{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YNJAHHSVD5EHN6O2NNAIXW3FVL","short_pith_number":"pith:YNJAHHSV","schema_version":"1.0","canonical_sha256":"c352039e551f4876f9da6b408bdb65aaea1fee0a6221251cf66b0e99c6076c5d","source":{"kind":"arxiv","id":"2110.06852","version":2},"attestation_state":"computed","paper":{"title":"Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Go Inoue, Nizar Habash, Salam Khalifa","submitted_at":"2021-10-13T16:43:44Z","abstract_excerpt":"We present state-of-the-art results on morphosyntactic tagging across different varieties of Arabic using fine-tuned pre-trained transformer language models. Our models consistently outperform existing systems in Modern Standard Arabic and all the Arabic dialects we study, achieving 2.6% absolute improvement over the previous state-of-the-art in Modern Standard Arabic, 2.8% in Gulf, 1.6% in Egyptian, and 8.3% in Levantine. We explore different training setups for fine-tuning pre-trained transformer language models, including training data size, the use of external linguistic resources, and the"},"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":"2110.06852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T16:43:44Z","cross_cats_sorted":[],"title_canon_sha256":"2867559b24ab3d404e9888ac06d6328bc0fdbea3919943fe3d9e9d567c621d24","abstract_canon_sha256":"371824fe0d81d61f53c6b7e48e983c2b59bd84db81c190f4f860baa622ae6044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:45.889755Z","signature_b64":"Gex94rUpbY9kEDo/yThPRJ9cFj23GlDZP/+Ea3XNZjFoxu1UWiqtZNez5PNmOdjlkYbJFDcMb4tl+PQ3r6VBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c352039e551f4876f9da6b408bdb65aaea1fee0a6221251cf66b0e99c6076c5d","last_reissued_at":"2026-07-05T04:06:45.889328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:45.889328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Go Inoue, Nizar Habash, Salam Khalifa","submitted_at":"2021-10-13T16:43:44Z","abstract_excerpt":"We present state-of-the-art results on morphosyntactic tagging across different varieties of Arabic using fine-tuned pre-trained transformer language models. Our models consistently outperform existing systems in Modern Standard Arabic and all the Arabic dialects we study, achieving 2.6% absolute improvement over the previous state-of-the-art in Modern Standard Arabic, 2.8% in Gulf, 1.6% in Egyptian, and 8.3% in Levantine. We explore different training setups for fine-tuning pre-trained transformer language models, including training data size, the use of external linguistic resources, and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06852","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/2110.06852/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":"2110.06852","created_at":"2026-07-05T04:06:45.889384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06852v2","created_at":"2026-07-05T04:06:45.889384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06852","created_at":"2026-07-05T04:06:45.889384+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNJAHHSVD5EH","created_at":"2026-07-05T04:06:45.889384+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNJAHHSVD5EHN6O2","created_at":"2026-07-05T04:06:45.889384+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNJAHHSV","created_at":"2026-07-05T04:06:45.889384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18399","citing_title":"Lemmatization as a Classification Task: Results from Arabic across Multiple Genres","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL","json":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL.json","graph_json":"https://pith.science/api/pith-number/YNJAHHSVD5EHN6O2NNAIXW3FVL/graph.json","events_json":"https://pith.science/api/pith-number/YNJAHHSVD5EHN6O2NNAIXW3FVL/events.json","paper":"https://pith.science/paper/YNJAHHSV"},"agent_actions":{"view_html":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL","download_json":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL.json","view_paper":"https://pith.science/paper/YNJAHHSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06852&json=true","fetch_graph":"https://pith.science/api/pith-number/YNJAHHSVD5EHN6O2NNAIXW3FVL/graph.json","fetch_events":"https://pith.science/api/pith-number/YNJAHHSVD5EHN6O2NNAIXW3FVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL/action/storage_attestation","attest_author":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL/action/author_attestation","sign_citation":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL/action/citation_signature","submit_replication":"https://pith.science/pith/YNJAHHSVD5EHN6O2NNAIXW3FVL/action/replication_record"}},"created_at":"2026-07-05T04:06:45.889384+00:00","updated_at":"2026-07-05T04:06:45.889384+00:00"}