{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LE4R42VJXKANHCZ6BKG2GXGXNL","short_pith_number":"pith:LE4R42VJ","schema_version":"1.0","canonical_sha256":"59391e6aa9ba80d38b3e0a8da35cd76ad18eadb8fcb243082a748f4f9610e750","source":{"kind":"arxiv","id":"2103.06678","version":2},"attestation_state":"computed","paper":{"title":"The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bashar Alhafni, Go Inoue, Houda Bouamor, Nizar Habash, Nurpeiis Baimukan","submitted_at":"2021-03-11T14:11:43Z","abstract_excerpt":"In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: Modern Standard Arabic (MSA), dialectal Arabic, and classical Arabic, in addition to a fourth language model which is pre-trained on a mix of the three. We also examine the importance of pre-training data size by building additional models that are pre-trained on a scaled-down set of the MSA variant. We compare our different models to each other, as well as to eight publicl"},"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":"2103.06678","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T14:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"523cbf2b380bd8e95b16b6430d74f1f4c250c406d6377300a0da8ba3c2b82af8","abstract_canon_sha256":"81ef035897b2db7cfdddcf4b3e2580fc29be7d515ccc55be0ea7c692d812368c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:28.403037Z","signature_b64":"9p1vLm0RJaa65w/I4IyACHzePBbzMkXM6kUgHx3+QtIrLdQENF5HQ22s/KlR5acxhLrmpDdT/S0lLw8/Z0JkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59391e6aa9ba80d38b3e0a8da35cd76ad18eadb8fcb243082a748f4f9610e750","last_reissued_at":"2026-07-05T03:11:28.402676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:28.402676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bashar Alhafni, Go Inoue, Houda Bouamor, Nizar Habash, Nurpeiis Baimukan","submitted_at":"2021-03-11T14:11:43Z","abstract_excerpt":"In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: Modern Standard Arabic (MSA), dialectal Arabic, and classical Arabic, in addition to a fourth language model which is pre-trained on a mix of the three. We also examine the importance of pre-training data size by building additional models that are pre-trained on a scaled-down set of the MSA variant. We compare our different models to each other, as well as to eight publicl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06678","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/2103.06678/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":"2103.06678","created_at":"2026-07-05T03:11:28.402742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.06678v2","created_at":"2026-07-05T03:11:28.402742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06678","created_at":"2026-07-05T03:11:28.402742+00:00"},{"alias_kind":"pith_short_12","alias_value":"LE4R42VJXKAN","created_at":"2026-07-05T03:11:28.402742+00:00"},{"alias_kind":"pith_short_16","alias_value":"LE4R42VJXKANHCZ6","created_at":"2026-07-05T03:11:28.402742+00:00"},{"alias_kind":"pith_short_8","alias_value":"LE4R42VJ","created_at":"2026-07-05T03:11:28.402742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23404","citing_title":"Enhanced Arabic Text Retrieval with Attentive Relevance Scoring","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL","json":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL.json","graph_json":"https://pith.science/api/pith-number/LE4R42VJXKANHCZ6BKG2GXGXNL/graph.json","events_json":"https://pith.science/api/pith-number/LE4R42VJXKANHCZ6BKG2GXGXNL/events.json","paper":"https://pith.science/paper/LE4R42VJ"},"agent_actions":{"view_html":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL","download_json":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL.json","view_paper":"https://pith.science/paper/LE4R42VJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.06678&json=true","fetch_graph":"https://pith.science/api/pith-number/LE4R42VJXKANHCZ6BKG2GXGXNL/graph.json","fetch_events":"https://pith.science/api/pith-number/LE4R42VJXKANHCZ6BKG2GXGXNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL/action/storage_attestation","attest_author":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL/action/author_attestation","sign_citation":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL/action/citation_signature","submit_replication":"https://pith.science/pith/LE4R42VJXKANHCZ6BKG2GXGXNL/action/replication_record"}},"created_at":"2026-07-05T03:11:28.402742+00:00","updated_at":"2026-07-05T03:11:28.402742+00:00"}