{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5OWQQSW5M2ATFY46GI7LL6PVDM","short_pith_number":"pith:5OWQQSW5","schema_version":"1.0","canonical_sha256":"ebad084add668132e39e323eb5f9f51b144d8f70bbe7cbbe1d629f43063352fe","source":{"kind":"arxiv","id":"2411.05934","version":1},"attestation_state":"computed","paper":{"title":"Qwen2.5-32B: Leveraging Self-Consistent Tool-Integrated Reasoning for Bengali Mathematical Olympiad Problem Solving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Saad Tahmid, Sourav Sarker","submitted_at":"2024-11-08T19:44:12Z","abstract_excerpt":"We present an innovative approach for solving mathematical problems in Bengali, developed for the DL Sprint 3.0 BUET CSE Fest 2024 Competition. Our method uses advanced deep learning models, notably the Qwen 2.5 series, with improvements made through prompt engineering, model quantization, and Tool Integrated Reasoning (TIR) to handle complex calculations. Initially, we explored various model architectures, including fine-tuned Mistral and quantized Qwen models, refining them with translation techniques, Retrieval-Augmented Generation (RAG), and custom dataset curation. Manual hyperparameter t"},"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":"2411.05934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-08T19:44:12Z","cross_cats_sorted":[],"title_canon_sha256":"f664861215ba319d41a5729f285731466602f8aa8416a37e7da0c08aec97ac22","abstract_canon_sha256":"c9171a011971bdbf7f23c12aff355aca855ac2500b0f97f10474b17399eb8bfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:13.591814Z","signature_b64":"5wk1Rl1ADlMyitkl+WafH1zciDTwVGdx0mgXhgaM3833T/DOpZO8i4PHcVcoDvFoKBJsjseZDWInZno6jSvbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebad084add668132e39e323eb5f9f51b144d8f70bbe7cbbe1d629f43063352fe","last_reissued_at":"2026-07-05T09:33:13.591281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:13.591281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Qwen2.5-32B: Leveraging Self-Consistent Tool-Integrated Reasoning for Bengali Mathematical Olympiad Problem Solving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Saad Tahmid, Sourav Sarker","submitted_at":"2024-11-08T19:44:12Z","abstract_excerpt":"We present an innovative approach for solving mathematical problems in Bengali, developed for the DL Sprint 3.0 BUET CSE Fest 2024 Competition. Our method uses advanced deep learning models, notably the Qwen 2.5 series, with improvements made through prompt engineering, model quantization, and Tool Integrated Reasoning (TIR) to handle complex calculations. Initially, we explored various model architectures, including fine-tuned Mistral and quantized Qwen models, refining them with translation techniques, Retrieval-Augmented Generation (RAG), and custom dataset curation. Manual hyperparameter t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05934","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/2411.05934/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":"2411.05934","created_at":"2026-07-05T09:33:13.591343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05934v1","created_at":"2026-07-05T09:33:13.591343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05934","created_at":"2026-07-05T09:33:13.591343+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OWQQSW5M2AT","created_at":"2026-07-05T09:33:13.591343+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OWQQSW5M2ATFY46","created_at":"2026-07-05T09:33:13.591343+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OWQQSW5","created_at":"2026-07-05T09:33:13.591343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19500","citing_title":"NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM","json":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM.json","graph_json":"https://pith.science/api/pith-number/5OWQQSW5M2ATFY46GI7LL6PVDM/graph.json","events_json":"https://pith.science/api/pith-number/5OWQQSW5M2ATFY46GI7LL6PVDM/events.json","paper":"https://pith.science/paper/5OWQQSW5"},"agent_actions":{"view_html":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM","download_json":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM.json","view_paper":"https://pith.science/paper/5OWQQSW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05934&json=true","fetch_graph":"https://pith.science/api/pith-number/5OWQQSW5M2ATFY46GI7LL6PVDM/graph.json","fetch_events":"https://pith.science/api/pith-number/5OWQQSW5M2ATFY46GI7LL6PVDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM/action/storage_attestation","attest_author":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM/action/author_attestation","sign_citation":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM/action/citation_signature","submit_replication":"https://pith.science/pith/5OWQQSW5M2ATFY46GI7LL6PVDM/action/replication_record"}},"created_at":"2026-07-05T09:33:13.591343+00:00","updated_at":"2026-07-05T09:33:13.591343+00:00"}