{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:62H7HOIYQ66PWL6B3BMJJC3ECR","short_pith_number":"pith:62H7HOIY","schema_version":"1.0","canonical_sha256":"f68ff3b91887bcfb2fc1d858948b641445a318959985534c44b0d1b653c8b725","source":{"kind":"arxiv","id":"2411.02538","version":3},"attestation_state":"computed","paper":{"title":"MILU: A Multi-task Indic Language Understanding Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jaydeep Sen, Mohammed Safi Ur Rahman Khan, Rudra Murthy, Sshubam Verma, Vishwajeet Kumar","submitted_at":"2024-11-04T19:17:17Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) in low-resource and linguistically diverse languages remains a significant challenge in NLP, particularly for languages using non-Latin scripts like those spoken in India. Existing benchmarks predominantly focus on English, leaving substantial gaps in assessing LLM capabilities in these languages. We introduce MILU, a Multi task Indic Language Understanding Benchmark, a comprehensive evaluation benchmark designed to address this gap. MILU spans 8 domains and 41 subjects across 11 Indic languages, reflecting both general and culturally specific knowledge."},"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":"2411.02538","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T19:17:17Z","cross_cats_sorted":[],"title_canon_sha256":"99b53cdb2cc4dfcaa25d7e0c880015d537271ed7b47b2a3e55c8013da173ccd7","abstract_canon_sha256":"81fe3b1aff6a1f5b7d1c9ab42035f331a96f71e55c70bf7f2bf020d73312fb68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:11.630278Z","signature_b64":"apw1RgMS7KfoGh5F5UnRfpo9siKSES+pewvHq7HVEEqE+eTKMvReXSV7I4qGPaIZjTZta432V2GPzzsjOsdNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f68ff3b91887bcfb2fc1d858948b641445a318959985534c44b0d1b653c8b725","last_reissued_at":"2026-07-05T10:09:11.629863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:11.629863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MILU: A Multi-task Indic Language Understanding Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jaydeep Sen, Mohammed Safi Ur Rahman Khan, Rudra Murthy, Sshubam Verma, Vishwajeet Kumar","submitted_at":"2024-11-04T19:17:17Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) in low-resource and linguistically diverse languages remains a significant challenge in NLP, particularly for languages using non-Latin scripts like those spoken in India. Existing benchmarks predominantly focus on English, leaving substantial gaps in assessing LLM capabilities in these languages. We introduce MILU, a Multi task Indic Language Understanding Benchmark, a comprehensive evaluation benchmark designed to address this gap. MILU spans 8 domains and 41 subjects across 11 Indic languages, reflecting both general and culturally specific knowledge."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02538","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/2411.02538/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":"2411.02538","created_at":"2026-07-05T10:09:11.629919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02538v3","created_at":"2026-07-05T10:09:11.629919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02538","created_at":"2026-07-05T10:09:11.629919+00:00"},{"alias_kind":"pith_short_12","alias_value":"62H7HOIYQ66P","created_at":"2026-07-05T10:09:11.629919+00:00"},{"alias_kind":"pith_short_16","alias_value":"62H7HOIYQ66PWL6B","created_at":"2026-07-05T10:09:11.629919+00:00"},{"alias_kind":"pith_short_8","alias_value":"62H7HOIY","created_at":"2026-07-05T10:09:11.629919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24635","citing_title":"HiMed: Incentivizing Hindi Reasoning in Medical LLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11490","citing_title":"Anthropogenic Regional Adaptation in Multimodal Vision-Language Model","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR","json":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR.json","graph_json":"https://pith.science/api/pith-number/62H7HOIYQ66PWL6B3BMJJC3ECR/graph.json","events_json":"https://pith.science/api/pith-number/62H7HOIYQ66PWL6B3BMJJC3ECR/events.json","paper":"https://pith.science/paper/62H7HOIY"},"agent_actions":{"view_html":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR","download_json":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR.json","view_paper":"https://pith.science/paper/62H7HOIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02538&json=true","fetch_graph":"https://pith.science/api/pith-number/62H7HOIYQ66PWL6B3BMJJC3ECR/graph.json","fetch_events":"https://pith.science/api/pith-number/62H7HOIYQ66PWL6B3BMJJC3ECR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR/action/storage_attestation","attest_author":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR/action/author_attestation","sign_citation":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR/action/citation_signature","submit_replication":"https://pith.science/pith/62H7HOIYQ66PWL6B3BMJJC3ECR/action/replication_record"}},"created_at":"2026-07-05T10:09:11.629919+00:00","updated_at":"2026-07-05T10:09:11.629919+00:00"}