{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BGSKOX2JALOH73PMRCJH3A7RGG","short_pith_number":"pith:BGSKOX2J","schema_version":"1.0","canonical_sha256":"09a4a75f4902dc7fedec88927d83f13185cdec1b3f82337b2676c9d1aa6b8796","source":{"kind":"arxiv","id":"2506.07617","version":1},"attestation_state":"computed","paper":{"title":"Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ihor Pysmennyi, Roman Kyslyi, Yuliia Maksymiuk","submitted_at":"2025-06-09T10:30:35Z","abstract_excerpt":"In this paper we introduce the first effort to adapt large language models (LLMs) to the Ukrainian dialect (in our case Hutsul), a low-resource and morphologically complex dialect spoken in the Carpathian Highlands. We created a parallel corpus of 9852 dialect-to-standard Ukrainian sentence pairs and a dictionary of 7320 dialectal word mappings. We also addressed data shortage by proposing an advanced Retrieval-Augmented Generation (RAG) pipeline to generate synthetic parallel translation pairs, expanding the corpus with 52142 examples. We have fine-tuned multiple open-source LLMs using LoRA a"},"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":"2506.07617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:30:35Z","cross_cats_sorted":[],"title_canon_sha256":"190dcc4b71d36a4b72663823e1fd65a8be400efd2ebced4fe31a93eb4f5c21fc","abstract_canon_sha256":"86ce661eaff7cb5c2c34931bddf44aaf470c0e7ea1a7fab9087c2c2741c1d2d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:32.695265Z","signature_b64":"AxAMH/sb9SX8aY2BMcbabEQU5dEr7BNxz6Ic6fvKPuAGKZpEXnDNXHOm1fYVfKZXwUbZkgBQp/e/phus6ucPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09a4a75f4902dc7fedec88927d83f13185cdec1b3f82337b2676c9d1aa6b8796","last_reissued_at":"2026-07-05T11:43:32.694810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:32.694810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ihor Pysmennyi, Roman Kyslyi, Yuliia Maksymiuk","submitted_at":"2025-06-09T10:30:35Z","abstract_excerpt":"In this paper we introduce the first effort to adapt large language models (LLMs) to the Ukrainian dialect (in our case Hutsul), a low-resource and morphologically complex dialect spoken in the Carpathian Highlands. We created a parallel corpus of 9852 dialect-to-standard Ukrainian sentence pairs and a dictionary of 7320 dialectal word mappings. We also addressed data shortage by proposing an advanced Retrieval-Augmented Generation (RAG) pipeline to generate synthetic parallel translation pairs, expanding the corpus with 52142 examples. We have fine-tuned multiple open-source LLMs using LoRA a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07617","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/2506.07617/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":"2506.07617","created_at":"2026-07-05T11:43:32.694868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07617v1","created_at":"2026-07-05T11:43:32.694868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07617","created_at":"2026-07-05T11:43:32.694868+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGSKOX2JALOH","created_at":"2026-07-05T11:43:32.694868+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGSKOX2JALOH73PM","created_at":"2026-07-05T11:43:32.694868+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGSKOX2J","created_at":"2026-07-05T11:43:32.694868+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/BGSKOX2JALOH73PMRCJH3A7RGG","json":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG.json","graph_json":"https://pith.science/api/pith-number/BGSKOX2JALOH73PMRCJH3A7RGG/graph.json","events_json":"https://pith.science/api/pith-number/BGSKOX2JALOH73PMRCJH3A7RGG/events.json","paper":"https://pith.science/paper/BGSKOX2J"},"agent_actions":{"view_html":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG","download_json":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG.json","view_paper":"https://pith.science/paper/BGSKOX2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07617&json=true","fetch_graph":"https://pith.science/api/pith-number/BGSKOX2JALOH73PMRCJH3A7RGG/graph.json","fetch_events":"https://pith.science/api/pith-number/BGSKOX2JALOH73PMRCJH3A7RGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/action/storage_attestation","attest_author":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/action/author_attestation","sign_citation":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/action/citation_signature","submit_replication":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/action/replication_record"}},"created_at":"2026-07-05T11:43:32.694868+00:00","updated_at":"2026-07-05T11:43:32.694868+00:00"}