{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2HLYRFBB7WHPB7JZS5XMPK6SOW","short_pith_number":"pith:2HLYRFBB","schema_version":"1.0","canonical_sha256":"d1d7889421fd8ef0fd39976ec7abd2758e92ee8f8f6e4152d58f92d8794f42a0","source":{"kind":"arxiv","id":"2109.06862","version":2},"attestation_state":"computed","paper":{"title":"Legal Transformer Models May Not Always Help","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karl Aberer, R\\'emi Lebret, Saibo Geng","submitted_at":"2021-09-14T17:53:55Z","abstract_excerpt":"Deep learning-based Natural Language Processing methods, especially transformers, have achieved impressive performance in the last few years. Applying those state-of-the-art NLP methods to legal activities to automate or simplify some simple work is of great value. This work investigates the value of domain adaptive pre-training and language adapters in legal NLP tasks. By comparing the performance of language models with domain adaptive pre-training on different tasks and different dataset splits, we show that domain adaptive pre-training is only helpful with low-resource downstream tasks, th"},"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":"2109.06862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-14T17:53:55Z","cross_cats_sorted":[],"title_canon_sha256":"27816886dc02321447bc133fc59650869086ad64f287da38797b915699152cab","abstract_canon_sha256":"49e3f3e4c3bf34ed4c458c8c0c2fbfe7451ecd7f8860f24cf06443e5f6e0ddb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:36.833066Z","signature_b64":"Ec8M8yo/MZ7m4CNWbvFA68ONpMIzMAsqbLBnLCvMqhNH7/4didVnKJKiqSIgMW+oF1F4OLMEmUNvK3bdMs/PBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1d7889421fd8ef0fd39976ec7abd2758e92ee8f8f6e4152d58f92d8794f42a0","last_reissued_at":"2026-07-05T03:14:36.832716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:36.832716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Legal Transformer Models May Not Always Help","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karl Aberer, R\\'emi Lebret, Saibo Geng","submitted_at":"2021-09-14T17:53:55Z","abstract_excerpt":"Deep learning-based Natural Language Processing methods, especially transformers, have achieved impressive performance in the last few years. Applying those state-of-the-art NLP methods to legal activities to automate or simplify some simple work is of great value. This work investigates the value of domain adaptive pre-training and language adapters in legal NLP tasks. By comparing the performance of language models with domain adaptive pre-training on different tasks and different dataset splits, we show that domain adaptive pre-training is only helpful with low-resource downstream tasks, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06862","kind":"arxiv","version":2},"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/2109.06862/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":"2109.06862","created_at":"2026-07-05T03:14:36.832772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06862v2","created_at":"2026-07-05T03:14:36.832772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06862","created_at":"2026-07-05T03:14:36.832772+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HLYRFBB7WHP","created_at":"2026-07-05T03:14:36.832772+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HLYRFBB7WHPB7JZ","created_at":"2026-07-05T03:14:36.832772+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HLYRFBB","created_at":"2026-07-05T03:14:36.832772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09768","citing_title":"Can Large Language Models Predict the Outcome of Judicial Decisions?","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW","json":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW.json","graph_json":"https://pith.science/api/pith-number/2HLYRFBB7WHPB7JZS5XMPK6SOW/graph.json","events_json":"https://pith.science/api/pith-number/2HLYRFBB7WHPB7JZS5XMPK6SOW/events.json","paper":"https://pith.science/paper/2HLYRFBB"},"agent_actions":{"view_html":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW","download_json":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW.json","view_paper":"https://pith.science/paper/2HLYRFBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06862&json=true","fetch_graph":"https://pith.science/api/pith-number/2HLYRFBB7WHPB7JZS5XMPK6SOW/graph.json","fetch_events":"https://pith.science/api/pith-number/2HLYRFBB7WHPB7JZS5XMPK6SOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW/action/storage_attestation","attest_author":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW/action/author_attestation","sign_citation":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW/action/citation_signature","submit_replication":"https://pith.science/pith/2HLYRFBB7WHPB7JZS5XMPK6SOW/action/replication_record"}},"created_at":"2026-07-05T03:14:36.832772+00:00","updated_at":"2026-07-05T03:14:36.832772+00:00"}