{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GNRV6BSAFTOUP2D4J36A4UD5HN","short_pith_number":"pith:GNRV6BSA","schema_version":"1.0","canonical_sha256":"33635f06402cdd47e87c4efc0e507d3b7a0f83de0296789c813d2a2bac28792f","source":{"kind":"arxiv","id":"2309.13173","version":2},"attestation_state":"computed","paper":{"title":"BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Enamul Hoque, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, Mohammed Saidul Islam, Mohsinul Kabir, M Saiful Bari","submitted_at":"2023-09-22T20:29:34Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as one of the most important breakthroughs in NLP for their impressive skills in language generation and other language-specific tasks. Though LLMs have been evaluated in various tasks, mostly in English, they have not yet undergone thorough evaluation in under-resourced languages such as Bengali (Bangla). To this end, this paper introduces BenLLM-Eval, which consists of a comprehensive evaluation of LLMs to benchmark their performance in the Bengali language that has modest resources. In this regard, we select various important and diverse Bengali NLP"},"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":"2309.13173","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-22T20:29:34Z","cross_cats_sorted":[],"title_canon_sha256":"7f17b158ed1ae1d42e59605d25bdadb4dd4327e1e8dc57a540c176306c6e509c","abstract_canon_sha256":"993cbcf6d5141107763f3563fd777424b147e292b9d0295127c81f4f8a416272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:43.942724Z","signature_b64":"BCU9DdWIg9rDk+HSrYmAb8PnKi+MbXzLD3RjRjIBCJA7XmGMMsb/og+qqSI67frxrNeisAwVohT7vppoZ4FFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33635f06402cdd47e87c4efc0e507d3b7a0f83de0296789c813d2a2bac28792f","last_reissued_at":"2026-07-05T07:57:43.942238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:43.942238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Enamul Hoque, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, Mohammed Saidul Islam, Mohsinul Kabir, M Saiful Bari","submitted_at":"2023-09-22T20:29:34Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as one of the most important breakthroughs in NLP for their impressive skills in language generation and other language-specific tasks. Though LLMs have been evaluated in various tasks, mostly in English, they have not yet undergone thorough evaluation in under-resourced languages such as Bengali (Bangla). To this end, this paper introduces BenLLM-Eval, which consists of a comprehensive evaluation of LLMs to benchmark their performance in the Bengali language that has modest resources. In this regard, we select various important and diverse Bengali NLP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13173","kind":"arxiv","version":2},"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/2309.13173/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":"2309.13173","created_at":"2026-07-05T07:57:43.942298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13173v2","created_at":"2026-07-05T07:57:43.942298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13173","created_at":"2026-07-05T07:57:43.942298+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNRV6BSAFTOU","created_at":"2026-07-05T07:57:43.942298+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNRV6BSAFTOUP2D4","created_at":"2026-07-05T07:57:43.942298+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNRV6BSA","created_at":"2026-07-05T07:57:43.942298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19508","citing_title":"Bangla Key2Text: Text Generation from Keywords for a Low Resource Language","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN","json":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN.json","graph_json":"https://pith.science/api/pith-number/GNRV6BSAFTOUP2D4J36A4UD5HN/graph.json","events_json":"https://pith.science/api/pith-number/GNRV6BSAFTOUP2D4J36A4UD5HN/events.json","paper":"https://pith.science/paper/GNRV6BSA"},"agent_actions":{"view_html":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN","download_json":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN.json","view_paper":"https://pith.science/paper/GNRV6BSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13173&json=true","fetch_graph":"https://pith.science/api/pith-number/GNRV6BSAFTOUP2D4J36A4UD5HN/graph.json","fetch_events":"https://pith.science/api/pith-number/GNRV6BSAFTOUP2D4J36A4UD5HN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN/action/storage_attestation","attest_author":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN/action/author_attestation","sign_citation":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN/action/citation_signature","submit_replication":"https://pith.science/pith/GNRV6BSAFTOUP2D4J36A4UD5HN/action/replication_record"}},"created_at":"2026-07-05T07:57:43.942298+00:00","updated_at":"2026-07-05T07:57:43.942298+00:00"}