{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FSYRE3564UL6NSC7GPW4FFTB3G","short_pith_number":"pith:FSYRE356","schema_version":"1.0","canonical_sha256":"2cb1126fbee517e6c85f33edc29661d98882ae7b169b1a8d02653194c375b8a6","source":{"kind":"arxiv","id":"2306.05443","version":1},"attestation_state":"computed","paper":{"title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alejandro Lopez-Lira, Jimin Huang, Min Peng, Qianqian Xie, Weiguang Han, Xiao Zhang, Yanzhao Lai","submitted_at":"2023-06-08T14:20:29Z","abstract_excerpt":"Although large language models (LLMs) has shown great performance on natural language processing (NLP) in the financial domain, there are no publicly available financial tailtored LLMs, instruction tuning datasets, and evaluation benchmarks, which is critical for continually pushing forward the open-source development of financial artificial intelligence (AI). This paper introduces PIXIU, a comprehensive framework including the first financial LLM based on fine-tuning LLaMA with instruction data, the first instruction data with 136K data samples to support the fine-tuning, and an evaluation be"},"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":"2306.05443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T14:20:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f9a5556e63e5cdc12556cfe710bf2798af4dc2fb5709e91a0f0203fd80708fe9","abstract_canon_sha256":"a50df3a107fe86bfb71b6464d731d27ca5b9f41ec8676574233e10f0d70c289b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:06.225558Z","signature_b64":"sEB30srsId88ptGw434bQob4ONnOJG2GIQm1AxevKPGjC6ZOAmIuH823+j7E8xSy2eB4/JHaAtbrfW6P9lVuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb1126fbee517e6c85f33edc29661d98882ae7b169b1a8d02653194c375b8a6","last_reissued_at":"2026-07-05T06:19:06.225041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:06.225041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alejandro Lopez-Lira, Jimin Huang, Min Peng, Qianqian Xie, Weiguang Han, Xiao Zhang, Yanzhao Lai","submitted_at":"2023-06-08T14:20:29Z","abstract_excerpt":"Although large language models (LLMs) has shown great performance on natural language processing (NLP) in the financial domain, there are no publicly available financial tailtored LLMs, instruction tuning datasets, and evaluation benchmarks, which is critical for continually pushing forward the open-source development of financial artificial intelligence (AI). This paper introduces PIXIU, a comprehensive framework including the first financial LLM based on fine-tuning LLaMA with instruction data, the first instruction data with 136K data samples to support the fine-tuning, and an evaluation be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05443","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/2306.05443/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":"2306.05443","created_at":"2026-07-05T06:19:06.225104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05443v1","created_at":"2026-07-05T06:19:06.225104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05443","created_at":"2026-07-05T06:19:06.225104+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSYRE3564UL6","created_at":"2026-07-05T06:19:06.225104+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSYRE3564UL6NSC7","created_at":"2026-07-05T06:19:06.225104+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSYRE356","created_at":"2026-07-05T06:19:06.225104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26350","citing_title":"OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23370","citing_title":"FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11537","citing_title":"MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30997","citing_title":"A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31608","citing_title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25188","citing_title":"DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15482","citing_title":"FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17011","citing_title":"Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08886","citing_title":"FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15482","citing_title":"FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11512","citing_title":"From Time Series Analysis to Question Answering: A Survey in the LLM Era","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26100","citing_title":"AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09046","citing_title":"FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26747","citing_title":"From Hypotheses to Factors: Constrained LLM Agents in Cryptocurrency Markets","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09106","citing_title":"Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06024","citing_title":"Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19476","citing_title":"Cross-Stock Predictability via LLM-Augmented Semantic Networks","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18272","citing_title":"MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09285","citing_title":"SAGE: A Service Agent Graph-guided Evaluation Benchmark","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04812","citing_title":"SysTradeBench: An Iterative Build-Test-Patch Benchmark for Strategy-to-Code Trading Systems with Drift-Aware Diagnostics","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G","json":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G.json","graph_json":"https://pith.science/api/pith-number/FSYRE3564UL6NSC7GPW4FFTB3G/graph.json","events_json":"https://pith.science/api/pith-number/FSYRE3564UL6NSC7GPW4FFTB3G/events.json","paper":"https://pith.science/paper/FSYRE356"},"agent_actions":{"view_html":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G","download_json":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G.json","view_paper":"https://pith.science/paper/FSYRE356","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05443&json=true","fetch_graph":"https://pith.science/api/pith-number/FSYRE3564UL6NSC7GPW4FFTB3G/graph.json","fetch_events":"https://pith.science/api/pith-number/FSYRE3564UL6NSC7GPW4FFTB3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G/action/storage_attestation","attest_author":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G/action/author_attestation","sign_citation":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G/action/citation_signature","submit_replication":"https://pith.science/pith/FSYRE3564UL6NSC7GPW4FFTB3G/action/replication_record"}},"created_at":"2026-07-05T06:19:06.225104+00:00","updated_at":"2026-07-05T06:19:06.225104+00:00"}