{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HP64FMPHG6GGZUYDWZYN5YUMLD","short_pith_number":"pith:HP64FMPH","schema_version":"1.0","canonical_sha256":"3bfdc2b1e7378c6cd303b670dee28c58f8c64acf1b23b34a9387a0dd0cbd3fae","source":{"kind":"arxiv","id":"2412.20584","version":2},"attestation_state":"computed","paper":{"title":"Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Madhavendra Thakur","submitted_at":"2024-12-29T21:12:39Z","abstract_excerpt":"No-resource languages - those with minimal or no digital representation - pose unique challenges for machine translation (MT). Unlike low-resource languages, which rely on limited but existent corpora, no-resource languages often have fewer than 100 sentences available for training. This work explores the problem of no-resource translation through three distinct workflows: fine-tuning of translation-specific models, in-context learning with large language models (LLMs) using chain-of-reasoning prompting, and direct prompting without reasoning. Using Owens Valley Paiute as a case study, we demo"},"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":"2412.20584","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T21:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"a9f30a7a97f196a5047b0e677a224661584b785f6d79b3d09bc32f5dba92f96c","abstract_canon_sha256":"2c66a3dfb346fb8c8a394ebb6fc579fe1490567b89ab6b9fe8f82893ad3cbef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:17.906499Z","signature_b64":"4c8Srnrx2K4e7qiGo6jnq4v0mtdHbfu3u4wjkkRsTopnrNHxBUOxjcEUmNj4DrRb0DaJjSH7EdRGqvRM6JJlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bfdc2b1e7378c6cd303b670dee28c58f8c64acf1b23b34a9387a0dd0cbd3fae","last_reissued_at":"2026-07-05T11:13:17.906021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:17.906021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Madhavendra Thakur","submitted_at":"2024-12-29T21:12:39Z","abstract_excerpt":"No-resource languages - those with minimal or no digital representation - pose unique challenges for machine translation (MT). Unlike low-resource languages, which rely on limited but existent corpora, no-resource languages often have fewer than 100 sentences available for training. This work explores the problem of no-resource translation through three distinct workflows: fine-tuning of translation-specific models, in-context learning with large language models (LLMs) using chain-of-reasoning prompting, and direct prompting without reasoning. Using Owens Valley Paiute as a case study, we demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20584","kind":"arxiv","version":2},"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/2412.20584/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":"2412.20584","created_at":"2026-07-05T11:13:17.906085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20584v2","created_at":"2026-07-05T11:13:17.906085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20584","created_at":"2026-07-05T11:13:17.906085+00:00"},{"alias_kind":"pith_short_12","alias_value":"HP64FMPHG6GG","created_at":"2026-07-05T11:13:17.906085+00:00"},{"alias_kind":"pith_short_16","alias_value":"HP64FMPHG6GGZUYD","created_at":"2026-07-05T11:13:17.906085+00:00"},{"alias_kind":"pith_short_8","alias_value":"HP64FMPH","created_at":"2026-07-05T11:13:17.906085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06420","citing_title":"A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD","json":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD.json","graph_json":"https://pith.science/api/pith-number/HP64FMPHG6GGZUYDWZYN5YUMLD/graph.json","events_json":"https://pith.science/api/pith-number/HP64FMPHG6GGZUYDWZYN5YUMLD/events.json","paper":"https://pith.science/paper/HP64FMPH"},"agent_actions":{"view_html":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD","download_json":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD.json","view_paper":"https://pith.science/paper/HP64FMPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20584&json=true","fetch_graph":"https://pith.science/api/pith-number/HP64FMPHG6GGZUYDWZYN5YUMLD/graph.json","fetch_events":"https://pith.science/api/pith-number/HP64FMPHG6GGZUYDWZYN5YUMLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD/action/storage_attestation","attest_author":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD/action/author_attestation","sign_citation":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD/action/citation_signature","submit_replication":"https://pith.science/pith/HP64FMPHG6GGZUYDWZYN5YUMLD/action/replication_record"}},"created_at":"2026-07-05T11:13:17.906085+00:00","updated_at":"2026-07-05T11:13:17.906085+00:00"}