{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AGEJ5FZ4ZXNVC4Q62L535HBQA5","short_pith_number":"pith:AGEJ5FZ4","schema_version":"1.0","canonical_sha256":"01889e973ccddb51721ed2fbbe9c300778c25ff00920ca304d413d64e335be25","source":{"kind":"arxiv","id":"2402.17231","version":3},"attestation_state":"computed","paper":{"title":"MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Kulkarni, Debopriyo Banerjee, Debrup Das, Somak Aditya","submitted_at":"2024-02-27T05:50:35Z","abstract_excerpt":"Tool-augmented Large Language Models (TALMs) are known to enhance the skillset of large language models (LLMs), thereby, leading to their improved reasoning abilities across many tasks. While, TALMs have been successfully employed in different question-answering benchmarks, their efficacy on complex mathematical reasoning benchmarks, and the potential complementary benefits offered by tools for knowledge retrieval and mathematical equation solving are open research questions. In this work, we present MathSensei, a tool-augmented large language model for mathematical reasoning. We study the com"},"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":"2402.17231","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T05:50:35Z","cross_cats_sorted":[],"title_canon_sha256":"2633164f39038017f9abd004a6e0eac73eb7395e070402d86ae68c3e9278e84b","abstract_canon_sha256":"ecf4f3f26dcc36a0c822530aa5ed82e4b5c9eec95bf42452786a707d2cf46aa5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:49.165150Z","signature_b64":"ex3ofk8EB4Htx5Uvz62UAdDBSiJcuxUeLUBBJ10vJ/yhCNp04UIwWMMaitWYZdQiagJPcCgGTRsDYh2dp4l9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01889e973ccddb51721ed2fbbe9c300778c25ff00920ca304d413d64e335be25","last_reissued_at":"2026-07-05T08:03:49.164662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:49.164662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Kulkarni, Debopriyo Banerjee, Debrup Das, Somak Aditya","submitted_at":"2024-02-27T05:50:35Z","abstract_excerpt":"Tool-augmented Large Language Models (TALMs) are known to enhance the skillset of large language models (LLMs), thereby, leading to their improved reasoning abilities across many tasks. While, TALMs have been successfully employed in different question-answering benchmarks, their efficacy on complex mathematical reasoning benchmarks, and the potential complementary benefits offered by tools for knowledge retrieval and mathematical equation solving are open research questions. In this work, we present MathSensei, a tool-augmented large language model for mathematical reasoning. We study the com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17231","kind":"arxiv","version":3},"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/2402.17231/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":"2402.17231","created_at":"2026-07-05T08:03:49.164723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17231v3","created_at":"2026-07-05T08:03:49.164723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17231","created_at":"2026-07-05T08:03:49.164723+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGEJ5FZ4ZXNV","created_at":"2026-07-05T08:03:49.164723+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGEJ5FZ4ZXNVC4Q6","created_at":"2026-07-05T08:03:49.164723+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGEJ5FZ4","created_at":"2026-07-05T08:03:49.164723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08212","citing_title":"LLMs with in-context learning for Algorithmic Theoretical Physics","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07536","citing_title":"TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5","json":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5.json","graph_json":"https://pith.science/api/pith-number/AGEJ5FZ4ZXNVC4Q62L535HBQA5/graph.json","events_json":"https://pith.science/api/pith-number/AGEJ5FZ4ZXNVC4Q62L535HBQA5/events.json","paper":"https://pith.science/paper/AGEJ5FZ4"},"agent_actions":{"view_html":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5","download_json":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5.json","view_paper":"https://pith.science/paper/AGEJ5FZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17231&json=true","fetch_graph":"https://pith.science/api/pith-number/AGEJ5FZ4ZXNVC4Q62L535HBQA5/graph.json","fetch_events":"https://pith.science/api/pith-number/AGEJ5FZ4ZXNVC4Q62L535HBQA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5/action/storage_attestation","attest_author":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5/action/author_attestation","sign_citation":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5/action/citation_signature","submit_replication":"https://pith.science/pith/AGEJ5FZ4ZXNVC4Q62L535HBQA5/action/replication_record"}},"created_at":"2026-07-05T08:03:49.164723+00:00","updated_at":"2026-07-05T08:03:49.164723+00:00"}