{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BGSKOX2JALOH73PMRCJH3A7RGG","short_pith_number":"pith:BGSKOX2J","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"},"canonical_sha256":"09a4a75f4902dc7fedec88927d83f13185cdec1b3f82337b2676c9d1aa6b8796","source":{"kind":"arxiv","id":"2506.07617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07617","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07617v1","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07617","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"BGSKOX2JALOH","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"BGSKOX2JALOH73PM","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"BGSKOX2J","created_at":"2026-07-05T11:43:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BGSKOX2JALOH73PMRCJH3A7RGG","target":"record","payload":{"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"},"canonical_sha256":"09a4a75f4902dc7fedec88927d83f13185cdec1b3f82337b2676c9d1aa6b8796","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"},"source_kind":"arxiv","source_id":"2506.07617","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tM7W3Uvwe0XUXY/ze91ZtjNG2rl9pOretoop2b2trEY2gGv65Auob2t9hEwQF/5MpM83LXs2hMiHwf3mXN0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:45:43.233255Z"},"content_sha256":"9696d0fd31710f2ae3d1ccf0241fb2f885de7f6c0e93f488247307ef112f9172","schema_version":"1.0","event_id":"sha256:9696d0fd31710f2ae3d1ccf0241fb2f885de7f6c0e93f488247307ef112f9172"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BGSKOX2JALOH73PMRCJH3A7RGG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"exsWm3BCjVI43Ekn5/f64JGoLFGM6pSxXrCYbciPdsfvias+xTr7jxkP+EhKJyTGK6RaHeyThnJBfbvUAKGmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:45:43.234245Z"},"content_sha256":"0ff204f9b574d56b529974a7a8ef65d369a5610b34bc88d596567c933f997ace","schema_version":"1.0","event_id":"sha256:0ff204f9b574d56b529974a7a8ef65d369a5610b34bc88d596567c933f997ace"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/bundle.json","state_url":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGSKOX2JALOH73PMRCJH3A7RGG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T11:45:43Z","links":{"resolver":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG","bundle":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/bundle.json","state":"https://pith.science/pith/BGSKOX2JALOH73PMRCJH3A7RGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGSKOX2JALOH73PMRCJH3A7RGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BGSKOX2JALOH73PMRCJH3A7RGG","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":"86ce661eaff7cb5c2c34931bddf44aaf470c0e7ea1a7fab9087c2c2741c1d2d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:30:35Z","title_canon_sha256":"190dcc4b71d36a4b72663823e1fd65a8be400efd2ebced4fe31a93eb4f5c21fc"},"schema_version":"1.0","source":{"id":"2506.07617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07617","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07617v1","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07617","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"BGSKOX2JALOH","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"BGSKOX2JALOH73PM","created_at":"2026-07-05T11:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"BGSKOX2J","created_at":"2026-07-05T11:43:32Z"}],"graph_snapshots":[{"event_id":"sha256:0ff204f9b574d56b529974a7a8ef65d369a5610b34bc88d596567c933f997ace","target":"graph","created_at":"2026-07-05T11:43:32Z","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/2506.07617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ihor Pysmennyi, Roman Kyslyi, Yuliia Maksymiuk","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:30:35Z","title":"Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07617","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":"sha256:9696d0fd31710f2ae3d1ccf0241fb2f885de7f6c0e93f488247307ef112f9172","target":"record","created_at":"2026-07-05T11:43:32Z","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":"86ce661eaff7cb5c2c34931bddf44aaf470c0e7ea1a7fab9087c2c2741c1d2d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:30:35Z","title_canon_sha256":"190dcc4b71d36a4b72663823e1fd65a8be400efd2ebced4fe31a93eb4f5c21fc"},"schema_version":"1.0","source":{"id":"2506.07617","kind":"arxiv","version":1}},"canonical_sha256":"09a4a75f4902dc7fedec88927d83f13185cdec1b3f82337b2676c9d1aa6b8796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09a4a75f4902dc7fedec88927d83f13185cdec1b3f82337b2676c9d1aa6b8796","first_computed_at":"2026-07-05T11:43:32.694810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:32.694810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AxAMH/sb9SX8aY2BMcbabEQU5dEr7BNxz6Ic6fvKPuAGKZpEXnDNXHOm1fYVfKZXwUbZkgBQp/e/phus6ucPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:32.695265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9696d0fd31710f2ae3d1ccf0241fb2f885de7f6c0e93f488247307ef112f9172","sha256:0ff204f9b574d56b529974a7a8ef65d369a5610b34bc88d596567c933f997ace"],"state_sha256":"748f323f6e650d03ba0ab1e17845f66a27e5b40efe6a96e7010cbc24ab96e986"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Uc0O5hiuJalJFdFhSeeAc5+k33fYlFPvR8f23S5ZvCD00tiYDpDHnAo3ZpNCp/vOzPPGWCp24UyvDFDzfhsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:45:43.240630Z","bundle_sha256":"11e3e179b27ac4779046528800b2814c315dfabf512ed67145ccbe1b35abc941"}}