{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A5V5XJFCLCLRIURJGXNKL4NJSG","short_pith_number":"pith:A5V5XJFC","schema_version":"1.0","canonical_sha256":"076bdba4a2589714522935daa5f1a99193267eccaed0772ceb240ad0836d3b4e","source":{"kind":"arxiv","id":"2412.18707","version":2},"attestation_state":"computed","paper":{"title":"Multiple References with Meaningful Variations Improve Literary Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David A. Smith, John Wieting, Si Wu","submitted_at":"2024-12-24T23:49:12Z","abstract_excerpt":"While a source sentence can be translated in many ways, most machine translation (MT) models are trained with only a single reference. Previous work has shown that using synthetic paraphrases can improve MT. This paper investigates best practices for employing multiple references by analyzing the semantic similarity among different English translations of world literature in the Par3 dataset. We classify the semantic similarity between paraphrases into three levels: low, medium, and high, and fine-tune three different models (mT5-large, LLaMA-2-7B, and Opus-MT) for literary MT tasks. Across di"},"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":"2412.18707","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T23:49:12Z","cross_cats_sorted":[],"title_canon_sha256":"eb38d77fe18857cf3a223dfe6b8c2c8f4f2c3b7dd03af3cb3dfef8da62cd5f19","abstract_canon_sha256":"7c0588e44e0a405d48215c8b0be3507e679008cd2597ac1afc9547cce8228fb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:56.888932Z","signature_b64":"Yy5m3m7tgW0bJG+7cchsqTe+dCVJEdGCvH0DSKS8MRHIN0i9cw+MoWX+/SoQU3mvmUvWpB/Lr43Etsj+Fst0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076bdba4a2589714522935daa5f1a99193267eccaed0772ceb240ad0836d3b4e","last_reissued_at":"2026-07-05T10:19:56.888423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:56.888423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiple References with Meaningful Variations Improve Literary Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David A. Smith, John Wieting, Si Wu","submitted_at":"2024-12-24T23:49:12Z","abstract_excerpt":"While a source sentence can be translated in many ways, most machine translation (MT) models are trained with only a single reference. Previous work has shown that using synthetic paraphrases can improve MT. This paper investigates best practices for employing multiple references by analyzing the semantic similarity among different English translations of world literature in the Par3 dataset. We classify the semantic similarity between paraphrases into three levels: low, medium, and high, and fine-tune three different models (mT5-large, LLaMA-2-7B, and Opus-MT) for literary MT tasks. Across di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18707","kind":"arxiv","version":2},"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/2412.18707/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":"2412.18707","created_at":"2026-07-05T10:19:56.888492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18707v2","created_at":"2026-07-05T10:19:56.888492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18707","created_at":"2026-07-05T10:19:56.888492+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5V5XJFCLCLR","created_at":"2026-07-05T10:19:56.888492+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5V5XJFCLCLRIURJ","created_at":"2026-07-05T10:19:56.888492+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5V5XJFC","created_at":"2026-07-05T10:19:56.888492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01136","citing_title":"From Outliers to Errors: Auditing Pali-to-English LLM Translations with Multi-Reference Adjudication","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG","json":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG.json","graph_json":"https://pith.science/api/pith-number/A5V5XJFCLCLRIURJGXNKL4NJSG/graph.json","events_json":"https://pith.science/api/pith-number/A5V5XJFCLCLRIURJGXNKL4NJSG/events.json","paper":"https://pith.science/paper/A5V5XJFC"},"agent_actions":{"view_html":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG","download_json":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG.json","view_paper":"https://pith.science/paper/A5V5XJFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18707&json=true","fetch_graph":"https://pith.science/api/pith-number/A5V5XJFCLCLRIURJGXNKL4NJSG/graph.json","fetch_events":"https://pith.science/api/pith-number/A5V5XJFCLCLRIURJGXNKL4NJSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG/action/storage_attestation","attest_author":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG/action/author_attestation","sign_citation":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG/action/citation_signature","submit_replication":"https://pith.science/pith/A5V5XJFCLCLRIURJGXNKL4NJSG/action/replication_record"}},"created_at":"2026-07-05T10:19:56.888492+00:00","updated_at":"2026-07-05T10:19:56.888492+00:00"}