{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WGLEXUDF5JOQ5VU7BMIOXBIM7J","short_pith_number":"pith:WGLEXUDF","schema_version":"1.0","canonical_sha256":"b1964bd065ea5d0ed69f0b10eb850cfa77d298c0bc51128e42239ac87d96a86a","source":{"kind":"arxiv","id":"1908.10063","version":1},"attestation_state":"computed","paper":{"title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FinBERT adapts a BERT model with financial text to improve sentiment classification on specialized datasets.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dogu Araci","submitted_at":"2019-08-27T07:40:48Z","abstract_excerpt":"Financial sentiment analysis is a challenging task due to the specialized language and lack of labeled data in that domain. General-purpose models are not effective enough because of the specialized language used in a financial context. We hypothesize that pre-trained language models can help with this problem because they require fewer labeled examples and they can be further trained on domain-specific corpora. We introduce FinBERT, a language model based on BERT, to tackle NLP tasks in the financial domain. Our results show improvement in every measured metric on current state-of-the-art res"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"1908.10063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T07:40:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be62609ed8ed73995cdefdc927ee6831878a944bee486866326962b1b1024631","abstract_canon_sha256":"3fc3db52cd3ffee1dac601fa5c82ba5996838d3b9bc1cb59fe6e32babc1eb2a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.274544Z","signature_b64":"o8PvWxUbXOmTUgGnBu6DdrQxMEkp/2IaNAMLfE0WoueEAaW8l5wZ3tGFdopL9qVirF3qx+ZeIhzwkLwoln9QAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1964bd065ea5d0ed69f0b10eb850cfa77d298c0bc51128e42239ac87d96a86a","last_reissued_at":"2026-05-17T23:38:50.273963Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.273963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FinBERT adapts a BERT model with financial text to improve sentiment classification on specialized datasets.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dogu Araci","submitted_at":"2019-08-27T07:40:48Z","abstract_excerpt":"Financial sentiment analysis is a challenging task due to the specialized language and lack of labeled data in that domain. General-purpose models are not effective enough because of the specialized language used in a financial context. We hypothesize that pre-trained language models can help with this problem because they require fewer labeled examples and they can be further trained on domain-specific corpora. We introduce FinBERT, a language model based on BERT, to tackle NLP tasks in the financial domain. Our results show improvement in every measured metric on current state-of-the-art res"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results show improvement in every measured metric on current state-of-the-art results for two financial sentiment analysis datasets. We find that even with a smaller training set and fine-tuning only a part of the model, FinBERT outperforms state-of-the-art machine learning methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That further pre-training on domain-specific financial corpora plus partial fine-tuning will reliably produce better sentiment classification than general-purpose models or traditional machine-learning baselines when labeled financial data is limited.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FinBERT adapts BERT to the financial domain and outperforms prior state-of-the-art methods on financial sentiment analysis tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FinBERT adapts a BERT model with financial text to improve sentiment classification on specialized datasets.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"499bedf3667912b6b9843da21f6663b2295ad14bb3a6c5c91de3ca38d596a765"},"source":{"id":"1908.10063","kind":"arxiv","version":1},"verdict":{"id":"55305194-ebfd-4011-8938-dd39477e3c7d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:22:30.685641Z","strongest_claim":"Our results show improvement in every measured metric on current state-of-the-art results for two financial sentiment analysis datasets. We find that even with a smaller training set and fine-tuning only a part of the model, FinBERT outperforms state-of-the-art machine learning methods.","one_line_summary":"FinBERT adapts BERT to the financial domain and outperforms prior state-of-the-art methods on financial sentiment analysis tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That further pre-training on domain-specific financial corpora plus partial fine-tuning will reliably produce better sentiment classification than general-purpose models or traditional machine-learning baselines when labeled financial data is limited.","pith_extraction_headline":"FinBERT adapts a BERT model with financial text to improve sentiment classification on specialized datasets."},"references":{"count":35,"sample":[{"doi":"10.1007/978-3-319-25343-5_3","year":2016,"title":"Basant Agarwal and Namita Mittal. 2016. Machine Learning Approach for Sentiment Analysis. Springer International Publishing, Cham, 21–45. https: //doi.org/10.1007/978-3-319-25343-5_3","work_id":"211e4061-c85e-45ea-9c00-5487ea1743c5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.eswa.2017.02.002","year":2017,"title":"Fernando Sánchez-Rada, and Carlos A","work_id":"2805d73d-a21e-431c-85a9-66ae1d3690b0","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Shallue and Jaehoon Lee and Joe Antognini and Jascha Sohl-Dickstein and Roy Frostig and George E","work_id":"3f2397b9-748a-4ee8-b371-99c0a4f13cdb","ref_index":3,"cited_arxiv_id":"1811.03600","is_internal_anchor":true},{"doi":"10.1016/j.jfds.2017.02.001","year":2016,"title":"Li Guo, Feng Shi, and Jun Tu. 2016. Textual analysis and machine leaning: Crack unstructured data in finance and accounting. The Journal of Finance and Data Science 2, 3 (sep 2016), 153–170. https://d","work_id":"9de23409-dd72-439a-8f28-769462db129f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Universal language model fine-tuning for text classification","work_id":"9990d84d-84b4-4fd4-acb5-da451524d2f4","ref_index":5,"cited_arxiv_id":"1801.06146","is_internal_anchor":true}],"resolved_work":35,"snapshot_sha256":"819ac636916b7226b2487cd63c250fc7f6c121e5e48040a7c6fec7fdc92c8f89","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dd4184825ff3e1bd012511be15e1a0de1d052c497b705b89d516dcee8701bc69"},"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":"1908.10063","created_at":"2026-05-17T23:38:50.274060+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10063v1","created_at":"2026-05-17T23:38:50.274060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10063","created_at":"2026-05-17T23:38:50.274060+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGLEXUDF5JOQ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGLEXUDF5JOQ5VU7","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGLEXUDF","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":26,"sample":[{"citing_arxiv_id":"2406.12009","citing_title":"FinTruthQA: A Benchmark for AI-Driven Financial Disclosure Quality Assessment in Investor -- Firm Interactions","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02429","citing_title":"MulFSA: Multi-level Financial Sentiment Analysis Framework for Bond Market","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17088","citing_title":"ACIL: Auto Chain of Thoughts for In-Context Learning","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19779","citing_title":"Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15413","citing_title":"Transformer Scalability Crisis: The First Comprehensive Empirical Analysis of Performance Walls in Modern Language Models","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13749","citing_title":"Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2603.20480","citing_title":"Developing an ESG-Oriented Large Language Model through ESG Practices","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2303.17564","citing_title":"BloombergGPT: A Large Language Model for Finance","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14199","citing_title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03888","citing_title":"PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11687","citing_title":"Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2310.04451","citing_title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24038","citing_title":"AgentPulse: A Continuous Multi-Signal Framework for Evaluating AI Agents in Deployment","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05409","citing_title":"Agentic Retrieval-Augmented Generation for Financial Document Question Answering","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04243","citing_title":"Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19299","citing_title":"Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12047","citing_title":"Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01384","citing_title":"SBCA: Cross-Modal BERT-driven Actor-Critic for Multi-Asset Portfolio Optimization","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05211","citing_title":"A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective","ref_index":20,"is_internal_anchor":true},{"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":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14619","citing_title":"The Acoustic Camouflage Phenomenon: Re-evaluating Speech Features for Financial Risk Prediction","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16862","citing_title":"Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03147","citing_title":"Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls","ref_index":79,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J","json":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J.json","graph_json":"https://pith.science/api/pith-number/WGLEXUDF5JOQ5VU7BMIOXBIM7J/graph.json","events_json":"https://pith.science/api/pith-number/WGLEXUDF5JOQ5VU7BMIOXBIM7J/events.json","paper":"https://pith.science/paper/WGLEXUDF"},"agent_actions":{"view_html":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J","download_json":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J.json","view_paper":"https://pith.science/paper/WGLEXUDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10063&json=true","fetch_graph":"https://pith.science/api/pith-number/WGLEXUDF5JOQ5VU7BMIOXBIM7J/graph.json","fetch_events":"https://pith.science/api/pith-number/WGLEXUDF5JOQ5VU7BMIOXBIM7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J/action/storage_attestation","attest_author":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J/action/author_attestation","sign_citation":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J/action/citation_signature","submit_replication":"https://pith.science/pith/WGLEXUDF5JOQ5VU7BMIOXBIM7J/action/replication_record"}},"created_at":"2026-05-17T23:38:50.274060+00:00","updated_at":"2026-05-17T23:38:50.274060+00:00"}