{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DMGG7DAHZF6CPM2NI6HXJZG5SV","short_pith_number":"pith:DMGG7DAH","schema_version":"1.0","canonical_sha256":"1b0c6f8c07c97c27b34d478f74e4dd9550ea2d75dc14d1e4066314f77a84116d","source":{"kind":"arxiv","id":"2310.08678","version":1},"attestation_state":"computed","paper":{"title":"Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-fin.GN"],"primary_cat":"cs.CL","authors_text":"Amarachi Mbakwe, Antony Papadimitriou, Ethan Callanan, Mathieu Sibue, Sameena Shah, Xiaodan Zhu, Xiaomo Liu, Yulong Pei, Zhiqiang Ma","submitted_at":"2023-10-12T19:28:57Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models. This study aims at assessing the financial reasoning capabilities of LLMs. We leverage mock exam questions of the Chartered Financial Analyst (CFA) Program to conduct a comprehensive evaluation of ChatGPT and GPT-4 in financial analysis, considering Zero-Shot (ZS), Chain-of-Thought (CoT), and Few-Shot (FS) scenarios. We present an in-depth analysis of the models' performance and limitations, and e"},"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":"2310.08678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T19:28:57Z","cross_cats_sorted":["cs.AI","q-fin.GN"],"title_canon_sha256":"7417ca140eab18ced41ec5ee557419f0c5254ae0f29649e1a693c77ac5e8f2cf","abstract_canon_sha256":"0512399059fde668304ac686e7b3b841b54e758761c8e0c71927d41dd986bac9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:33.209998Z","signature_b64":"NAHHLoSELvEY9zawjigP+ixmr0FwMiPgERUwH4dy9biBVmmhvHIEDMV34gf4bHCSbnPJM1VusacMiBJgFszZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b0c6f8c07c97c27b34d478f74e4dd9550ea2d75dc14d1e4066314f77a84116d","last_reissued_at":"2026-07-05T07:00:33.209551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:33.209551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-fin.GN"],"primary_cat":"cs.CL","authors_text":"Amarachi Mbakwe, Antony Papadimitriou, Ethan Callanan, Mathieu Sibue, Sameena Shah, Xiaodan Zhu, Xiaomo Liu, Yulong Pei, Zhiqiang Ma","submitted_at":"2023-10-12T19:28:57Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models. This study aims at assessing the financial reasoning capabilities of LLMs. We leverage mock exam questions of the Chartered Financial Analyst (CFA) Program to conduct a comprehensive evaluation of ChatGPT and GPT-4 in financial analysis, considering Zero-Shot (ZS), Chain-of-Thought (CoT), and Few-Shot (FS) scenarios. We present an in-depth analysis of the models' performance and limitations, and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08678","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/2310.08678/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":"2310.08678","created_at":"2026-07-05T07:00:33.209615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08678v1","created_at":"2026-07-05T07:00:33.209615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08678","created_at":"2026-07-05T07:00:33.209615+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMGG7DAHZF6C","created_at":"2026-07-05T07:00:33.209615+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMGG7DAHZF6CPM2N","created_at":"2026-07-05T07:00:33.209615+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMGG7DAH","created_at":"2026-07-05T07:00:33.209615+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/DMGG7DAHZF6CPM2NI6HXJZG5SV","json":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV.json","graph_json":"https://pith.science/api/pith-number/DMGG7DAHZF6CPM2NI6HXJZG5SV/graph.json","events_json":"https://pith.science/api/pith-number/DMGG7DAHZF6CPM2NI6HXJZG5SV/events.json","paper":"https://pith.science/paper/DMGG7DAH"},"agent_actions":{"view_html":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV","download_json":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV.json","view_paper":"https://pith.science/paper/DMGG7DAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08678&json=true","fetch_graph":"https://pith.science/api/pith-number/DMGG7DAHZF6CPM2NI6HXJZG5SV/graph.json","fetch_events":"https://pith.science/api/pith-number/DMGG7DAHZF6CPM2NI6HXJZG5SV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV/action/storage_attestation","attest_author":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV/action/author_attestation","sign_citation":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV/action/citation_signature","submit_replication":"https://pith.science/pith/DMGG7DAHZF6CPM2NI6HXJZG5SV/action/replication_record"}},"created_at":"2026-07-05T07:00:33.209615+00:00","updated_at":"2026-07-05T07:00:33.209615+00:00"}