{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RHWXPPJTJ5PXCNGF3KWYXA5ZAP","short_pith_number":"pith:RHWXPPJT","schema_version":"1.0","canonical_sha256":"89ed77bd334f5f7134c5daad8b83b903ff4eb233b7454cb06177676ef26bfd89","source":{"kind":"arxiv","id":"2505.18159","version":1},"attestation_state":"computed","paper":{"title":"Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashley Celeste Prado, Daua D. Karajeanes, Ivory Yang, Jesus Alvarez C, John Ruttan, Kevin Zhu, Sean O'Brien, Vasu Sharma","submitted_at":"2025-05-10T06:11:58Z","abstract_excerpt":"The digital exclusion of endangered languages remains a critical challenge in NLP, limiting both linguistic research and revitalization efforts. This study introduces the first computational investigation of Comanche, an Uto-Aztecan language on the verge of extinction, demonstrating how minimal-cost, community-informed NLP interventions can support language preservation. We present a manually curated dataset of 412 phrases, a synthetic data generation pipeline, and an empirical evaluation of GPT-4o and GPT-4o-mini for language identification. Our experiments reveal that while LLMs struggle wit"},"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":"2505.18159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T06:11:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5c048ac2b87ab25bb57c50fe1e2a4e8b618940d97b08488cf6635d8d53451c6b","abstract_canon_sha256":"9b474a2cd607f0d910b45e3067d5ce2bf7b6caacd782ad981c42981cd5d0d617"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:42.075563Z","signature_b64":"mcFK7fK5j6k1yv1vc3DXhRNX0ecjN4GsQw7S8Bkf/Mf+StzACTpkL9DfWS5jvUIHn7CrNMnjzgy3GE3RM18wAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ed77bd334f5f7134c5daad8b83b903ff4eb233b7454cb06177676ef26bfd89","last_reissued_at":"2026-07-05T11:08:42.075152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:42.075152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashley Celeste Prado, Daua D. Karajeanes, Ivory Yang, Jesus Alvarez C, John Ruttan, Kevin Zhu, Sean O'Brien, Vasu Sharma","submitted_at":"2025-05-10T06:11:58Z","abstract_excerpt":"The digital exclusion of endangered languages remains a critical challenge in NLP, limiting both linguistic research and revitalization efforts. This study introduces the first computational investigation of Comanche, an Uto-Aztecan language on the verge of extinction, demonstrating how minimal-cost, community-informed NLP interventions can support language preservation. We present a manually curated dataset of 412 phrases, a synthetic data generation pipeline, and an empirical evaluation of GPT-4o and GPT-4o-mini for language identification. Our experiments reveal that while LLMs struggle wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18159","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/2505.18159/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":"2505.18159","created_at":"2026-07-05T11:08:42.075208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18159v1","created_at":"2026-07-05T11:08:42.075208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18159","created_at":"2026-07-05T11:08:42.075208+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHWXPPJTJ5PX","created_at":"2026-07-05T11:08:42.075208+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHWXPPJTJ5PXCNGF","created_at":"2026-07-05T11:08:42.075208+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHWXPPJT","created_at":"2026-07-05T11:08:42.075208+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/RHWXPPJTJ5PXCNGF3KWYXA5ZAP","json":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP.json","graph_json":"https://pith.science/api/pith-number/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/graph.json","events_json":"https://pith.science/api/pith-number/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/events.json","paper":"https://pith.science/paper/RHWXPPJT"},"agent_actions":{"view_html":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP","download_json":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP.json","view_paper":"https://pith.science/paper/RHWXPPJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18159&json=true","fetch_graph":"https://pith.science/api/pith-number/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/graph.json","fetch_events":"https://pith.science/api/pith-number/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/action/storage_attestation","attest_author":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/action/author_attestation","sign_citation":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/action/citation_signature","submit_replication":"https://pith.science/pith/RHWXPPJTJ5PXCNGF3KWYXA5ZAP/action/replication_record"}},"created_at":"2026-07-05T11:08:42.075208+00:00","updated_at":"2026-07-05T11:08:42.075208+00:00"}