{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2XY7QKZQL2Z7SVFZWPGDDZFYNB","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":"7d7217e1204c7f32a8ead3901901d03f9299069b563f871b31e47258b68ba6bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-10T04:35:16Z","title_canon_sha256":"9454e819df0607bf60c9333506435dfd42e6e9425c74791904e2dd9d5462ac97"},"schema_version":"1.0","source":{"id":"2010.04900","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04900","created_at":"2026-07-05T01:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04900v2","created_at":"2026-07-05T01:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04900","created_at":"2026-07-05T01:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"2XY7QKZQL2Z7","created_at":"2026-07-05T01:57:20Z"},{"alias_kind":"pith_short_16","alias_value":"2XY7QKZQL2Z7SVFZ","created_at":"2026-07-05T01:57:20Z"},{"alias_kind":"pith_short_8","alias_value":"2XY7QKZQ","created_at":"2026-07-05T01:57:20Z"}],"graph_snapshots":[{"event_id":"sha256:e4bd5c1a0ea48d3cf2506d4e9fbe66657dbeb5737fa13bef0d1b4ba4b9a6f83a","target":"graph","created_at":"2026-07-05T01:57:20Z","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/2010.04900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although the prediction of dialects is an important language processing task, with a wide range of applications, existing work is largely limited to coarse-grained varieties. Inspired by geolocation research, we propose the novel task of Micro-Dialect Identification (MDI) and introduce MARBERT, a new language model with striking abilities to predict a fine-grained variety (as small as that of a city) given a single, short message. For modeling, we offer a range of novel spatially and linguistically-motivated multi-task learning models. To showcase the utility of our models, we introduce a new,","authors_text":"AbdelRahim Elmadany, Chiyu Zhang, Lyle Ungar, Muhammad Abdul-Mageed","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-10T04:35:16Z","title":"Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04900","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:ec7e82247c25aa222749f8e45e91b6a0f3c3580e77cc46a84ebbd3ff8ad283bd","target":"record","created_at":"2026-07-05T01:57:20Z","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":"7d7217e1204c7f32a8ead3901901d03f9299069b563f871b31e47258b68ba6bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-10T04:35:16Z","title_canon_sha256":"9454e819df0607bf60c9333506435dfd42e6e9425c74791904e2dd9d5462ac97"},"schema_version":"1.0","source":{"id":"2010.04900","kind":"arxiv","version":2}},"canonical_sha256":"d5f1f82b305eb3f954b9b3cc31e4b8684206db2fcfc3b372ba17ba89e2df0d5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5f1f82b305eb3f954b9b3cc31e4b8684206db2fcfc3b372ba17ba89e2df0d5a","first_computed_at":"2026-07-05T01:57:20.693043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:20.693043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YOgk6qc+YEl0fYZxLqNI12LdNHYif79FzDpehF/uGcLdJuZ0XGCUCf4z1cahkx5U7FyReN8m/mN+sZPweHYTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:20.693435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04900","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec7e82247c25aa222749f8e45e91b6a0f3c3580e77cc46a84ebbd3ff8ad283bd","sha256:e4bd5c1a0ea48d3cf2506d4e9fbe66657dbeb5737fa13bef0d1b4ba4b9a6f83a"],"state_sha256":"131c3160cf03c9a01d0dfe2bb04c81fb880b04b20d45a98e12dde413e411c1ac"}