{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:75KFZ6WY57SFI76ZIQY33XNGGC","short_pith_number":"pith:75KFZ6WY","schema_version":"1.0","canonical_sha256":"ff545cfad8efe4547fd94431bddda630ba850f0da3515f647dd7dc1e259de13a","source":{"kind":"arxiv","id":"2505.21172","version":1},"attestation_state":"computed","paper":{"title":"TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mao Zheng, Mingyang Song, Wenjie Yang, Zheng Li","submitted_at":"2025-05-27T13:26:02Z","abstract_excerpt":"Recently, deep reasoning large language models(LLMs) like DeepSeek-R1 have made significant progress in tasks such as mathematics and coding. Inspired by this, several studies have employed reinforcement learning(RL) to enhance models' deep reasoning capabilities and improve machine translation(MT) quality. However, the terminology translation, an essential task in MT, remains unexplored in deep reasoning LLMs. In this paper, we propose \\textbf{TAT-R1}, a terminology-aware translation model trained with reinforcement learning and word alignment. Specifically, we first extract the keyword trans"},"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":"2505.21172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T13:26:02Z","cross_cats_sorted":[],"title_canon_sha256":"c72347f3c3fb68be004e1bef84170efc4a141aceae5640e79d38f9cec9f0b9c4","abstract_canon_sha256":"62dccf3acbc06e71ba292af058d3629b58613cb1a07aa0ef93ae61ed4c0a41ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:24.930848Z","signature_b64":"L83C3mvmcN9/io8DljKHFuHXzjd8ONPQOIaKS3npi8Cubhk49N4ST+jzE1E+Dx5iKH4r3C7DVcaUHprUchJrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff545cfad8efe4547fd94431bddda630ba850f0da3515f647dd7dc1e259de13a","last_reissued_at":"2026-07-05T11:10:24.930373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:24.930373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mao Zheng, Mingyang Song, Wenjie Yang, Zheng Li","submitted_at":"2025-05-27T13:26:02Z","abstract_excerpt":"Recently, deep reasoning large language models(LLMs) like DeepSeek-R1 have made significant progress in tasks such as mathematics and coding. Inspired by this, several studies have employed reinforcement learning(RL) to enhance models' deep reasoning capabilities and improve machine translation(MT) quality. However, the terminology translation, an essential task in MT, remains unexplored in deep reasoning LLMs. In this paper, we propose \\textbf{TAT-R1}, a terminology-aware translation model trained with reinforcement learning and word alignment. Specifically, we first extract the keyword trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21172","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/2505.21172/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":"2505.21172","created_at":"2026-07-05T11:10:24.930431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21172v1","created_at":"2026-07-05T11:10:24.930431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21172","created_at":"2026-07-05T11:10:24.930431+00:00"},{"alias_kind":"pith_short_12","alias_value":"75KFZ6WY57SF","created_at":"2026-07-05T11:10:24.930431+00:00"},{"alias_kind":"pith_short_16","alias_value":"75KFZ6WY57SFI76Z","created_at":"2026-07-05T11:10:24.930431+00:00"},{"alias_kind":"pith_short_8","alias_value":"75KFZ6WY","created_at":"2026-07-05T11:10:24.930431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.03790","citing_title":"NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC","json":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC.json","graph_json":"https://pith.science/api/pith-number/75KFZ6WY57SFI76ZIQY33XNGGC/graph.json","events_json":"https://pith.science/api/pith-number/75KFZ6WY57SFI76ZIQY33XNGGC/events.json","paper":"https://pith.science/paper/75KFZ6WY"},"agent_actions":{"view_html":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC","download_json":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC.json","view_paper":"https://pith.science/paper/75KFZ6WY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21172&json=true","fetch_graph":"https://pith.science/api/pith-number/75KFZ6WY57SFI76ZIQY33XNGGC/graph.json","fetch_events":"https://pith.science/api/pith-number/75KFZ6WY57SFI76ZIQY33XNGGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC/action/storage_attestation","attest_author":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC/action/author_attestation","sign_citation":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC/action/citation_signature","submit_replication":"https://pith.science/pith/75KFZ6WY57SFI76ZIQY33XNGGC/action/replication_record"}},"created_at":"2026-07-05T11:10:24.930431+00:00","updated_at":"2026-07-05T11:10:24.930431+00:00"}