{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EVN6FLTMQE3ZI7KZMOH2DTD55X","short_pith_number":"pith:EVN6FLTM","schema_version":"1.0","canonical_sha256":"255be2ae6c8137947d59638fa1cc7dede0748fad796396cec879daf5ad84b2bd","source":{"kind":"arxiv","id":"2508.12459","version":1},"attestation_state":"computed","paper":{"title":"LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Trevor Cohn","submitted_at":"2025-08-17T18:07:57Z","abstract_excerpt":"As one of the world's most populous countries, with 700 languages spoken, Indonesia is behind in terms of NLP progress. We introduce LoraxBench, a benchmark that focuses on low-resource languages of Indonesia and covers 6 diverse tasks: reading comprehension, open-domain QA, language inference, causal reasoning, translation, and cultural QA. Our dataset covers 20 languages, with the addition of two formality registers for three languages. We evaluate a diverse set of multilingual and region-focused LLMs and found that this benchmark is challenging. We note a visible discrepancy between perform"},"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":"2508.12459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-17T18:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"600a8cd6290e2f590ad3a072b2d887e9b1c2fe0c2ce0a1bfbb92a7697fc056f1","abstract_canon_sha256":"b828be7aaf686eb96c536fa7d58897c50cbb8169a0fb86987bebd57947fa4c5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:06.062459Z","signature_b64":"CKdiCrFHFDggYXVutLMw2Af+R4QI3ga/iao8I2ehe06lNgVaJy+2KqtYeKLUopItTqMnFOswh/StIjYJzjntDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"255be2ae6c8137947d59638fa1cc7dede0748fad796396cec879daf5ad84b2bd","last_reissued_at":"2026-07-05T11:55:06.061983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:06.061983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Trevor Cohn","submitted_at":"2025-08-17T18:07:57Z","abstract_excerpt":"As one of the world's most populous countries, with 700 languages spoken, Indonesia is behind in terms of NLP progress. We introduce LoraxBench, a benchmark that focuses on low-resource languages of Indonesia and covers 6 diverse tasks: reading comprehension, open-domain QA, language inference, causal reasoning, translation, and cultural QA. Our dataset covers 20 languages, with the addition of two formality registers for three languages. We evaluate a diverse set of multilingual and region-focused LLMs and found that this benchmark is challenging. We note a visible discrepancy between perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12459","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/2508.12459/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":"2508.12459","created_at":"2026-07-05T11:55:06.062040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12459v1","created_at":"2026-07-05T11:55:06.062040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12459","created_at":"2026-07-05T11:55:06.062040+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVN6FLTMQE3Z","created_at":"2026-07-05T11:55:06.062040+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVN6FLTMQE3ZI7KZ","created_at":"2026-07-05T11:55:06.062040+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVN6FLTM","created_at":"2026-07-05T11:55:06.062040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28715","citing_title":"SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X","json":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X.json","graph_json":"https://pith.science/api/pith-number/EVN6FLTMQE3ZI7KZMOH2DTD55X/graph.json","events_json":"https://pith.science/api/pith-number/EVN6FLTMQE3ZI7KZMOH2DTD55X/events.json","paper":"https://pith.science/paper/EVN6FLTM"},"agent_actions":{"view_html":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X","download_json":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X.json","view_paper":"https://pith.science/paper/EVN6FLTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12459&json=true","fetch_graph":"https://pith.science/api/pith-number/EVN6FLTMQE3ZI7KZMOH2DTD55X/graph.json","fetch_events":"https://pith.science/api/pith-number/EVN6FLTMQE3ZI7KZMOH2DTD55X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X/action/storage_attestation","attest_author":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X/action/author_attestation","sign_citation":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X/action/citation_signature","submit_replication":"https://pith.science/pith/EVN6FLTMQE3ZI7KZMOH2DTD55X/action/replication_record"}},"created_at":"2026-07-05T11:55:06.062040+00:00","updated_at":"2026-07-05T11:55:06.062040+00:00"}