{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WGLEXUDF5JOQ5VU7BMIOXBIM7J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3fc3db52cd3ffee1dac601fa5c82ba5996838d3b9bc1cb59fe6e32babc1eb2a0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T07:40:48Z","title_canon_sha256":"be62609ed8ed73995cdefdc927ee6831878a944bee486866326962b1b1024631"},"schema_version":"1.0","source":{"id":"1908.10063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.10063","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"1908.10063v1","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10063","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"WGLEXUDF5JOQ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WGLEXUDF5JOQ5VU7","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WGLEXUDF","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:44d46cf556508ac9fbb6091bc75ff0beb6c551763628b430667603fca843d1ef","target":"graph","created_at":"2026-05-17T23:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FinBERT adapts BERT to the financial domain and outperforms prior state-of-the-art methods on financial sentiment analysis tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FinBERT adapts a BERT model with financial text to improve sentiment classification on specialized datasets."}],"snapshot_sha256":"499bedf3667912b6b9843da21f6663b2295ad14bb3a6c5c91de3ca38d596a765"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dd4184825ff3e1bd012511be15e1a0de1d052c497b705b89d516dcee8701bc69"},"paper":{"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","authors_text":"Dogu Araci","cross_cats":["cs.LG"],"headline":"FinBERT adapts a BERT model with financial text to improve sentiment classification on specialized datasets.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T07:40:48Z","title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models"},"references":{"count":35,"internal_anchors":13,"resolved_work":35,"sample":[{"cited_arxiv_id":"","doi":"10.1007/978-3-319-25343-5_3","is_internal_anchor":false,"ref_index":1,"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","year":2016},{"cited_arxiv_id":"","doi":"10.1016/j.eswa.2017.02.002","is_internal_anchor":false,"ref_index":2,"title":"Fernando Sánchez-Rada, and Carlos A","work_id":"2805d73d-a21e-431c-85a9-66ae1d3690b0","year":2017},{"cited_arxiv_id":"1811.03600","doi":"","is_internal_anchor":true,"ref_index":3,"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","year":2018},{"cited_arxiv_id":"","doi":"10.1016/j.jfds.2017.02.001","is_internal_anchor":false,"ref_index":4,"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","year":2016},{"cited_arxiv_id":"1801.06146","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Universal language model fine-tuning for text classification","work_id":"9990d84d-84b4-4fd4-acb5-da451524d2f4","year":2018}],"snapshot_sha256":"819ac636916b7226b2487cd63c250fc7f6c121e5e48040a7c6fec7fdc92c8f89"},"source":{"id":"1908.10063","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T20:22:30.685641Z","id":"55305194-ebfd-4011-8938-dd39477e3c7d","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"FinBERT adapts a BERT model with financial text to improve sentiment classification on specialized datasets.","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.","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."}},"verdict_id":"55305194-ebfd-4011-8938-dd39477e3c7d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:baca70c809b69b7608cb66c3e29a4484352fc49c52556dcd63a201aeab6537e7","target":"record","created_at":"2026-05-17T23:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3fc3db52cd3ffee1dac601fa5c82ba5996838d3b9bc1cb59fe6e32babc1eb2a0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T07:40:48Z","title_canon_sha256":"be62609ed8ed73995cdefdc927ee6831878a944bee486866326962b1b1024631"},"schema_version":"1.0","source":{"id":"1908.10063","kind":"arxiv","version":1}},"canonical_sha256":"b1964bd065ea5d0ed69f0b10eb850cfa77d298c0bc51128e42239ac87d96a86a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1964bd065ea5d0ed69f0b10eb850cfa77d298c0bc51128e42239ac87d96a86a","first_computed_at":"2026-05-17T23:38:50.273963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.273963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o8PvWxUbXOmTUgGnBu6DdrQxMEkp/2IaNAMLfE0WoueEAaW8l5wZ3tGFdopL9qVirF3qx+ZeIhzwkLwoln9QAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.274544Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.10063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baca70c809b69b7608cb66c3e29a4484352fc49c52556dcd63a201aeab6537e7","sha256:44d46cf556508ac9fbb6091bc75ff0beb6c551763628b430667603fca843d1ef"],"state_sha256":"e24e6938b6e356979e8b86cb9327f549df624ba2904931c96f173d45d5267c45"}