{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XFZ4G32LLFGZANO2DCZDCJWQ34","short_pith_number":"pith:XFZ4G32L","schema_version":"1.0","canonical_sha256":"b973c36f4b594d9035da18b23126d0df2ca04695f3ec7f8958c89b2c05a1f5c9","source":{"kind":"arxiv","id":"2310.12664","version":1},"attestation_state":"computed","paper":{"title":"Is ChatGPT a Financial Expert? Evaluating Language Models on Financial Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yi Yang, Yue Guo, Zian Xu","submitted_at":"2023-10-19T11:43:15Z","abstract_excerpt":"The emergence of Large Language Models (LLMs), such as ChatGPT, has revolutionized general natural language preprocessing (NLP) tasks. However, their expertise in the financial domain lacks a comprehensive evaluation. To assess the ability of LLMs to solve financial NLP tasks, we present FinLMEval, a framework for Financial Language Model Evaluation, comprising nine datasets designed to evaluate the performance of language models. This study compares the performance of encoder-only language models and the decoder-only language models. Our findings reveal that while some decoder-only LLMs demon"},"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":"2310.12664","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T11:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"1119a805ff7741b1bdf9d6b3b1a053280c0a050a8670217f0bc28de0db70bd1b","abstract_canon_sha256":"c8df1e619de3a41cab1f3808d2751a1443997009b4fd91ee149932731c549bd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:41.244381Z","signature_b64":"6y8NF3vurxBGkhuvp9kn4WMyCQWAcxf4PlsqC4lfOONRpWC+X8QYMwmyqaagnDxZo+kCagoRoLiVDHAaw2+WAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b973c36f4b594d9035da18b23126d0df2ca04695f3ec7f8958c89b2c05a1f5c9","last_reissued_at":"2026-07-05T07:02:41.244012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:41.244012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is ChatGPT a Financial Expert? Evaluating Language Models on Financial Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yi Yang, Yue Guo, Zian Xu","submitted_at":"2023-10-19T11:43:15Z","abstract_excerpt":"The emergence of Large Language Models (LLMs), such as ChatGPT, has revolutionized general natural language preprocessing (NLP) tasks. However, their expertise in the financial domain lacks a comprehensive evaluation. To assess the ability of LLMs to solve financial NLP tasks, we present FinLMEval, a framework for Financial Language Model Evaluation, comprising nine datasets designed to evaluate the performance of language models. This study compares the performance of encoder-only language models and the decoder-only language models. Our findings reveal that while some decoder-only LLMs demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12664","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/2310.12664/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":"2310.12664","created_at":"2026-07-05T07:02:41.244064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12664v1","created_at":"2026-07-05T07:02:41.244064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12664","created_at":"2026-07-05T07:02:41.244064+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFZ4G32LLFGZ","created_at":"2026-07-05T07:02:41.244064+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFZ4G32LLFGZANO2","created_at":"2026-07-05T07:02:41.244064+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFZ4G32L","created_at":"2026-07-05T07:02:41.244064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19887","citing_title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34","json":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34.json","graph_json":"https://pith.science/api/pith-number/XFZ4G32LLFGZANO2DCZDCJWQ34/graph.json","events_json":"https://pith.science/api/pith-number/XFZ4G32LLFGZANO2DCZDCJWQ34/events.json","paper":"https://pith.science/paper/XFZ4G32L"},"agent_actions":{"view_html":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34","download_json":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34.json","view_paper":"https://pith.science/paper/XFZ4G32L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12664&json=true","fetch_graph":"https://pith.science/api/pith-number/XFZ4G32LLFGZANO2DCZDCJWQ34/graph.json","fetch_events":"https://pith.science/api/pith-number/XFZ4G32LLFGZANO2DCZDCJWQ34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34/action/storage_attestation","attest_author":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34/action/author_attestation","sign_citation":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34/action/citation_signature","submit_replication":"https://pith.science/pith/XFZ4G32LLFGZANO2DCZDCJWQ34/action/replication_record"}},"created_at":"2026-07-05T07:02:41.244064+00:00","updated_at":"2026-07-05T07:02:41.244064+00:00"}