{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MIGRC5EJGSSK3J2GVHO23JV7GG","short_pith_number":"pith:MIGRC5EJ","schema_version":"1.0","canonical_sha256":"620d11748934a4ada746a9ddada6bf31b8cd64f20490cb675b2780cc5e958915","source":{"kind":"arxiv","id":"2110.01485","version":2},"attestation_state":"computed","paper":{"title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Restrepo Amariles, Hadi Abdine, Michalis Vazirgiannis, Rajaa El Hamdani, Stella Douka","submitted_at":"2021-10-04T14:51:24Z","abstract_excerpt":"Language models have proven to be very useful when adapted to specific domains. Nonetheless, little research has been done on the adaptation of domain-specific BERT models in the French language. In this paper, we focus on creating a language model adapted to French legal text with the goal of helping law professionals. We conclude that some specific tasks do not benefit from generic language models pre-trained on large amounts of data. We explore the use of smaller architectures in domain-specific sub-languages and their benefits for French legal text. We prove that domain-specific pre-traine"},"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":"2110.01485","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-04T14:51:24Z","cross_cats_sorted":[],"title_canon_sha256":"5742fe14056073a925fa57247924d9a7311c4c544b9c67e0d567bd9c73d14d26","abstract_canon_sha256":"7cb4a3dc50253989ebda366a9d44b08d697723f4620df8a5a9c892137ac46452"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:16.380713Z","signature_b64":"AJfj6C0Mz0WYydVYIDPttTQ1mu/pbQPQFxue9RlNj35mzdjuHRQoMaBqkAqQ6+sxfwg9Q61stHqKvWZeuw0uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"620d11748934a4ada746a9ddada6bf31b8cd64f20490cb675b2780cc5e958915","last_reissued_at":"2026-07-05T03:56:16.380225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:16.380225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Restrepo Amariles, Hadi Abdine, Michalis Vazirgiannis, Rajaa El Hamdani, Stella Douka","submitted_at":"2021-10-04T14:51:24Z","abstract_excerpt":"Language models have proven to be very useful when adapted to specific domains. Nonetheless, little research has been done on the adaptation of domain-specific BERT models in the French language. In this paper, we focus on creating a language model adapted to French legal text with the goal of helping law professionals. We conclude that some specific tasks do not benefit from generic language models pre-trained on large amounts of data. We explore the use of smaller architectures in domain-specific sub-languages and their benefits for French legal text. We prove that domain-specific pre-traine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01485","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/2110.01485/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":"2110.01485","created_at":"2026-07-05T03:56:16.380281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.01485v2","created_at":"2026-07-05T03:56:16.380281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01485","created_at":"2026-07-05T03:56:16.380281+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIGRC5EJGSSK","created_at":"2026-07-05T03:56:16.380281+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIGRC5EJGSSK3J2G","created_at":"2026-07-05T03:56:16.380281+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIGRC5EJ","created_at":"2026-07-05T03:56:16.380281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG","json":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG.json","graph_json":"https://pith.science/api/pith-number/MIGRC5EJGSSK3J2GVHO23JV7GG/graph.json","events_json":"https://pith.science/api/pith-number/MIGRC5EJGSSK3J2GVHO23JV7GG/events.json","paper":"https://pith.science/paper/MIGRC5EJ"},"agent_actions":{"view_html":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG","download_json":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG.json","view_paper":"https://pith.science/paper/MIGRC5EJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.01485&json=true","fetch_graph":"https://pith.science/api/pith-number/MIGRC5EJGSSK3J2GVHO23JV7GG/graph.json","fetch_events":"https://pith.science/api/pith-number/MIGRC5EJGSSK3J2GVHO23JV7GG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG/action/storage_attestation","attest_author":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG/action/author_attestation","sign_citation":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG/action/citation_signature","submit_replication":"https://pith.science/pith/MIGRC5EJGSSK3J2GVHO23JV7GG/action/replication_record"}},"created_at":"2026-07-05T03:56:16.380281+00:00","updated_at":"2026-07-05T03:56:16.380281+00:00"}