{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ASKHVVKIXITGBQGA7SMLZTZOCE","short_pith_number":"pith:ASKHVVKI","schema_version":"1.0","canonical_sha256":"04947ad548ba2660c0c0fc98bccf2e1112a5f649c6425ad39cc4e1de8ff3c739","source":{"kind":"arxiv","id":"2408.09437","version":1},"attestation_state":"computed","paper":{"title":"Hindi-BEIR : A Large Scale Retrieval Benchmark in Hindi","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Arkadeep Acharya, Jaydeep Sen, Rudra Murthy, Vishwajeet Kumar","submitted_at":"2024-08-18T10:55:04Z","abstract_excerpt":"Given the large number of Hindi speakers worldwide, there is a pressing need for robust and efficient information retrieval systems for Hindi. Despite ongoing research, there is a lack of comprehensive benchmark for evaluating retrieval models in Hindi. To address this gap, we introduce the Hindi version of the BEIR benchmark, which includes a subset of English BEIR datasets translated to Hindi, existing Hindi retrieval datasets, and synthetically created datasets for retrieval. The benchmark is comprised of $15$ datasets spanning across $8$ distinct tasks. We evaluate state-of-the-art multili"},"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":"2408.09437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-18T10:55:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c55f98eb4c8887836bf6079e324af2bfbeb700af12c42aa61e13097294a4273b","abstract_canon_sha256":"3b1e0e1e749b5048bceaac5a65dbbb4b4081e3eb5b9b85ea4687fdd8c225a634"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:32.530969Z","signature_b64":"PD8K8E2EzwEwisiJP6RM05v20Am8/8dZnbyGO3yPjmTAc2/a+J/1xkJ21ZTMd83Q/aJGOZ2GMOJVHk5Vxh70Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04947ad548ba2660c0c0fc98bccf2e1112a5f649c6425ad39cc4e1de8ff3c739","last_reissued_at":"2026-07-05T08:56:32.530506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:32.530506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hindi-BEIR : A Large Scale Retrieval Benchmark in Hindi","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Arkadeep Acharya, Jaydeep Sen, Rudra Murthy, Vishwajeet Kumar","submitted_at":"2024-08-18T10:55:04Z","abstract_excerpt":"Given the large number of Hindi speakers worldwide, there is a pressing need for robust and efficient information retrieval systems for Hindi. Despite ongoing research, there is a lack of comprehensive benchmark for evaluating retrieval models in Hindi. To address this gap, we introduce the Hindi version of the BEIR benchmark, which includes a subset of English BEIR datasets translated to Hindi, existing Hindi retrieval datasets, and synthetically created datasets for retrieval. The benchmark is comprised of $15$ datasets spanning across $8$ distinct tasks. We evaluate state-of-the-art multili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09437","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/2408.09437/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":"2408.09437","created_at":"2026-07-05T08:56:32.530580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09437v1","created_at":"2026-07-05T08:56:32.530580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09437","created_at":"2026-07-05T08:56:32.530580+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASKHVVKIXITG","created_at":"2026-07-05T08:56:32.530580+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASKHVVKIXITGBQGA","created_at":"2026-07-05T08:56:32.530580+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASKHVVKI","created_at":"2026-07-05T08:56:32.530580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12879","citing_title":"Building Russian Benchmark for Evaluation of Information Retrieval Models","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE","json":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE.json","graph_json":"https://pith.science/api/pith-number/ASKHVVKIXITGBQGA7SMLZTZOCE/graph.json","events_json":"https://pith.science/api/pith-number/ASKHVVKIXITGBQGA7SMLZTZOCE/events.json","paper":"https://pith.science/paper/ASKHVVKI"},"agent_actions":{"view_html":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE","download_json":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE.json","view_paper":"https://pith.science/paper/ASKHVVKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09437&json=true","fetch_graph":"https://pith.science/api/pith-number/ASKHVVKIXITGBQGA7SMLZTZOCE/graph.json","fetch_events":"https://pith.science/api/pith-number/ASKHVVKIXITGBQGA7SMLZTZOCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE/action/storage_attestation","attest_author":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE/action/author_attestation","sign_citation":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE/action/citation_signature","submit_replication":"https://pith.science/pith/ASKHVVKIXITGBQGA7SMLZTZOCE/action/replication_record"}},"created_at":"2026-07-05T08:56:32.530580+00:00","updated_at":"2026-07-05T08:56:32.530580+00:00"}