{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RZL2AYFJVJQIF25AJLFS7I4YIV","short_pith_number":"pith:RZL2AYFJ","schema_version":"1.0","canonical_sha256":"8e57a060a9aa6082eba04acb2fa398455b1f294688228d9671ea6ff3b56d0ca4","source":{"kind":"arxiv","id":"1903.10676","version":3},"attestation_state":"computed","paper":{"title":"SciBERT: A Pretrained Language Model for Scientific Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Iz Beltagy, Kyle Lo","submitted_at":"2019-03-26T05:11:46Z","abstract_excerpt":"Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et al., 2018) to address the lack of high-quality, large-scale labeled scientific data. SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks. We evaluate on a suite of tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains. We demonstrate s"},"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":"1903.10676","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T05:11:46Z","cross_cats_sorted":[],"title_canon_sha256":"7eb82fa0d870de51f73017b764dde7e6f921b4cd47928a4dd973bb56395e916a","abstract_canon_sha256":"3f38e7d3c9b8f211234c157a5069919d9e74d2e394d8845b1cf007a089071ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:55.820636Z","signature_b64":"r17QLEUpFMpWUTC4M3QKipB6A6fTbWiMnT47rlVp0TjLYggTGfncPW4xEnOEj/33r58mg5t5DOPStPf1MtS/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e57a060a9aa6082eba04acb2fa398455b1f294688228d9671ea6ff3b56d0ca4","last_reissued_at":"2026-07-05T00:03:55.820214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:55.820214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciBERT: A Pretrained Language Model for Scientific Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Iz Beltagy, Kyle Lo","submitted_at":"2019-03-26T05:11:46Z","abstract_excerpt":"Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et al., 2018) to address the lack of high-quality, large-scale labeled scientific data. SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks. We evaluate on a suite of tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains. We demonstrate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10676","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/1903.10676/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":"1903.10676","created_at":"2026-07-05T00:03:55.820269+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10676v3","created_at":"2026-07-05T00:03:55.820269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10676","created_at":"2026-07-05T00:03:55.820269+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZL2AYFJVJQI","created_at":"2026-07-05T00:03:55.820269+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZL2AYFJVJQIF25A","created_at":"2026-07-05T00:03:55.820269+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZL2AYFJ","created_at":"2026-07-05T00:03:55.820269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19345","citing_title":"Ensembles of Large Language Models for Identifying EQ-5D Studies in PubMed Based on Their Abstracts","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21908","citing_title":"Gender Differences in Research Topic and Method Convergence among Collaborating Scholars in Library and Information Science","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20553","citing_title":"From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08497","citing_title":"Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31058","citing_title":"Exploring the relationship between team institutional composition and novelty in academic papers based on fine-grained knowledge entities","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30247","citing_title":"OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13452","citing_title":"Examining the Cognitive Gap Between Authors and Peer Reviewers on Academic Paper Novelty","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2302.12039","citing_title":"Natural Language Processing in the Legal Domain","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.19363","citing_title":"Large Language Models for Market Research: A Data-augmentation Approach","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2507.03674","citing_title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10895","citing_title":"Teaching Robots to Interpret Social Interactions through Lexically-guided Dynamic Graph Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17762","citing_title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18752","citing_title":"Traditional statistical representations outperform generative AI in identifying expert peer reviewers","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20374","citing_title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00264","citing_title":"S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06208","citing_title":"Extracting Breast Cancer Phenotypes from Clinical Notes: Comparing LLMs with Classical Ontology Methods","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03861","citing_title":"Aspect-Aware Content-Based Recommendations for Mathematical Research Papers","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23820","citing_title":"The software space of science","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10895","citing_title":"Teaching Robots to Interpret Social Interactions through Lexically-guided Dynamic Graph Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17680","citing_title":"MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17393","citing_title":"Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV","json":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV.json","graph_json":"https://pith.science/api/pith-number/RZL2AYFJVJQIF25AJLFS7I4YIV/graph.json","events_json":"https://pith.science/api/pith-number/RZL2AYFJVJQIF25AJLFS7I4YIV/events.json","paper":"https://pith.science/paper/RZL2AYFJ"},"agent_actions":{"view_html":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV","download_json":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV.json","view_paper":"https://pith.science/paper/RZL2AYFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10676&json=true","fetch_graph":"https://pith.science/api/pith-number/RZL2AYFJVJQIF25AJLFS7I4YIV/graph.json","fetch_events":"https://pith.science/api/pith-number/RZL2AYFJVJQIF25AJLFS7I4YIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/action/storage_attestation","attest_author":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/action/author_attestation","sign_citation":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/action/citation_signature","submit_replication":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/action/replication_record"}},"created_at":"2026-07-05T00:03:55.820269+00:00","updated_at":"2026-07-05T00:03:55.820269+00:00"}