{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RUKMFS7MAUFTBSEGCQWWALE7T6","short_pith_number":"pith:RUKMFS7M","schema_version":"1.0","canonical_sha256":"8d14c2cbec050b30c886142d602c9f9f906f9236bc5b45fde68e16b6634dc9e1","source":{"kind":"arxiv","id":"2505.21354","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bidyarthi Paul, Faisal Muhammad Shah, Jalisha Jashim Era, Mirazur Rahman Zim, Tahmid Sattar Aothoi","submitted_at":"2025-05-27T15:47:10Z","abstract_excerpt":"Solving Bengali Math Word Problems (MWPs) remains a major challenge in natural language processing (NLP) due to the language's low-resource status and the multi-step reasoning required. Existing models struggle with complex Bengali MWPs, largely because no human-annotated Bengali dataset has previously addressed this task. This gap has limited progress in Bengali mathematical reasoning. To address this, we created SOMADHAN, a dataset of 8792 complex Bengali MWPs with manually written, step-by-step solutions. We designed this dataset to support reasoning-focused evaluation and model development"},"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":"2505.21354","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T15:47:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d4463118d32992f24d6ee42e20687c0e7c288042f788c6fcce7c8f98518c14d","abstract_canon_sha256":"58ac93ae2d76303686693a62f3d8e8d6f499636c8edf9437aa396e5fa7abef8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:36.145194Z","signature_b64":"478JE6Fr9PsW0BBFBhrmr84s7REjfxzERMG+oTQ5Ie0YU7AH7M2t7gZx7EYoD84kvQcZT5r4B3gl/AZbncO5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d14c2cbec050b30c886142d602c9f9f906f9236bc5b45fde68e16b6634dc9e1","last_reissued_at":"2026-07-05T11:45:36.144673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:36.144673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bidyarthi Paul, Faisal Muhammad Shah, Jalisha Jashim Era, Mirazur Rahman Zim, Tahmid Sattar Aothoi","submitted_at":"2025-05-27T15:47:10Z","abstract_excerpt":"Solving Bengali Math Word Problems (MWPs) remains a major challenge in natural language processing (NLP) due to the language's low-resource status and the multi-step reasoning required. Existing models struggle with complex Bengali MWPs, largely because no human-annotated Bengali dataset has previously addressed this task. This gap has limited progress in Bengali mathematical reasoning. To address this, we created SOMADHAN, a dataset of 8792 complex Bengali MWPs with manually written, step-by-step solutions. We designed this dataset to support reasoning-focused evaluation and model development"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21354","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/2505.21354/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":"2505.21354","created_at":"2026-07-05T11:45:36.144728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21354v2","created_at":"2026-07-05T11:45:36.144728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21354","created_at":"2026-07-05T11:45:36.144728+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUKMFS7MAUFT","created_at":"2026-07-05T11:45:36.144728+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUKMFS7MAUFTBSEG","created_at":"2026-07-05T11:45:36.144728+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUKMFS7M","created_at":"2026-07-05T11:45:36.144728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31483","citing_title":"BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31483","citing_title":"BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6","json":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6.json","graph_json":"https://pith.science/api/pith-number/RUKMFS7MAUFTBSEGCQWWALE7T6/graph.json","events_json":"https://pith.science/api/pith-number/RUKMFS7MAUFTBSEGCQWWALE7T6/events.json","paper":"https://pith.science/paper/RUKMFS7M"},"agent_actions":{"view_html":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6","download_json":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6.json","view_paper":"https://pith.science/paper/RUKMFS7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21354&json=true","fetch_graph":"https://pith.science/api/pith-number/RUKMFS7MAUFTBSEGCQWWALE7T6/graph.json","fetch_events":"https://pith.science/api/pith-number/RUKMFS7MAUFTBSEGCQWWALE7T6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6/action/storage_attestation","attest_author":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6/action/author_attestation","sign_citation":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6/action/citation_signature","submit_replication":"https://pith.science/pith/RUKMFS7MAUFTBSEGCQWWALE7T6/action/replication_record"}},"created_at":"2026-07-05T11:45:36.144728+00:00","updated_at":"2026-07-05T11:45:36.144728+00:00"}