{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LOBVJGCNVXHFPDNPVLJLD4RQC2","short_pith_number":"pith:LOBVJGCN","schema_version":"1.0","canonical_sha256":"5b8354984dadce578dafaad2b1f230168c285b4b149fdae8f260be4d92d76900","source":{"kind":"arxiv","id":"2504.18142","version":1},"attestation_state":"computed","paper":{"title":"EDU-NER-2025: Named Entity Recognition in Urdu Educational Texts using XLM-RoBERTa with X (formerly Twitter)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Gelbukh, Edgardo Manuel Felipe River\\'on, Fida Ullah, Grigori Sidorov, Muhammad Ahmad, Muhammad Arif, Muhammad Tayyab Zamir","submitted_at":"2025-04-25T07:50:58Z","abstract_excerpt":"Named Entity Recognition (NER) plays a pivotal role in various Natural Language Processing (NLP) tasks by identifying and classifying named entities (NEs) from unstructured data into predefined categories such as person, organization, location, date, and time. While extensive research exists for high-resource languages and general domains, NER in Urdu particularly within domain-specific contexts like education remains significantly underexplored. This is Due to lack of annotated datasets for educational content which limits the ability of existing models to accurately identify entities such as"},"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":"2504.18142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T07:50:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"111e6b66ab04645d880e752cab21d311a2fb6d32b3e09566b371476adfb52037","abstract_canon_sha256":"b61e37dd7d902c34f934a6ed157bdfb28417efa9df5e6b1235bd23c25e3c6e4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:02.636326Z","signature_b64":"CRUVhK4buuXrTWDT2SkJkaIGf51EcLdrxU3fAKNrtuXx3W0btKtT+7QBvDaAxoU/EbCRAJL/dZalngZBANI+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b8354984dadce578dafaad2b1f230168c285b4b149fdae8f260be4d92d76900","last_reissued_at":"2026-07-05T10:54:02.635842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:02.635842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EDU-NER-2025: Named Entity Recognition in Urdu Educational Texts using XLM-RoBERTa with X (formerly Twitter)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Gelbukh, Edgardo Manuel Felipe River\\'on, Fida Ullah, Grigori Sidorov, Muhammad Ahmad, Muhammad Arif, Muhammad Tayyab Zamir","submitted_at":"2025-04-25T07:50:58Z","abstract_excerpt":"Named Entity Recognition (NER) plays a pivotal role in various Natural Language Processing (NLP) tasks by identifying and classifying named entities (NEs) from unstructured data into predefined categories such as person, organization, location, date, and time. While extensive research exists for high-resource languages and general domains, NER in Urdu particularly within domain-specific contexts like education remains significantly underexplored. This is Due to lack of annotated datasets for educational content which limits the ability of existing models to accurately identify entities such as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18142","kind":"arxiv","version":1},"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/2504.18142/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":"2504.18142","created_at":"2026-07-05T10:54:02.635918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18142v1","created_at":"2026-07-05T10:54:02.635918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18142","created_at":"2026-07-05T10:54:02.635918+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOBVJGCNVXHF","created_at":"2026-07-05T10:54:02.635918+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOBVJGCNVXHFPDNP","created_at":"2026-07-05T10:54:02.635918+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOBVJGCN","created_at":"2026-07-05T10:54:02.635918+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/LOBVJGCNVXHFPDNPVLJLD4RQC2","json":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2.json","graph_json":"https://pith.science/api/pith-number/LOBVJGCNVXHFPDNPVLJLD4RQC2/graph.json","events_json":"https://pith.science/api/pith-number/LOBVJGCNVXHFPDNPVLJLD4RQC2/events.json","paper":"https://pith.science/paper/LOBVJGCN"},"agent_actions":{"view_html":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2","download_json":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2.json","view_paper":"https://pith.science/paper/LOBVJGCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18142&json=true","fetch_graph":"https://pith.science/api/pith-number/LOBVJGCNVXHFPDNPVLJLD4RQC2/graph.json","fetch_events":"https://pith.science/api/pith-number/LOBVJGCNVXHFPDNPVLJLD4RQC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2/action/storage_attestation","attest_author":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2/action/author_attestation","sign_citation":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2/action/citation_signature","submit_replication":"https://pith.science/pith/LOBVJGCNVXHFPDNPVLJLD4RQC2/action/replication_record"}},"created_at":"2026-07-05T10:54:02.635918+00:00","updated_at":"2026-07-05T10:54:02.635918+00:00"}