{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YNJAHHSVD5EHN6O2NNAIXW3FVL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"371824fe0d81d61f53c6b7e48e983c2b59bd84db81c190f4f860baa622ae6044","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T16:43:44Z","title_canon_sha256":"2867559b24ab3d404e9888ac06d6328bc0fdbea3919943fe3d9e9d567c621d24"},"schema_version":"1.0","source":{"id":"2110.06852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06852","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06852v2","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06852","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"YNJAHHSVD5EH","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"YNJAHHSVD5EHN6O2","created_at":"2026-07-05T04:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"YNJAHHSV","created_at":"2026-07-05T04:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:35d2389f011429dca5236d2154a77d36dc7220e44309c7557f61d5dfbbd2c83d","target":"graph","created_at":"2026-07-05T04:06:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.06852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Go Inoue, Nizar Habash, Salam Khalifa","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T16:43:44Z","title":"Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06852","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ba03813def94993468c4c3eed528f942e63aecff28cc8e87fe429c661782357e","target":"record","created_at":"2026-07-05T04:06:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"371824fe0d81d61f53c6b7e48e983c2b59bd84db81c190f4f860baa622ae6044","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T16:43:44Z","title_canon_sha256":"2867559b24ab3d404e9888ac06d6328bc0fdbea3919943fe3d9e9d567c621d24"},"schema_version":"1.0","source":{"id":"2110.06852","kind":"arxiv","version":2}},"canonical_sha256":"c352039e551f4876f9da6b408bdb65aaea1fee0a6221251cf66b0e99c6076c5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c352039e551f4876f9da6b408bdb65aaea1fee0a6221251cf66b0e99c6076c5d","first_computed_at":"2026-07-05T04:06:45.889328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:45.889328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gex94rUpbY9kEDo/yThPRJ9cFj23GlDZP/+Ea3XNZjFoxu1UWiqtZNez5PNmOdjlkYbJFDcMb4tl+PQ3r6VBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:45.889755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba03813def94993468c4c3eed528f942e63aecff28cc8e87fe429c661782357e","sha256:35d2389f011429dca5236d2154a77d36dc7220e44309c7557f61d5dfbbd2c83d"],"state_sha256":"cbdc659784e9f5db9db831279f9055a177e0dafac3e8d0e9ad7742855a68d8d0"}