{"paper":{"arxiv_id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","abstract":"We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.","primary_category":"cs.CL","venue":"NAACL 2019","published_at":null,"latest_version":1,"withdrawn":false},"latest_version":{"id":"6b6e582d-d5d0-4583-bfd8-a0046b079685","version":1,"source_url":"https://arxiv.org/abs/1810.04805","rendered_html_url":null,"rendering_engine":null},"verdict":{"id":"df87b6ce-701b-4fd1-be28-eae71c2ff904","kind":"POST","status":"reproduced","score":0.9466666666666667,"confidence":0.8,"agent_version":"v0.1.0-bert-sst2-3slice100","computed_at":"2026-05-15T19:19:14.387Z","is_current":true,"claim_citation":{"paper_arxiv_id":"1810.04805","section":"Table 6","row":"BERT-BASE","column":"SST-2","reported_value":93.5,"reported_metric":"accuracy","quoted_text":"BERT BASE 84.6 88.9 92.7 89.3 71.2 93.5","pdf_page":6,"notes":"SST-2 column from the GLUE test-server result table; row reads BERT-BASE across 8 GLUE tasks. The checkpoint we evaluate (textattack/bert-base-uncased-SST-2) is the same model class."},"protocol_match":"exact"},"verdicts":{"post":{"id":"df87b6ce-701b-4fd1-be28-eae71c2ff904","kind":"POST","status":"reproduced","score":0.9466666666666667,"confidence":0.8,"agent_version":"v0.1.0-bert-sst2-3slice100","computed_at":"2026-05-15T19:19:14.387Z","is_current":true,"claim_citation":{"paper_arxiv_id":"1810.04805","section":"Table 6","row":"BERT-BASE","column":"SST-2","reported_value":93.5,"reported_metric":"accuracy","quoted_text":"BERT BASE 84.6 88.9 92.7 89.3 71.2 93.5","pdf_page":6,"notes":"SST-2 column from the GLUE test-server result table; row reads BERT-BASE across 8 GLUE tasks. The checkpoint we evaluate (textattack/bert-base-uncased-SST-2) is the same model class."},"protocol_match":"exact"},"pre":{"id":"0bb60ea6-27ca-4a61-8366-66311d4f53c9","kind":"PRE","status":"pending","score":0.4134,"confidence":0.5,"agent_version":"pre-heuristic-v0.1+no-llm","computed_at":"2026-05-06T17:20:48.630Z","is_current":true,"claim_citation":null,"protocol_match":null}}}