{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TYP47B4KS5N3M3NG4263F3URZ7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e1d150deb646879a8086f2cb63ff429cc274a7fed047c58faef3ee209065f9a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T06:58:02Z","title_canon_sha256":"9e82bdff3f13fa76cbdaf4a5198a16a44888b687f8023e4886821f0610faa3cd"},"schema_version":"1.0","source":{"id":"2508.08680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08680","created_at":"2026-07-05T11:52:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08680v1","created_at":"2026-07-05T11:52:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08680","created_at":"2026-07-05T11:52:32Z"},{"alias_kind":"pith_short_12","alias_value":"TYP47B4KS5N3","created_at":"2026-07-05T11:52:32Z"},{"alias_kind":"pith_short_16","alias_value":"TYP47B4KS5N3M3NG","created_at":"2026-07-05T11:52:32Z"},{"alias_kind":"pith_short_8","alias_value":"TYP47B4K","created_at":"2026-07-05T11:52:32Z"}],"graph_snapshots":[{"event_id":"sha256:bc232dc55b38099476830800bcc63c4877708b161b613ae4dae78cb9e5672e0a","target":"graph","created_at":"2026-07-05T11:52:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.08680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Armel Zebaze, Beno\\^it Sagot, Rachel Bawden","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T06:58:02Z","title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08680","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7ca76b68530bc184de3b62f5982a6b1ba99ffac969322991b4fea59b799dd6d8","target":"record","created_at":"2026-07-05T11:52:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e1d150deb646879a8086f2cb63ff429cc274a7fed047c58faef3ee209065f9a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T06:58:02Z","title_canon_sha256":"9e82bdff3f13fa76cbdaf4a5198a16a44888b687f8023e4886821f0610faa3cd"},"schema_version":"1.0","source":{"id":"2508.08680","kind":"arxiv","version":1}},"canonical_sha256":"9e1fcf878a975bb66da6e6bdb2ee91cffc3aeddd71d61f07205b919e374038c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e1fcf878a975bb66da6e6bdb2ee91cffc3aeddd71d61f07205b919e374038c6","first_computed_at":"2026-07-05T11:52:32.244949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:32.244949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+UjQCd2VPp0e2TRxd1fA1t5lysrTMTYpLLMi/bTJdE1wFtQDlm7lxq2k9zjnR5tCFa8I68xih2vi2HnVqpXqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:32.245449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ca76b68530bc184de3b62f5982a6b1ba99ffac969322991b4fea59b799dd6d8","sha256:bc232dc55b38099476830800bcc63c4877708b161b613ae4dae78cb9e5672e0a"],"state_sha256":"f0c33db1b852c25bc3a6394add32d29690483631ef0286581b561b809dbdb098"}