{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YDJGKCXV2DTGSVIBPM4D5KQ3PZ","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":"7b8cbd225efa21bea50fe5dd514cfb6f55efd7fb332b3da54d949f1003f4e188","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-19T05:39:21Z","title_canon_sha256":"945b6d96b263881c7cbcb3c59850dc3c8db11e6012c4cc35e570a49fbbe628d1"},"schema_version":"1.0","source":{"id":"2102.09749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09749","created_at":"2026-07-05T02:16:54Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09749v2","created_at":"2026-07-05T02:16:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09749","created_at":"2026-07-05T02:16:54Z"},{"alias_kind":"pith_short_12","alias_value":"YDJGKCXV2DTG","created_at":"2026-07-05T02:16:54Z"},{"alias_kind":"pith_short_16","alias_value":"YDJGKCXV2DTGSVIB","created_at":"2026-07-05T02:16:54Z"},{"alias_kind":"pith_short_8","alias_value":"YDJGKCXV","created_at":"2026-07-05T02:16:54Z"}],"graph_snapshots":[{"event_id":"sha256:507131212e9d1294415b3d2662546ac0ef11c1e07b1ba3af8597abf1d5d8bc7d","target":"graph","created_at":"2026-07-05T02:16:54Z","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/2102.09749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents our approach to address the EACL WANLP-2021 Shared Task 1: Nuanced Arabic Dialect Identification (NADI). The task is aimed at developing a system that identifies the geographical location(country/province) from where an Arabic tweet in the form of modern standard Arabic or dialect comes from. We solve the task in two parts. The first part involves pre-processing the provided dataset by cleaning, adding and segmenting various parts of the text. This is followed by carrying out experiments with different versions of two Transformer based models, AraBERT and AraELECTRA. Our fi","authors_text":"Anshul Wadhawan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-19T05:39:21Z","title":"Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09749","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":"sha256:095b892624004539a512a3fcdff834f06afbdc4ad1ee311d37703215281f40ad","target":"record","created_at":"2026-07-05T02:16:54Z","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":"7b8cbd225efa21bea50fe5dd514cfb6f55efd7fb332b3da54d949f1003f4e188","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-19T05:39:21Z","title_canon_sha256":"945b6d96b263881c7cbcb3c59850dc3c8db11e6012c4cc35e570a49fbbe628d1"},"schema_version":"1.0","source":{"id":"2102.09749","kind":"arxiv","version":2}},"canonical_sha256":"c0d2650af5d0e66955017b383eaa1b7e5727a523ba946f5aece97e6d2904b1e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0d2650af5d0e66955017b383eaa1b7e5727a523ba946f5aece97e6d2904b1e7","first_computed_at":"2026-07-05T02:16:54.074791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:16:54.074791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NaaQZLHUbjIC6N8khskmNZJKq0PyaH5RNISyXFaPOfVrwJDMmzoKMz1Sq5WNaAl3KiGSLoRmLMG5mSvOZBKTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:16:54.075234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.09749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:095b892624004539a512a3fcdff834f06afbdc4ad1ee311d37703215281f40ad","sha256:507131212e9d1294415b3d2662546ac0ef11c1e07b1ba3af8597abf1d5d8bc7d"],"state_sha256":"37c56c7ff41dbd965b315150559c584f7612db5879ecb19649445bf25654d477"}