{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HQJUNWT65IIY3UWGDD2UP42KCR","short_pith_number":"pith:HQJUNWT6","schema_version":"1.0","canonical_sha256":"3c1346da7eea118dd2c618f547f34a1470458bbb73c094415cabc9f12c9c4772","source":{"kind":"arxiv","id":"2606.06420","version":1},"attestation_state":"computed","paper":{"title":"A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Petr Parshakov","submitted_at":"2026-06-04T17:26:38Z","abstract_excerpt":"We present the first Komi-Yazva--Russian parallel corpus together with an explicit evaluation protocol for studying LLM translation in an endangered, extremely low-resource setting. The dataset contains 457 aligned sentence pairs from 74 narrative texts and is accompanied by documented provenance, sentence-level alignment, and story identifiers that enable leakage-aware evaluation. We use this setup to compare modern large language models on Komi-Yazva-to-Russian translation under severe parallel-data scarcity in zero-shot and retrieval-based few-shot regimes. The protocol includes story-level"},"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":"2606.06420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T17:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"13fd71e18ea4067413be962cdc6f5076d1a9e2bebc50d102e0f296562ed97234","abstract_canon_sha256":"936644150e73414c46a39b6dfce57938570de9ce345d0d6bdda3ca1c85d7c87b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:45.053146Z","signature_b64":"mABAMIu5fcOxLA/AILdrpY/e32Lqo8pVRPPOrmDmGFG3JUmmpodXBuwxpeeit7HTgzAsRhmQiv1qw+MzvQy0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c1346da7eea118dd2c618f547f34a1470458bbb73c094415cabc9f12c9c4772","last_reissued_at":"2026-06-05T01:15:45.052740Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:45.052740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Petr Parshakov","submitted_at":"2026-06-04T17:26:38Z","abstract_excerpt":"We present the first Komi-Yazva--Russian parallel corpus together with an explicit evaluation protocol for studying LLM translation in an endangered, extremely low-resource setting. The dataset contains 457 aligned sentence pairs from 74 narrative texts and is accompanied by documented provenance, sentence-level alignment, and story identifiers that enable leakage-aware evaluation. We use this setup to compare modern large language models on Komi-Yazva-to-Russian translation under severe parallel-data scarcity in zero-shot and retrieval-based few-shot regimes. The protocol includes story-level"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06420","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/2606.06420/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":"2606.06420","created_at":"2026-06-05T01:15:45.052812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06420v1","created_at":"2026-06-05T01:15:45.052812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06420","created_at":"2026-06-05T01:15:45.052812+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQJUNWT65IIY","created_at":"2026-06-05T01:15:45.052812+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQJUNWT65IIY3UWG","created_at":"2026-06-05T01:15:45.052812+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQJUNWT6","created_at":"2026-06-05T01:15:45.052812+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/HQJUNWT65IIY3UWGDD2UP42KCR","json":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR.json","graph_json":"https://pith.science/api/pith-number/HQJUNWT65IIY3UWGDD2UP42KCR/graph.json","events_json":"https://pith.science/api/pith-number/HQJUNWT65IIY3UWGDD2UP42KCR/events.json","paper":"https://pith.science/paper/HQJUNWT6"},"agent_actions":{"view_html":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR","download_json":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR.json","view_paper":"https://pith.science/paper/HQJUNWT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06420&json=true","fetch_graph":"https://pith.science/api/pith-number/HQJUNWT65IIY3UWGDD2UP42KCR/graph.json","fetch_events":"https://pith.science/api/pith-number/HQJUNWT65IIY3UWGDD2UP42KCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR/action/storage_attestation","attest_author":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR/action/author_attestation","sign_citation":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR/action/citation_signature","submit_replication":"https://pith.science/pith/HQJUNWT65IIY3UWGDD2UP42KCR/action/replication_record"}},"created_at":"2026-06-05T01:15:45.052812+00:00","updated_at":"2026-06-05T01:15:45.052812+00:00"}