2dd450-37f6-41fa-a3fc-30ae4540c645","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":130,"snapshot_sha256":"df677d842fccc16f555bd598783cf37afe9ed33b9044b9285f069c74e23edfcb","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":"2605.13596","created_at":"2026-05-18T02:44:23.010308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13596v1","created_at":"2026-05-18T02:44:23.010308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13596","created_at":"2026-05-18T02:44:23.010308+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPZIX56FVQVL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPZIX56FVQVL2OXH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPZIX56F","created_at":"2026-05-18T12:33:37.589309+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/IPZIX56FVQVL2OXHZHMS2OHRNT","json":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT.json","graph_json":"https://pith.science/api/pith-number/IPZIX56FVQVL2OXHZHMS2OHRNT/graph.json","events_json":"https://pith.science/api/pith-number/IPZIX56FVQVL2OXHZHMS2OHRNT/events.json","paper":"https://pith.science/paper/IPZIX56F"},"agent_actions":{"view_html":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT","download_json":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT.json","view_paper":"https://pith.science/paper/IPZIX56F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13596&json=true","fetch_graph":"https://pith.science/api/pith-number/IPZIX56FVQVL2OXHZHMS2OHRNT/graph.json","fetch_events":"https://pith.science/api/pith-number/IPZIX56FVQVL2OXHZHMS2OHRNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT/action/storage_attestation","attest_author":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT/action/author_attestation","sign_citation":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT/action/citation_signature","submit_replication":"https://pith.science/pith/IPZIX56FVQVL2OXHZHMS2OHRNT/action/replication_record"}},"created_at":"2026-05-18T02:44:23.010308+00:00","updated_at":"2026-05-18T02:44:23.010308+00:00"}