{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F5Q67YPAKZP4GZ3675DT7OK7DM","short_pith_number":"pith:F5Q67YPA","schema_version":"1.0","canonical_sha256":"2f61efe1e0565fc3677eff473fb95f1b081246cc7e811bce3b24807db5f9b3ed","source":{"kind":"arxiv","id":"2503.10351","version":2},"attestation_state":"computed","paper":{"title":"New Trends for Modern Machine Translation with Large Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyang Lyu, Kaifu Zhang, Longyue Wang, Minghao Wu, Sinuo Liu, Weihua Luo, Zifu Shang","submitted_at":"2025-03-13T13:27:53Z","abstract_excerpt":"Recent advances in Large Reasoning Models (LRMs), particularly those leveraging Chain-of-Thought reasoning (CoT), have opened brand new possibility for Machine Translation (MT). This position paper argues that LRMs substantially transformed traditional neural MT as well as LLMs-based MT paradigms by reframing translation as a dynamic reasoning task that requires contextual, cultural, and linguistic understanding and reasoning. We identify three foundational shifts: 1) contextual coherence, where LRMs resolve ambiguities and preserve discourse structure through explicit reasoning over cross-sen"},"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":"2503.10351","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T13:27:53Z","cross_cats_sorted":[],"title_canon_sha256":"550fd81c8c6fcd9298b495117ee720d9ba9075efcf6afe5da55b83d88927fa2c","abstract_canon_sha256":"7e1f83d00f5be7f2012e2e81f903a25987be453c43e1b26620b66edf43bdd0b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:27.814334Z","signature_b64":"buF2ee4gwybmMFr4dYL6i7b6CaRhnqNYLg/V4b4sE/uEp2fWxnQXaTpTziYba/XXlAIz08/hZ+dc+DUlHRjlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f61efe1e0565fc3677eff473fb95f1b081246cc7e811bce3b24807db5f9b3ed","last_reissued_at":"2026-07-05T10:31:27.813643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:27.813643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"New Trends for Modern Machine Translation with Large Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyang Lyu, Kaifu Zhang, Longyue Wang, Minghao Wu, Sinuo Liu, Weihua Luo, Zifu Shang","submitted_at":"2025-03-13T13:27:53Z","abstract_excerpt":"Recent advances in Large Reasoning Models (LRMs), particularly those leveraging Chain-of-Thought reasoning (CoT), have opened brand new possibility for Machine Translation (MT). This position paper argues that LRMs substantially transformed traditional neural MT as well as LLMs-based MT paradigms by reframing translation as a dynamic reasoning task that requires contextual, cultural, and linguistic understanding and reasoning. We identify three foundational shifts: 1) contextual coherence, where LRMs resolve ambiguities and preserve discourse structure through explicit reasoning over cross-sen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10351","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/2503.10351/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":"2503.10351","created_at":"2026-07-05T10:31:27.813734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10351v2","created_at":"2026-07-05T10:31:27.813734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10351","created_at":"2026-07-05T10:31:27.813734+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5Q67YPAKZP4","created_at":"2026-07-05T10:31:27.813734+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5Q67YPAKZP4GZ36","created_at":"2026-07-05T10:31:27.813734+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5Q67YPA","created_at":"2026-07-05T10:31:27.813734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03259","citing_title":"Beyond \"To whom it may concern\": Tailoring Machine Translation to Audience and Intent","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19144","citing_title":"ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM","json":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM.json","graph_json":"https://pith.science/api/pith-number/F5Q67YPAKZP4GZ3675DT7OK7DM/graph.json","events_json":"https://pith.science/api/pith-number/F5Q67YPAKZP4GZ3675DT7OK7DM/events.json","paper":"https://pith.science/paper/F5Q67YPA"},"agent_actions":{"view_html":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM","download_json":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM.json","view_paper":"https://pith.science/paper/F5Q67YPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10351&json=true","fetch_graph":"https://pith.science/api/pith-number/F5Q67YPAKZP4GZ3675DT7OK7DM/graph.json","fetch_events":"https://pith.science/api/pith-number/F5Q67YPAKZP4GZ3675DT7OK7DM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM/action/storage_attestation","attest_author":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM/action/author_attestation","sign_citation":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM/action/citation_signature","submit_replication":"https://pith.science/pith/F5Q67YPAKZP4GZ3675DT7OK7DM/action/replication_record"}},"created_at":"2026-07-05T10:31:27.813734+00:00","updated_at":"2026-07-05T10:31:27.813734+00:00"}