{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MCAWRM5675R3THKWHX5AVOYHNY","short_pith_number":"pith:MCAWRM56","schema_version":"1.0","canonical_sha256":"608168b3beff63b99d563dfa0abb076e1c067a81699d88ac900eb7c4793ff070","source":{"kind":"arxiv","id":"2109.01293","version":1},"attestation_state":"computed","paper":{"title":"An Open-Source Dataset and A Multi-Task Model for Malay Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nankai Lin, Shengyi Jiang, Yingwen Fu, Zhihe Yang","submitted_at":"2021-09-03T03:29:25Z","abstract_excerpt":"Named entity recognition (NER) is a fundamental task of natural language processing (NLP). However, most state-of-the-art research is mainly oriented to high-resource languages such as English and has not been widely applied to low-resource languages. In Malay language, relevant NER resources are limited. In this work, we propose a dataset construction framework, which is based on labeled datasets of homologous languages and iterative optimization, to build a Malay NER dataset (MYNER) comprising 28,991 sentences (over 384 thousand tokens). Additionally, to better integrate boundary information"},"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":"2109.01293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T03:29:25Z","cross_cats_sorted":[],"title_canon_sha256":"9d5959e4d250eb2363e58c6d38455e685d97591961dd56c741651bf3bcbbb49a","abstract_canon_sha256":"bddbdcbced1690a392234ba377f9043fff51fa42c9d5d70b383ccd0552ac9442"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:17.165136Z","signature_b64":"VqxMeEZvFuHpiM+yshajdAvcYGxdd1ThmO0/6dKwx/A6h/Vp1HwBru8U0r1GzbLe+h2BKePzVoXDT+0mEmTEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"608168b3beff63b99d563dfa0abb076e1c067a81699d88ac900eb7c4793ff070","last_reissued_at":"2026-07-05T03:11:17.164530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:17.164530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Open-Source Dataset and A Multi-Task Model for Malay Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nankai Lin, Shengyi Jiang, Yingwen Fu, Zhihe Yang","submitted_at":"2021-09-03T03:29:25Z","abstract_excerpt":"Named entity recognition (NER) is a fundamental task of natural language processing (NLP). However, most state-of-the-art research is mainly oriented to high-resource languages such as English and has not been widely applied to low-resource languages. In Malay language, relevant NER resources are limited. In this work, we propose a dataset construction framework, which is based on labeled datasets of homologous languages and iterative optimization, to build a Malay NER dataset (MYNER) comprising 28,991 sentences (over 384 thousand tokens). Additionally, to better integrate boundary information"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01293","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/2109.01293/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":"2109.01293","created_at":"2026-07-05T03:11:17.164611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.01293v1","created_at":"2026-07-05T03:11:17.164611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01293","created_at":"2026-07-05T03:11:17.164611+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCAWRM5675R3","created_at":"2026-07-05T03:11:17.164611+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCAWRM5675R3THKW","created_at":"2026-07-05T03:11:17.164611+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCAWRM56","created_at":"2026-07-05T03:11:17.164611+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/MCAWRM5675R3THKWHX5AVOYHNY","json":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY.json","graph_json":"https://pith.science/api/pith-number/MCAWRM5675R3THKWHX5AVOYHNY/graph.json","events_json":"https://pith.science/api/pith-number/MCAWRM5675R3THKWHX5AVOYHNY/events.json","paper":"https://pith.science/paper/MCAWRM56"},"agent_actions":{"view_html":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY","download_json":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY.json","view_paper":"https://pith.science/paper/MCAWRM56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.01293&json=true","fetch_graph":"https://pith.science/api/pith-number/MCAWRM5675R3THKWHX5AVOYHNY/graph.json","fetch_events":"https://pith.science/api/pith-number/MCAWRM5675R3THKWHX5AVOYHNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY/action/storage_attestation","attest_author":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY/action/author_attestation","sign_citation":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY/action/citation_signature","submit_replication":"https://pith.science/pith/MCAWRM5675R3THKWHX5AVOYHNY/action/replication_record"}},"created_at":"2026-07-05T03:11:17.164611+00:00","updated_at":"2026-07-05T03:11:17.164611+00:00"}