{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LPP2JO636HTORCD5DSF6IO3KCE","short_pith_number":"pith:LPP2JO63","schema_version":"1.0","canonical_sha256":"5bdfa4bbdbf1e6e8887d1c8be43b6a110a3c2e82f0bdac810b599a5286b5a671","source":{"kind":"arxiv","id":"2312.15006","version":2},"attestation_state":"computed","paper":{"title":"Assessing the Impact of Prompting Methods on ChatGPT's Mathematical Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Amisha Prasad, Benthan Vu, Chloe Wong, Eric Phuong, Hanwen Yang, James Davis, Juan Aguenza, Manny Fluss, Minghao Liu, Raja Kumar, Sai Bhujangari, Vanshika Vats, Xun Lei, Yuhao Chen","submitted_at":"2023-12-22T17:39:40Z","abstract_excerpt":"This study critically evaluates the efficacy of prompting methods in enhancing the mathematical reasoning capability of large language models (LLMs). The investigation uses three prescriptive prompting methods - simple, persona, and conversational prompting - known for their effectiveness in enhancing the linguistic tasks of LLMs. We conduct this analysis on OpenAI's LLM chatbot, ChatGPT-3.5, on extensive problem sets from the MATH, GSM8K, and MMLU datasets, encompassing a broad spectrum of mathematical challenges. A grading script adapted to each dataset is used to determine the effectiveness"},"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":"2312.15006","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-22T17:39:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5be9d108fb0b72a5695d49d70e869322220d01e0bd7d9f9eeb9f9afa1c2158bf","abstract_canon_sha256":"bc39a9bfd19d94cacdd47ccaf2e318ba24f278309869cf15c242db46ec4604f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:07.534649Z","signature_b64":"78Fi2eGGbjlMCT8+DzJegkkgZ2miIdzmV0hj96oQwWnq2lp6B2YvO5NBpaCHAu+LUa2iwMHUdL8bVZ0LYYT8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bdfa4bbdbf1e6e8887d1c8be43b6a110a3c2e82f0bdac810b599a5286b5a671","last_reissued_at":"2026-07-05T07:47:07.534162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:07.534162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Impact of Prompting Methods on ChatGPT's Mathematical Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Amisha Prasad, Benthan Vu, Chloe Wong, Eric Phuong, Hanwen Yang, James Davis, Juan Aguenza, Manny Fluss, Minghao Liu, Raja Kumar, Sai Bhujangari, Vanshika Vats, Xun Lei, Yuhao Chen","submitted_at":"2023-12-22T17:39:40Z","abstract_excerpt":"This study critically evaluates the efficacy of prompting methods in enhancing the mathematical reasoning capability of large language models (LLMs). The investigation uses three prescriptive prompting methods - simple, persona, and conversational prompting - known for their effectiveness in enhancing the linguistic tasks of LLMs. We conduct this analysis on OpenAI's LLM chatbot, ChatGPT-3.5, on extensive problem sets from the MATH, GSM8K, and MMLU datasets, encompassing a broad spectrum of mathematical challenges. A grading script adapted to each dataset is used to determine the effectiveness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15006","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/2312.15006/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":"2312.15006","created_at":"2026-07-05T07:47:07.534238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15006v2","created_at":"2026-07-05T07:47:07.534238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15006","created_at":"2026-07-05T07:47:07.534238+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPP2JO636HTO","created_at":"2026-07-05T07:47:07.534238+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPP2JO636HTORCD5","created_at":"2026-07-05T07:47:07.534238+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPP2JO63","created_at":"2026-07-05T07:47:07.534238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE","json":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE.json","graph_json":"https://pith.science/api/pith-number/LPP2JO636HTORCD5DSF6IO3KCE/graph.json","events_json":"https://pith.science/api/pith-number/LPP2JO636HTORCD5DSF6IO3KCE/events.json","paper":"https://pith.science/paper/LPP2JO63"},"agent_actions":{"view_html":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE","download_json":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE.json","view_paper":"https://pith.science/paper/LPP2JO63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15006&json=true","fetch_graph":"https://pith.science/api/pith-number/LPP2JO636HTORCD5DSF6IO3KCE/graph.json","fetch_events":"https://pith.science/api/pith-number/LPP2JO636HTORCD5DSF6IO3KCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE/action/storage_attestation","attest_author":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE/action/author_attestation","sign_citation":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE/action/citation_signature","submit_replication":"https://pith.science/pith/LPP2JO636HTORCD5DSF6IO3KCE/action/replication_record"}},"created_at":"2026-07-05T07:47:07.534238+00:00","updated_at":"2026-07-05T07:47:07.534238+00:00"}