{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:L23H3QAY44KAMOFVH63OPZYMDU","short_pith_number":"pith:L23H3QAY","schema_version":"1.0","canonical_sha256":"5eb67dc018e7140638b53fb6e7e70c1d3929de040378c4d826224c74d228bd22","source":{"kind":"arxiv","id":"2010.02559","version":1},"attestation_state":"computed","paper":{"title":"LEGAL-BERT: The Muppets straight out of Law School","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis, Ion Androutsopoulos, Manos Fergadiotis, Nikolaos Aletras, Prodromos Malakasiotis","submitted_at":"2020-10-06T09:06:07Z","abstract_excerpt":"BERT has achieved impressive performance in several NLP tasks. However, there has been limited investigation on its adaptation guidelines in specialised domains. Here we focus on the legal domain, where we explore several approaches for applying BERT models to downstream legal tasks, evaluating on multiple datasets. Our findings indicate that the previous guidelines for pre-training and fine-tuning, often blindly followed, do not always generalize well in the legal domain. Thus we propose a systematic investigation of the available strategies when applying BERT in specialised domains. These ar"},"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":"2010.02559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T09:06:07Z","cross_cats_sorted":[],"title_canon_sha256":"626b65ff07d90b1ef0adf06d4e238b35957d7543d6ae9df0b8a3ab02df09e33f","abstract_canon_sha256":"742019242bca82624e69f659b81f725777df7750c684f5740de384e8e6fd147c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:51.370883Z","signature_b64":"JTV4UTUONuJd/+jQvoeOCoBHxqs94vKMG2IR5J2tbDUI+Xx6K1JsTaxDCtFIBRUpEQRt46ME2fqvBZ0VM5vHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eb67dc018e7140638b53fb6e7e70c1d3929de040378c4d826224c74d228bd22","last_reissued_at":"2026-07-05T01:40:51.370499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:51.370499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEGAL-BERT: The Muppets straight out of Law School","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis, Ion Androutsopoulos, Manos Fergadiotis, Nikolaos Aletras, Prodromos Malakasiotis","submitted_at":"2020-10-06T09:06:07Z","abstract_excerpt":"BERT has achieved impressive performance in several NLP tasks. However, there has been limited investigation on its adaptation guidelines in specialised domains. Here we focus on the legal domain, where we explore several approaches for applying BERT models to downstream legal tasks, evaluating on multiple datasets. Our findings indicate that the previous guidelines for pre-training and fine-tuning, often blindly followed, do not always generalize well in the legal domain. Thus we propose a systematic investigation of the available strategies when applying BERT in specialised domains. These ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02559","kind":"arxiv","version":1},"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/2010.02559/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":"2010.02559","created_at":"2026-07-05T01:40:51.370556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.02559v1","created_at":"2026-07-05T01:40:51.370556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02559","created_at":"2026-07-05T01:40:51.370556+00:00"},{"alias_kind":"pith_short_12","alias_value":"L23H3QAY44KA","created_at":"2026-07-05T01:40:51.370556+00:00"},{"alias_kind":"pith_short_16","alias_value":"L23H3QAY44KAMOFV","created_at":"2026-07-05T01:40:51.370556+00:00"},{"alias_kind":"pith_short_8","alias_value":"L23H3QAY","created_at":"2026-07-05T01:40:51.370556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20553","citing_title":"From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29511","citing_title":"DynaGraph: Lightweight Multi-Model Interaction Framework via Dynamic Topological Reconfiguration","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17691","citing_title":"Validate Your Authority: Benchmarking LLMs on Multi-Label Precedent Treatment Classification","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16767","citing_title":"Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06173","citing_title":"Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23585","citing_title":"ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19464","citing_title":"LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07028","citing_title":"Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16270","citing_title":"From Benchmarking to Reasoning: A Dual-Aspect, Large-Scale Evaluation of LLMs on Vietnamese Legal Text","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU","json":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU.json","graph_json":"https://pith.science/api/pith-number/L23H3QAY44KAMOFVH63OPZYMDU/graph.json","events_json":"https://pith.science/api/pith-number/L23H3QAY44KAMOFVH63OPZYMDU/events.json","paper":"https://pith.science/paper/L23H3QAY"},"agent_actions":{"view_html":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU","download_json":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU.json","view_paper":"https://pith.science/paper/L23H3QAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.02559&json=true","fetch_graph":"https://pith.science/api/pith-number/L23H3QAY44KAMOFVH63OPZYMDU/graph.json","fetch_events":"https://pith.science/api/pith-number/L23H3QAY44KAMOFVH63OPZYMDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU/action/storage_attestation","attest_author":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU/action/author_attestation","sign_citation":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU/action/citation_signature","submit_replication":"https://pith.science/pith/L23H3QAY44KAMOFVH63OPZYMDU/action/replication_record"}},"created_at":"2026-07-05T01:40:51.370556+00:00","updated_at":"2026-07-05T01:40:51.370556+00:00"}