{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TYP47B4KS5N3M3NG4263F3URZ7","short_pith_number":"pith:TYP47B4K","schema_version":"1.0","canonical_sha256":"9e1fcf878a975bb66da6e6bdb2ee91cffc3aeddd71d61f07205b919e374038c6","source":{"kind":"arxiv","id":"2508.08680","version":1},"attestation_state":"computed","paper":{"title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armel Zebaze, Beno\\^it Sagot, Rachel Bawden","submitted_at":"2025-08-12T06:58:02Z","abstract_excerpt":"LLMs have been shown to perform well in machine translation (MT) with the use of in-context learning (ICL), rivaling supervised models when translating into high-resource languages (HRLs). However, they lag behind when translating into low-resource language (LRLs). Example selection via similarity search and supervised fine-tuning help. However the improvements they give are limited by the size, quality and diversity of existing parallel datasets. A common technique in low-resource MT is synthetic parallel data creation, the most frequent of which is backtranslation, whereby existing target-si"},"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":"2508.08680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T06:58:02Z","cross_cats_sorted":[],"title_canon_sha256":"9e82bdff3f13fa76cbdaf4a5198a16a44888b687f8023e4886821f0610faa3cd","abstract_canon_sha256":"e1d150deb646879a8086f2cb63ff429cc274a7fed047c58faef3ee209065f9a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:32.245449Z","signature_b64":"+UjQCd2VPp0e2TRxd1fA1t5lysrTMTYpLLMi/bTJdE1wFtQDlm7lxq2k9zjnR5tCFa8I68xih2vi2HnVqpXqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e1fcf878a975bb66da6e6bdb2ee91cffc3aeddd71d61f07205b919e374038c6","last_reissued_at":"2026-07-05T11:52:32.244949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:32.244949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armel Zebaze, Beno\\^it Sagot, Rachel Bawden","submitted_at":"2025-08-12T06:58:02Z","abstract_excerpt":"LLMs have been shown to perform well in machine translation (MT) with the use of in-context learning (ICL), rivaling supervised models when translating into high-resource languages (HRLs). However, they lag behind when translating into low-resource language (LRLs). Example selection via similarity search and supervised fine-tuning help. However the improvements they give are limited by the size, quality and diversity of existing parallel datasets. A common technique in low-resource MT is synthetic parallel data creation, the most frequent of which is backtranslation, whereby existing target-si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08680","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/2508.08680/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":"2508.08680","created_at":"2026-07-05T11:52:32.245013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08680v1","created_at":"2026-07-05T11:52:32.245013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08680","created_at":"2026-07-05T11:52:32.245013+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYP47B4KS5N3","created_at":"2026-07-05T11:52:32.245013+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYP47B4KS5N3M3NG","created_at":"2026-07-05T11:52:32.245013+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYP47B4K","created_at":"2026-07-05T11:52:32.245013+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/TYP47B4KS5N3M3NG4263F3URZ7","json":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7.json","graph_json":"https://pith.science/api/pith-number/TYP47B4KS5N3M3NG4263F3URZ7/graph.json","events_json":"https://pith.science/api/pith-number/TYP47B4KS5N3M3NG4263F3URZ7/events.json","paper":"https://pith.science/paper/TYP47B4K"},"agent_actions":{"view_html":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7","download_json":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7.json","view_paper":"https://pith.science/paper/TYP47B4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08680&json=true","fetch_graph":"https://pith.science/api/pith-number/TYP47B4KS5N3M3NG4263F3URZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/TYP47B4KS5N3M3NG4263F3URZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7/action/storage_attestation","attest_author":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7/action/author_attestation","sign_citation":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7/action/citation_signature","submit_replication":"https://pith.science/pith/TYP47B4KS5N3M3NG4263F3URZ7/action/replication_record"}},"created_at":"2026-07-05T11:52:32.245013+00:00","updated_at":"2026-07-05T11:52:32.245013+00:00"}