{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FARIZGQELJOH5Y2OUJ3TTV6YWB","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":"a919fcd6686312284e9bb691fde5d30b3a0a8a7eb631b6fcb8886a251bc66df9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T17:27:31Z","title_canon_sha256":"b5dae4557df647d477a27bf32d00c2c3c8923d32542128e04c29c100952a03d0"},"schema_version":"1.0","source":{"id":"2306.14866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14866","created_at":"2026-07-05T09:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14866v1","created_at":"2026-07-05T09:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14866","created_at":"2026-07-05T09:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"FARIZGQELJOH","created_at":"2026-07-05T09:44:48Z"},{"alias_kind":"pith_short_16","alias_value":"FARIZGQELJOH5Y2O","created_at":"2026-07-05T09:44:48Z"},{"alias_kind":"pith_short_8","alias_value":"FARIZGQE","created_at":"2026-07-05T09:44:48Z"}],"graph_snapshots":[{"event_id":"sha256:e7d6bfeffa035f51e243aef17676242c10bfa60fcbd2c6ee26f6252b3c3ec3d8","target":"graph","created_at":"2026-07-05T09:44:48Z","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/2306.14866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we address the scarcity of annotated data for NArabizi, a Romanized form of North African Arabic used mostly on social media, which poses challenges for Natural Language Processing (NLP). We introduce an enriched version of NArabizi Treebank (Seddah et al., 2020) with three main contributions: the addition of two novel annotation layers (named entity recognition and offensive language detection) and a re-annotation of the tokenization, morpho-syntactic and syntactic layers that ensure annotation consistency. Our experimental results, using different tokenization schemes, showcase","authors_text":"Arij Riabi, Djam\\'e Seddah, Menel Mahamdi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T17:27:31Z","title":"Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14866","kind":"arxiv","version":1},"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:f594c296e32454fa95442dd52613a149bc9dc640c3ce49d76df3080031772147","target":"record","created_at":"2026-07-05T09:44:48Z","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":"a919fcd6686312284e9bb691fde5d30b3a0a8a7eb631b6fcb8886a251bc66df9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T17:27:31Z","title_canon_sha256":"b5dae4557df647d477a27bf32d00c2c3c8923d32542128e04c29c100952a03d0"},"schema_version":"1.0","source":{"id":"2306.14866","kind":"arxiv","version":1}},"canonical_sha256":"28228c9a045a5c7ee34ea27739d7d8b04bb4f0cfed0e69fcc053f5ba540ea2ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28228c9a045a5c7ee34ea27739d7d8b04bb4f0cfed0e69fcc053f5ba540ea2ca","first_computed_at":"2026-07-05T09:44:48.237365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:48.237365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SszP8/fW0BnBQSq7iWwt+XYIM6N/VSl6Y+/TxUA1tGCBmzzud2Dr1Gbjw8VF6QYh8/LdAb7OkJSeB450Qv3CCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:48.237842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f594c296e32454fa95442dd52613a149bc9dc640c3ce49d76df3080031772147","sha256:e7d6bfeffa035f51e243aef17676242c10bfa60fcbd2c6ee26f6252b3c3ec3d8"],"state_sha256":"3760b70bf9bf424a61fea0cab132ac76dbbc4eae10e6efc9d7ae1e0732efaec8"}