{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UMDCI4PEVEJV7DU4YQFNSNS3D4","short_pith_number":"pith:UMDCI4PE","schema_version":"1.0","canonical_sha256":"a3062471e4a9135f8e9cc40ad9365b1f3ae7d8864347c88d0058b37009ed2ca8","source":{"kind":"arxiv","id":"2506.21563","version":1},"attestation_state":"computed","paper":{"title":"FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaoPeng Zhang, Hsiyu Chen, Kaiying Kevin Lin","submitted_at":"2025-06-12T07:02:28Z","abstract_excerpt":"While large language models (LLMs) have demonstrated impressive performance across a wide range of natural language processing (NLP) tasks in high-resource languages, their capabilities in low-resource and minority languages remain significantly underexplored. Formosan languages -- a subgroup of Austronesian languages spoken in Taiwan -- are both linguistically rich and endangered, largely due to the sociolinguistic dominance of Mandarin. In this work, we introduce FORMOSANBENCH, the first benchmark for evaluating LLMs on low-resource Austronesian languages. It covers three endangered Formosan"},"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":"2506.21563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T07:02:28Z","cross_cats_sorted":[],"title_canon_sha256":"9f86b43c6bd6a595ea35818bce9f32c2663bbc551f7b33043b5bb7ab25562511","abstract_canon_sha256":"4eacced3b35c5ced7b5030110177e764867920b1f05edaec3222622d89709644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.405810Z","signature_b64":"+fykHlg0bdyxDd/BaTiu0JEty2PXV7a3iCDwZx1qC14hRJ5jMGg/LO4NFcHbWb/zwvYrRhs+AdjgP2nHby8NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3062471e4a9135f8e9cc40ad9365b1f3ae7d8864347c88d0058b37009ed2ca8","last_reissued_at":"2026-07-05T11:27:56.405350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.405350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaoPeng Zhang, Hsiyu Chen, Kaiying Kevin Lin","submitted_at":"2025-06-12T07:02:28Z","abstract_excerpt":"While large language models (LLMs) have demonstrated impressive performance across a wide range of natural language processing (NLP) tasks in high-resource languages, their capabilities in low-resource and minority languages remain significantly underexplored. Formosan languages -- a subgroup of Austronesian languages spoken in Taiwan -- are both linguistically rich and endangered, largely due to the sociolinguistic dominance of Mandarin. In this work, we introduce FORMOSANBENCH, the first benchmark for evaluating LLMs on low-resource Austronesian languages. It covers three endangered Formosan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21563","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/2506.21563/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":"2506.21563","created_at":"2026-07-05T11:27:56.405409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21563v1","created_at":"2026-07-05T11:27:56.405409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21563","created_at":"2026-07-05T11:27:56.405409+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMDCI4PEVEJV","created_at":"2026-07-05T11:27:56.405409+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMDCI4PEVEJV7DU4","created_at":"2026-07-05T11:27:56.405409+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMDCI4PE","created_at":"2026-07-05T11:27:56.405409+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/UMDCI4PEVEJV7DU4YQFNSNS3D4","json":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4.json","graph_json":"https://pith.science/api/pith-number/UMDCI4PEVEJV7DU4YQFNSNS3D4/graph.json","events_json":"https://pith.science/api/pith-number/UMDCI4PEVEJV7DU4YQFNSNS3D4/events.json","paper":"https://pith.science/paper/UMDCI4PE"},"agent_actions":{"view_html":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4","download_json":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4.json","view_paper":"https://pith.science/paper/UMDCI4PE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21563&json=true","fetch_graph":"https://pith.science/api/pith-number/UMDCI4PEVEJV7DU4YQFNSNS3D4/graph.json","fetch_events":"https://pith.science/api/pith-number/UMDCI4PEVEJV7DU4YQFNSNS3D4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4/action/storage_attestation","attest_author":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4/action/author_attestation","sign_citation":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4/action/citation_signature","submit_replication":"https://pith.science/pith/UMDCI4PEVEJV7DU4YQFNSNS3D4/action/replication_record"}},"created_at":"2026-07-05T11:27:56.405409+00:00","updated_at":"2026-07-05T11:27:56.405409+00:00"}