{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NWW5DO2HWYP6EM5T4SYFBWMCU4","short_pith_number":"pith:NWW5DO2H","schema_version":"1.0","canonical_sha256":"6dadd1bb47b61fe233b3e4b050d982a717b3e05562fd8a6ec2d2786f95e3048a","source":{"kind":"arxiv","id":"2505.18638","version":2},"attestation_state":"computed","paper":{"title":"Multilingual Question Answering in Low-Resource Settings: A Dzongkha-English Benchmark for Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Md. Kishor Morol, Md. Tanzib Hosain, Rajan Das Gupta","submitted_at":"2025-05-24T11:01:05Z","abstract_excerpt":"In this work, we provide DZEN, a dataset of parallel Dzongkha and English test questions for Bhutanese middle and high school students. The over 5K questions in our collection span a variety of scientific topics and include factual, application, and reasoning-based questions. We use our parallel dataset to test a number of Large Language Models (LLMs) and find a significant performance difference between the models in English and Dzongkha. We also look at different prompting strategies and discover that Chain-of-Thought (CoT) prompting works well for reasoning questions but less well for factu"},"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":"2505.18638","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T11:01:05Z","cross_cats_sorted":[],"title_canon_sha256":"84a4e5f36dc0fc3312d2113b7ef56d7dca7f378c609535acbaf5d158a899ffca","abstract_canon_sha256":"c10717203b21a0a7590d4c4a8dc281514231f5e7f24960b96eda84953f745122"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:46.423823Z","signature_b64":"xtIunopYYjM3g1hSh653JJ46comGqrKRYGOJ2lRGOGTt6dKItq55zwdgD5lSi6n9O0mhKz6LwuFhNwWts23YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dadd1bb47b61fe233b3e4b050d982a717b3e05562fd8a6ec2d2786f95e3048a","last_reissued_at":"2026-07-05T11:11:46.423241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:46.423241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Question Answering in Low-Resource Settings: A Dzongkha-English Benchmark for Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Md. Kishor Morol, Md. Tanzib Hosain, Rajan Das Gupta","submitted_at":"2025-05-24T11:01:05Z","abstract_excerpt":"In this work, we provide DZEN, a dataset of parallel Dzongkha and English test questions for Bhutanese middle and high school students. The over 5K questions in our collection span a variety of scientific topics and include factual, application, and reasoning-based questions. We use our parallel dataset to test a number of Large Language Models (LLMs) and find a significant performance difference between the models in English and Dzongkha. We also look at different prompting strategies and discover that Chain-of-Thought (CoT) prompting works well for reasoning questions but less well for factu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18638","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/2505.18638/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":"2505.18638","created_at":"2026-07-05T11:11:46.423294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18638v2","created_at":"2026-07-05T11:11:46.423294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18638","created_at":"2026-07-05T11:11:46.423294+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWW5DO2HWYP6","created_at":"2026-07-05T11:11:46.423294+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWW5DO2HWYP6EM5T","created_at":"2026-07-05T11:11:46.423294+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWW5DO2H","created_at":"2026-07-05T11:11:46.423294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27816","citing_title":"Pattern Recognition Tasks with Personalized Federated Learning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4","json":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4.json","graph_json":"https://pith.science/api/pith-number/NWW5DO2HWYP6EM5T4SYFBWMCU4/graph.json","events_json":"https://pith.science/api/pith-number/NWW5DO2HWYP6EM5T4SYFBWMCU4/events.json","paper":"https://pith.science/paper/NWW5DO2H"},"agent_actions":{"view_html":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4","download_json":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4.json","view_paper":"https://pith.science/paper/NWW5DO2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18638&json=true","fetch_graph":"https://pith.science/api/pith-number/NWW5DO2HWYP6EM5T4SYFBWMCU4/graph.json","fetch_events":"https://pith.science/api/pith-number/NWW5DO2HWYP6EM5T4SYFBWMCU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4/action/storage_attestation","attest_author":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4/action/author_attestation","sign_citation":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4/action/citation_signature","submit_replication":"https://pith.science/pith/NWW5DO2HWYP6EM5T4SYFBWMCU4/action/replication_record"}},"created_at":"2026-07-05T11:11:46.423294+00:00","updated_at":"2026-07-05T11:11:46.423294+00:00"}