{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UWPTMCCMUWZBL7ZGKMCU3WXO26","short_pith_number":"pith:UWPTMCCM","schema_version":"1.0","canonical_sha256":"a59f36084ca5b215ff2653054ddaeed7b6d5fe2398ac6180361f5bdc13bc03df","source":{"kind":"arxiv","id":"2602.18788","version":3},"attestation_state":"computed","paper":{"title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jann Railey Montalan, Jian Gang Ngui, Peerat Limkonchotiwat, Thura Aung","submitted_at":"2026-02-21T10:43:07Z","abstract_excerpt":"We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP competencies: understanding (NLU), reasoning (NLR), and generation (NLG). BURMESE-SAN consolidates seven subtasks spanning these competencies, including Question Answering, Sentiment Analysis, Toxicity Detection, Causal Reasoning, Natural Language Inference, Abstractive Summarization, and Machine Translation, several of which were previously unavailable for Burmese. The benchmark is constructed through a rigorous native-speaker-driven process to en"},"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":"2602.18788","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-21T10:43:07Z","cross_cats_sorted":[],"title_canon_sha256":"b751029c65f864ce8eb8c7e56b161b13842d6abb7653e41879219d7aa3b02837","abstract_canon_sha256":"de062398005e8ef326d184168edbefea1634f87d44dfcea88c345a01377754b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:15.820385Z","signature_b64":"uEh3YOEVN2SzGkuM23kFu55DHJ6VbQ1brx5pKq8GGudLfzUfhDXduSJj79c3u2ShtKMDAS5LyZc5gVC/w9bQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a59f36084ca5b215ff2653054ddaeed7b6d5fe2398ac6180361f5bdc13bc03df","last_reissued_at":"2026-05-25T02:01:15.819435Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:15.819435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jann Railey Montalan, Jian Gang Ngui, Peerat Limkonchotiwat, Thura Aung","submitted_at":"2026-02-21T10:43:07Z","abstract_excerpt":"We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP competencies: understanding (NLU), reasoning (NLR), and generation (NLG). BURMESE-SAN consolidates seven subtasks spanning these competencies, including Question Answering, Sentiment Analysis, Toxicity Detection, Causal Reasoning, Natural Language Inference, Abstractive Summarization, and Machine Translation, several of which were previously unavailable for Burmese. The benchmark is constructed through a rigorous native-speaker-driven process to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18788","kind":"arxiv","version":3},"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/2602.18788/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":"2602.18788","created_at":"2026-05-25T02:01:15.819571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18788v3","created_at":"2026-05-25T02:01:15.819571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18788","created_at":"2026-05-25T02:01:15.819571+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWPTMCCMUWZB","created_at":"2026-05-25T02:01:15.819571+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWPTMCCMUWZBL7ZG","created_at":"2026-05-25T02:01:15.819571+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWPTMCCM","created_at":"2026-05-25T02:01:15.819571+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/UWPTMCCMUWZBL7ZGKMCU3WXO26","json":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26.json","graph_json":"https://pith.science/api/pith-number/UWPTMCCMUWZBL7ZGKMCU3WXO26/graph.json","events_json":"https://pith.science/api/pith-number/UWPTMCCMUWZBL7ZGKMCU3WXO26/events.json","paper":"https://pith.science/paper/UWPTMCCM"},"agent_actions":{"view_html":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26","download_json":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26.json","view_paper":"https://pith.science/paper/UWPTMCCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18788&json=true","fetch_graph":"https://pith.science/api/pith-number/UWPTMCCMUWZBL7ZGKMCU3WXO26/graph.json","fetch_events":"https://pith.science/api/pith-number/UWPTMCCMUWZBL7ZGKMCU3WXO26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26/action/storage_attestation","attest_author":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26/action/author_attestation","sign_citation":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26/action/citation_signature","submit_replication":"https://pith.science/pith/UWPTMCCMUWZBL7ZGKMCU3WXO26/action/replication_record"}},"created_at":"2026-05-25T02:01:15.819571+00:00","updated_at":"2026-05-25T02:01:15.819571+00:00"}