{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ICNHV7EEOOT6ZIUCEVPVDHR7Q5","short_pith_number":"pith:ICNHV7EE","schema_version":"1.0","canonical_sha256":"409a7afc8473a7eca282255f519e3f877eba1a81d0de37860c266642a7bbc385","source":{"kind":"arxiv","id":"2112.04329","version":3},"attestation_state":"computed","paper":{"title":"JABER and SABER: Junior and Senior Arabic BERt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Ghaddar, Ahmad Rashid, Baoxing Huai, Chao Xing, Duan Xinyu, Khalil Bibi, Mehdi Rezagholizadeh, Philippe Langlais, Qun Liu, Xin Jiang, Yasheng Wang, Yimeng Wu, Zhefeng Wang","submitted_at":"2021-12-08T15:19:24Z","abstract_excerpt":"Language-specific pre-trained models have proven to be more accurate than multilingual ones in a monolingual evaluation setting, Arabic is no exception. However, we found that previously released Arabic BERT models were significantly under-trained. In this technical report, we present JABER and SABER, Junior and Senior Arabic BERt respectively, our pre-trained language model prototypes dedicated for Arabic. We conduct an empirical study to systematically evaluate the performance of models across a diverse set of existing Arabic NLU tasks. Experimental results show that JABER and SABER achieve "},"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":"2112.04329","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-08T15:19:24Z","cross_cats_sorted":[],"title_canon_sha256":"17d41493d4338018af50346ee49073b1a9403ef8c8383ad0b4008d269d647efc","abstract_canon_sha256":"9721ab1acee23c9daff2202cb40ebb1b23fd74eb0cf4cfc5cb7f64ba2ee7ce99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:02.991629Z","signature_b64":"vVNJ/8v0r1IR1yXb0pmyl+GrhePrWf3iIijPn8SG6zjK95UWxqeaTp8MS8Al1ZY7F42tf1mXDytQz0RZs1kWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"409a7afc8473a7eca282255f519e3f877eba1a81d0de37860c266642a7bbc385","last_reissued_at":"2026-07-05T03:47:02.991065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:02.991065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JABER and SABER: Junior and Senior Arabic BERt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Ghaddar, Ahmad Rashid, Baoxing Huai, Chao Xing, Duan Xinyu, Khalil Bibi, Mehdi Rezagholizadeh, Philippe Langlais, Qun Liu, Xin Jiang, Yasheng Wang, Yimeng Wu, Zhefeng Wang","submitted_at":"2021-12-08T15:19:24Z","abstract_excerpt":"Language-specific pre-trained models have proven to be more accurate than multilingual ones in a monolingual evaluation setting, Arabic is no exception. However, we found that previously released Arabic BERT models were significantly under-trained. In this technical report, we present JABER and SABER, Junior and Senior Arabic BERt respectively, our pre-trained language model prototypes dedicated for Arabic. We conduct an empirical study to systematically evaluate the performance of models across a diverse set of existing Arabic NLU tasks. Experimental results show that JABER and SABER achieve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04329","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/2112.04329/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":"2112.04329","created_at":"2026-07-05T03:47:02.991135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04329v3","created_at":"2026-07-05T03:47:02.991135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04329","created_at":"2026-07-05T03:47:02.991135+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICNHV7EEOOT6","created_at":"2026-07-05T03:47:02.991135+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICNHV7EEOOT6ZIUC","created_at":"2026-07-05T03:47:02.991135+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICNHV7EE","created_at":"2026-07-05T03:47:02.991135+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/ICNHV7EEOOT6ZIUCEVPVDHR7Q5","json":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5.json","graph_json":"https://pith.science/api/pith-number/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/graph.json","events_json":"https://pith.science/api/pith-number/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/events.json","paper":"https://pith.science/paper/ICNHV7EE"},"agent_actions":{"view_html":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5","download_json":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5.json","view_paper":"https://pith.science/paper/ICNHV7EE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04329&json=true","fetch_graph":"https://pith.science/api/pith-number/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/graph.json","fetch_events":"https://pith.science/api/pith-number/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/action/storage_attestation","attest_author":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/action/author_attestation","sign_citation":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/action/citation_signature","submit_replication":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/action/replication_record"}},"created_at":"2026-07-05T03:47:02.991135+00:00","updated_at":"2026-07-05T03:47:02.991135+00:00"}