{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VN6PAQ3RU7KXCSZCOFPUP3GINQ","short_pith_number":"pith:VN6PAQ3R","schema_version":"1.0","canonical_sha256":"ab7cf04371a7d5714b22715f47ecc86c235d774d0d2abf978648c154eed196f8","source":{"kind":"arxiv","id":"1905.05583","version":3},"attestation_state":"computed","paper":{"title":"How to Fine-Tune BERT for Text Classification?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Sun, Xipeng Qiu, Xuanjing Huang, Yige Xu","submitted_at":"2019-05-14T13:17:26Z","abstract_excerpt":"Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing results in many language understanding tasks. In this paper, we conduct exhaustive experiments to investigate different fine-tuning methods of BERT on text classification task and provide a general solution for BERT fine-tuning. Finally, the proposed solution obtains new state-of-the-art results on eight widely-studied text classification datasets."},"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":"1905.05583","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T13:17:26Z","cross_cats_sorted":[],"title_canon_sha256":"6981009aebcee7ebcae7b65b11088a78886de4e2df7b94791ae4709963e8753b","abstract_canon_sha256":"977e7effac9a15ee84323e18e7e911f333e3e189a14871b089d71da879ebb905"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:32.556890Z","signature_b64":"ypZ5M4YzQeu6m3my6wS67Wzr3zrB04rkHqFQxHLSN1uUc7pkPDsmRX7EyM/bRQ1yWOf0hDV1Q5eZ2kzYJ3wXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7cf04371a7d5714b22715f47ecc86c235d774d0d2abf978648c154eed196f8","last_reissued_at":"2026-07-05T00:38:32.556307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:32.556307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Fine-Tune BERT for Text Classification?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Sun, Xipeng Qiu, Xuanjing Huang, Yige Xu","submitted_at":"2019-05-14T13:17:26Z","abstract_excerpt":"Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing results in many language understanding tasks. In this paper, we conduct exhaustive experiments to investigate different fine-tuning methods of BERT on text classification task and provide a general solution for BERT fine-tuning. Finally, the proposed solution obtains new state-of-the-art results on eight widely-studied text classification datasets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05583","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/1905.05583/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":"1905.05583","created_at":"2026-07-05T00:38:32.556411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05583v3","created_at":"2026-07-05T00:38:32.556411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05583","created_at":"2026-07-05T00:38:32.556411+00:00"},{"alias_kind":"pith_short_12","alias_value":"VN6PAQ3RU7KX","created_at":"2026-07-05T00:38:32.556411+00:00"},{"alias_kind":"pith_short_16","alias_value":"VN6PAQ3RU7KXCSZC","created_at":"2026-07-05T00:38:32.556411+00:00"},{"alias_kind":"pith_short_8","alias_value":"VN6PAQ3R","created_at":"2026-07-05T00:38:32.556411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02100","citing_title":"PortBERT: Navigating the Depths of Portuguese Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"1907.05338","citing_title":"To Tune or Not To Tune? How About the Best of Both Worlds?","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2501.02407","citing_title":"Towards the Anonymization of the Language Modeling","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19559","citing_title":"Stay Focused: Problem Drift in Multi-Agent Debate","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09722","citing_title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16991","citing_title":"Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"1908.10063","citing_title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19754","citing_title":"Exploring Data Augmentation and Resampling Strategies for Transformer-Based Models to Address Class Imbalance in AI Scoring of Scientific Explanations in NGSS Classroom","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19559","citing_title":"Enhancing Construction Worker Safety in Extreme Heat: A Machine Learning Approach Utilizing Wearable Technology for Predictive Health Analytics","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ","json":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ.json","graph_json":"https://pith.science/api/pith-number/VN6PAQ3RU7KXCSZCOFPUP3GINQ/graph.json","events_json":"https://pith.science/api/pith-number/VN6PAQ3RU7KXCSZCOFPUP3GINQ/events.json","paper":"https://pith.science/paper/VN6PAQ3R"},"agent_actions":{"view_html":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ","download_json":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ.json","view_paper":"https://pith.science/paper/VN6PAQ3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05583&json=true","fetch_graph":"https://pith.science/api/pith-number/VN6PAQ3RU7KXCSZCOFPUP3GINQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VN6PAQ3RU7KXCSZCOFPUP3GINQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ/action/storage_attestation","attest_author":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ/action/author_attestation","sign_citation":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ/action/citation_signature","submit_replication":"https://pith.science/pith/VN6PAQ3RU7KXCSZCOFPUP3GINQ/action/replication_record"}},"created_at":"2026-07-05T00:38:32.556411+00:00","updated_at":"2026-07-05T00:38:32.556411+00:00"}