{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WWREUNIRSJBIIZPHCHUFHFPJTY","short_pith_number":"pith:WWREUNIR","schema_version":"1.0","canonical_sha256":"b5a24a351192428465e711e85395e99e0c144999de529fc945d1ce04c75800cd","source":{"kind":"arxiv","id":"2408.11878","version":3},"attestation_state":"computed","paper":{"title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CE","q-fin.CP"],"primary_cat":"cs.CL","authors_text":"Alejandro Lopez-Lira, Benyou Wang, Daniel Kim, Dong Li, Duanyu Feng, Guojun Xiong, Haohang Li, Honghai Yu, Jian-Yun Nie, Jimin Huang, Jordan W. Suchow, Junichi Tsujii, Kaleb E Smith, Lihang Shen, Lingfei Qian, Meikang Qiu, Mengxi Xiao, Min Peng, Peng Lu, Qianqian Xie, Ruey-Ling Weng, Ruoyu Xiang, Shunian Chen, Sophia Ananiadou, VijayaSai Somasundaram, Weiguang Han, Xiao-Yang Liu, Xiao Zhang, Xueqing Peng, Yang Ren, Yangyang Yu, Yan Wang, Yanzhao Lai, Yifei Zhang, Yongfu Dai, Yueru He, Yupeng Cao, Yuzhe Yang, Zheheng Luo, Zhengyu Chen, Zhiwei Liu, Zhiyang Deng, Zhiyuan Yao, Zihao Jiang","submitted_at":"2024-08-20T16:15:28Z","abstract_excerpt":"Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \\textit{Open-FinLLMs}, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data, excelling in zero-shot, few-shot, and fine-tuning settings. The suite includes FinLLaMA, pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tun"},"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":"2408.11878","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T16:15:28Z","cross_cats_sorted":["cs.CE","q-fin.CP"],"title_canon_sha256":"d1fc6c0fe96496a88bf552ac5b912954b26b8e8be333e4f1dc0390f8d1cc0eec","abstract_canon_sha256":"c1142ef13ebbe47925a1cdcb52f485e9c8e8b8bab243738c4c91218413d7ed6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:34.764477Z","signature_b64":"9Scg8EmiIK8i87xOwkCVCuM9p0ptVwYIum8nFDip1S5Z384i/xrXLxaacUpkCMtQrM6+S1t/K71D5TqeSO0CAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5a24a351192428465e711e85395e99e0c144999de529fc945d1ce04c75800cd","last_reissued_at":"2026-07-05T11:17:34.763996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:34.763996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CE","q-fin.CP"],"primary_cat":"cs.CL","authors_text":"Alejandro Lopez-Lira, Benyou Wang, Daniel Kim, Dong Li, Duanyu Feng, Guojun Xiong, Haohang Li, Honghai Yu, Jian-Yun Nie, Jimin Huang, Jordan W. Suchow, Junichi Tsujii, Kaleb E Smith, Lihang Shen, Lingfei Qian, Meikang Qiu, Mengxi Xiao, Min Peng, Peng Lu, Qianqian Xie, Ruey-Ling Weng, Ruoyu Xiang, Shunian Chen, Sophia Ananiadou, VijayaSai Somasundaram, Weiguang Han, Xiao-Yang Liu, Xiao Zhang, Xueqing Peng, Yang Ren, Yangyang Yu, Yan Wang, Yanzhao Lai, Yifei Zhang, Yongfu Dai, Yueru He, Yupeng Cao, Yuzhe Yang, Zheheng Luo, Zhengyu Chen, Zhiwei Liu, Zhiyang Deng, Zhiyuan Yao, Zihao Jiang","submitted_at":"2024-08-20T16:15:28Z","abstract_excerpt":"Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \\textit{Open-FinLLMs}, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data, excelling in zero-shot, few-shot, and fine-tuning settings. The suite includes FinLLaMA, pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11878","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/2408.11878/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":"2408.11878","created_at":"2026-07-05T11:17:34.764051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11878v3","created_at":"2026-07-05T11:17:34.764051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11878","created_at":"2026-07-05T11:17:34.764051+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWREUNIRSJBI","created_at":"2026-07-05T11:17:34.764051+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWREUNIRSJBIIZPH","created_at":"2026-07-05T11:17:34.764051+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWREUNIR","created_at":"2026-07-05T11:17:34.764051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17642","citing_title":"FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08285","citing_title":"Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14355","citing_title":"Herculean: An Agentic Benchmark for Financial Intelligence","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06440","citing_title":"Hyperbolic Concept Bottleneck Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06440","citing_title":"Hyperbolic Concept Bottleneck Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY","json":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY.json","graph_json":"https://pith.science/api/pith-number/WWREUNIRSJBIIZPHCHUFHFPJTY/graph.json","events_json":"https://pith.science/api/pith-number/WWREUNIRSJBIIZPHCHUFHFPJTY/events.json","paper":"https://pith.science/paper/WWREUNIR"},"agent_actions":{"view_html":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY","download_json":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY.json","view_paper":"https://pith.science/paper/WWREUNIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11878&json=true","fetch_graph":"https://pith.science/api/pith-number/WWREUNIRSJBIIZPHCHUFHFPJTY/graph.json","fetch_events":"https://pith.science/api/pith-number/WWREUNIRSJBIIZPHCHUFHFPJTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY/action/storage_attestation","attest_author":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY/action/author_attestation","sign_citation":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY/action/citation_signature","submit_replication":"https://pith.science/pith/WWREUNIRSJBIIZPHCHUFHFPJTY/action/replication_record"}},"created_at":"2026-07-05T11:17:34.764051+00:00","updated_at":"2026-07-05T11:17:34.764051+00:00"}