{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:25SWGN2VJSQ7V6HM5BLWIUCAPJ","short_pith_number":"pith:25SWGN2V","schema_version":"1.0","canonical_sha256":"d7656337554ca1faf8ece8576450407a4ce0d35d871b8c66c41e2b8d7583af1e","source":{"kind":"arxiv","id":"2404.19254","version":1},"attestation_state":"computed","paper":{"title":"Suvach -- Generated Hindi QA benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Prabin Raj KP, Saifudheen Nouphal, Vaishak Narayanan","submitted_at":"2024-04-30T04:19:17Z","abstract_excerpt":"Current evaluation benchmarks for question answering (QA) in Indic languages often rely on machine translation of existing English datasets. This approach suffers from bias and inaccuracies inherent in machine translation, leading to datasets that may not reflect the true capabilities of EQA models for Indic languages. This paper proposes a new benchmark specifically designed for evaluating Hindi EQA models and discusses the methodology to do the same for any task. This method leverages large language models (LLMs) to generate a high-quality dataset in an extractive setting, ensuring its relev"},"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":"2404.19254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-30T04:19:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ee123f9ae385ea4d008663f5d02fbcc50711dccbb742642920c0749313ffa013","abstract_canon_sha256":"32f1f8d759650be671554249cd98cd679713f6e6a5edf8e2adcfc24899c598ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:40.518344Z","signature_b64":"XBkENDTXj+j49W9WqWb/1ayEljq9qwoW9PhUf+rTJaxEbs7ucwC3U787xLWQCtr98UMRIopmr7dmdGR3Lkz1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7656337554ca1faf8ece8576450407a4ce0d35d871b8c66c41e2b8d7583af1e","last_reissued_at":"2026-07-05T08:13:40.517875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:40.517875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Suvach -- Generated Hindi QA benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Prabin Raj KP, Saifudheen Nouphal, Vaishak Narayanan","submitted_at":"2024-04-30T04:19:17Z","abstract_excerpt":"Current evaluation benchmarks for question answering (QA) in Indic languages often rely on machine translation of existing English datasets. This approach suffers from bias and inaccuracies inherent in machine translation, leading to datasets that may not reflect the true capabilities of EQA models for Indic languages. This paper proposes a new benchmark specifically designed for evaluating Hindi EQA models and discusses the methodology to do the same for any task. This method leverages large language models (LLMs) to generate a high-quality dataset in an extractive setting, ensuring its relev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19254","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/2404.19254/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":"2404.19254","created_at":"2026-07-05T08:13:40.517934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19254v1","created_at":"2026-07-05T08:13:40.517934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19254","created_at":"2026-07-05T08:13:40.517934+00:00"},{"alias_kind":"pith_short_12","alias_value":"25SWGN2VJSQ7","created_at":"2026-07-05T08:13:40.517934+00:00"},{"alias_kind":"pith_short_16","alias_value":"25SWGN2VJSQ7V6HM","created_at":"2026-07-05T08:13:40.517934+00:00"},{"alias_kind":"pith_short_8","alias_value":"25SWGN2V","created_at":"2026-07-05T08:13:40.517934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19699","citing_title":"Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ","json":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ.json","graph_json":"https://pith.science/api/pith-number/25SWGN2VJSQ7V6HM5BLWIUCAPJ/graph.json","events_json":"https://pith.science/api/pith-number/25SWGN2VJSQ7V6HM5BLWIUCAPJ/events.json","paper":"https://pith.science/paper/25SWGN2V"},"agent_actions":{"view_html":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ","download_json":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ.json","view_paper":"https://pith.science/paper/25SWGN2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19254&json=true","fetch_graph":"https://pith.science/api/pith-number/25SWGN2VJSQ7V6HM5BLWIUCAPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/25SWGN2VJSQ7V6HM5BLWIUCAPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ/action/storage_attestation","attest_author":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ/action/author_attestation","sign_citation":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ/action/citation_signature","submit_replication":"https://pith.science/pith/25SWGN2VJSQ7V6HM5BLWIUCAPJ/action/replication_record"}},"created_at":"2026-07-05T08:13:40.517934+00:00","updated_at":"2026-07-05T08:13:40.517934+00:00"}