{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FH5I6RBZJDDI2NCW74WBQ7QT7T","short_pith_number":"pith:FH5I6RBZ","schema_version":"1.0","canonical_sha256":"29fa8f443948c68d3456ff2c187e13fcdbef13c88f7d8865786a35d699ba20cf","source":{"kind":"arxiv","id":"2101.01785","version":3},"attestation_state":"computed","paper":{"title":"ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, El Moatez Billah Nagoudi, Muhammad Abdul-Mageed","submitted_at":"2020-12-27T06:32:55Z","abstract_excerpt":"Pre-trained language models (LMs) are currently integral to many natural language processing systems. Although multilingual LMs were also introduced to serve many languages, these have limitations such as being costly at inference time and the size and diversity of non-English data involved in their pre-training. We remedy these issues for a collection of diverse Arabic varieties by introducing two powerful deep bidirectional transformer-based models, ARBERT and MARBERT. To evaluate our models, we also introduce ARLUE, a new benchmark for multi-dialectal Arabic language understanding evaluatio"},"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":"2101.01785","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-27T06:32:55Z","cross_cats_sorted":[],"title_canon_sha256":"99206b9aad999436450dda0e6c65141759915022181dd81d1ac8486416789f29","abstract_canon_sha256":"2137986801351386b8b5aafe66f264e200bb965f0d84246c41454c96369702dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:38.257961Z","signature_b64":"0JXH84JnloGaNhiI9YVU92D8riMwOSVzX03J1X7YTu5dR7Pw3SWaNVHK4O8gzi7sG+zfeoVJgRWjHQby+gaKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29fa8f443948c68d3456ff2c187e13fcdbef13c88f7d8865786a35d699ba20cf","last_reissued_at":"2026-07-05T02:51:38.257593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:38.257593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, El Moatez Billah Nagoudi, Muhammad Abdul-Mageed","submitted_at":"2020-12-27T06:32:55Z","abstract_excerpt":"Pre-trained language models (LMs) are currently integral to many natural language processing systems. Although multilingual LMs were also introduced to serve many languages, these have limitations such as being costly at inference time and the size and diversity of non-English data involved in their pre-training. We remedy these issues for a collection of diverse Arabic varieties by introducing two powerful deep bidirectional transformer-based models, ARBERT and MARBERT. To evaluate our models, we also introduce ARLUE, a new benchmark for multi-dialectal Arabic language understanding evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01785","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/2101.01785/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":"2101.01785","created_at":"2026-07-05T02:51:38.257655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.01785v3","created_at":"2026-07-05T02:51:38.257655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01785","created_at":"2026-07-05T02:51:38.257655+00:00"},{"alias_kind":"pith_short_12","alias_value":"FH5I6RBZJDDI","created_at":"2026-07-05T02:51:38.257655+00:00"},{"alias_kind":"pith_short_16","alias_value":"FH5I6RBZJDDI2NCW","created_at":"2026-07-05T02:51:38.257655+00:00"},{"alias_kind":"pith_short_8","alias_value":"FH5I6RBZ","created_at":"2026-07-05T02:51:38.257655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00457","citing_title":"CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance Reasoning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T","json":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T.json","graph_json":"https://pith.science/api/pith-number/FH5I6RBZJDDI2NCW74WBQ7QT7T/graph.json","events_json":"https://pith.science/api/pith-number/FH5I6RBZJDDI2NCW74WBQ7QT7T/events.json","paper":"https://pith.science/paper/FH5I6RBZ"},"agent_actions":{"view_html":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T","download_json":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T.json","view_paper":"https://pith.science/paper/FH5I6RBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.01785&json=true","fetch_graph":"https://pith.science/api/pith-number/FH5I6RBZJDDI2NCW74WBQ7QT7T/graph.json","fetch_events":"https://pith.science/api/pith-number/FH5I6RBZJDDI2NCW74WBQ7QT7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T/action/storage_attestation","attest_author":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T/action/author_attestation","sign_citation":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T/action/citation_signature","submit_replication":"https://pith.science/pith/FH5I6RBZJDDI2NCW74WBQ7QT7T/action/replication_record"}},"created_at":"2026-07-05T02:51:38.257655+00:00","updated_at":"2026-07-05T02:51:38.257655+00:00"}