{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2XY7QKZQL2Z7SVFZWPGDDZFYNB","short_pith_number":"pith:2XY7QKZQ","schema_version":"1.0","canonical_sha256":"d5f1f82b305eb3f954b9b3cc31e4b8684206db2fcfc3b372ba17ba89e2df0d5a","source":{"kind":"arxiv","id":"2010.04900","version":2},"attestation_state":"computed","paper":{"title":"Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Chiyu Zhang, Lyle Ungar, Muhammad Abdul-Mageed","submitted_at":"2020-10-10T04:35:16Z","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,"},"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":"2010.04900","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-10T04:35:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9454e819df0607bf60c9333506435dfd42e6e9425c74791904e2dd9d5462ac97","abstract_canon_sha256":"7d7217e1204c7f32a8ead3901901d03f9299069b563f871b31e47258b68ba6bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:20.693435Z","signature_b64":"YOgk6qc+YEl0fYZxLqNI12LdNHYif79FzDpehF/uGcLdJuZ0XGCUCf4z1cahkx5U7FyReN8m/mN+sZPweHYTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5f1f82b305eb3f954b9b3cc31e4b8684206db2fcfc3b372ba17ba89e2df0d5a","last_reissued_at":"2026-07-05T01:57:20.693043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:20.693043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Chiyu Zhang, Lyle Ungar, Muhammad Abdul-Mageed","submitted_at":"2020-10-10T04:35:16Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04900","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/2010.04900/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":"2010.04900","created_at":"2026-07-05T01:57:20.693094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04900v2","created_at":"2026-07-05T01:57:20.693094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04900","created_at":"2026-07-05T01:57:20.693094+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XY7QKZQL2Z7","created_at":"2026-07-05T01:57:20.693094+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XY7QKZQL2Z7SVFZ","created_at":"2026-07-05T01:57:20.693094+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XY7QKZQ","created_at":"2026-07-05T01:57:20.693094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB","json":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB.json","graph_json":"https://pith.science/api/pith-number/2XY7QKZQL2Z7SVFZWPGDDZFYNB/graph.json","events_json":"https://pith.science/api/pith-number/2XY7QKZQL2Z7SVFZWPGDDZFYNB/events.json","paper":"https://pith.science/paper/2XY7QKZQ"},"agent_actions":{"view_html":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB","download_json":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB.json","view_paper":"https://pith.science/paper/2XY7QKZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04900&json=true","fetch_graph":"https://pith.science/api/pith-number/2XY7QKZQL2Z7SVFZWPGDDZFYNB/graph.json","fetch_events":"https://pith.science/api/pith-number/2XY7QKZQL2Z7SVFZWPGDDZFYNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB/action/storage_attestation","attest_author":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB/action/author_attestation","sign_citation":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB/action/citation_signature","submit_replication":"https://pith.science/pith/2XY7QKZQL2Z7SVFZWPGDDZFYNB/action/replication_record"}},"created_at":"2026-07-05T01:57:20.693094+00:00","updated_at":"2026-07-05T01:57:20.693094+00:00"}