{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LW7XRT36ZMO7QLO36HMRYV6MJF","short_pith_number":"pith:LW7XRT36","schema_version":"1.0","canonical_sha256":"5dbf78cf7ecb1df82ddbf1d91c57cc494fadcb30ac2e640f57100257864d58b3","source":{"kind":"arxiv","id":"2606.05924","version":1},"attestation_state":"computed","paper":{"title":"Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guanghui Wang, Hao Huang, Peiyang He, Zhihao Lin, Ziqi Zhu","submitted_at":"2026-06-04T09:27:29Z","abstract_excerpt":"Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary effect. We present a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators, each targeting a distinct quality dimension. We leverage the generated data for supervised fine-tuning and reinforcement learning. Experiments show that our generated references outperform the original ground truth for SFT by 8.65 CEA100 points. For reinforcement learning, "},"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":"2606.05924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T09:27:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34b0e72904f5110a7f92e4079f365311eb0541eef52a4e78a608272e3c808b53","abstract_canon_sha256":"66fee7f9cacf1f2e3fdf3406903dc7a2c2c50193d25cb7e91697be031e302895"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:27.786276Z","signature_b64":"a8IHMyV8Z18i3r0iZ9E/ajbGg5eyzh0YYT2pLpCUUQlStAvGk3apKtUo748ySkedYPFp1wkVdnuM8p5G3vVsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dbf78cf7ecb1df82ddbf1d91c57cc494fadcb30ac2e640f57100257864d58b3","last_reissued_at":"2026-06-05T01:15:27.785807Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:27.785807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guanghui Wang, Hao Huang, Peiyang He, Zhihao Lin, Ziqi Zhu","submitted_at":"2026-06-04T09:27:29Z","abstract_excerpt":"Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary effect. We present a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators, each targeting a distinct quality dimension. We leverage the generated data for supervised fine-tuning and reinforcement learning. Experiments show that our generated references outperform the original ground truth for SFT by 8.65 CEA100 points. For reinforcement learning, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05924","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/2606.05924/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":"2606.05924","created_at":"2026-06-05T01:15:27.785885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05924v1","created_at":"2026-06-05T01:15:27.785885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05924","created_at":"2026-06-05T01:15:27.785885+00:00"},{"alias_kind":"pith_short_12","alias_value":"LW7XRT36ZMO7","created_at":"2026-06-05T01:15:27.785885+00:00"},{"alias_kind":"pith_short_16","alias_value":"LW7XRT36ZMO7QLO3","created_at":"2026-06-05T01:15:27.785885+00:00"},{"alias_kind":"pith_short_8","alias_value":"LW7XRT36","created_at":"2026-06-05T01:15:27.785885+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/LW7XRT36ZMO7QLO36HMRYV6MJF","json":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF.json","graph_json":"https://pith.science/api/pith-number/LW7XRT36ZMO7QLO36HMRYV6MJF/graph.json","events_json":"https://pith.science/api/pith-number/LW7XRT36ZMO7QLO36HMRYV6MJF/events.json","paper":"https://pith.science/paper/LW7XRT36"},"agent_actions":{"view_html":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF","download_json":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF.json","view_paper":"https://pith.science/paper/LW7XRT36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05924&json=true","fetch_graph":"https://pith.science/api/pith-number/LW7XRT36ZMO7QLO36HMRYV6MJF/graph.json","fetch_events":"https://pith.science/api/pith-number/LW7XRT36ZMO7QLO36HMRYV6MJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF/action/storage_attestation","attest_author":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF/action/author_attestation","sign_citation":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF/action/citation_signature","submit_replication":"https://pith.science/pith/LW7XRT36ZMO7QLO36HMRYV6MJF/action/replication_record"}},"created_at":"2026-06-05T01:15:27.785885+00:00","updated_at":"2026-06-05T01:15:27.785885+00:00"}