{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MCAWRM5675R3THKWHX5AVOYHNY","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":"bddbdcbced1690a392234ba377f9043fff51fa42c9d5d70b383ccd0552ac9442","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T03:29:25Z","title_canon_sha256":"9d5959e4d250eb2363e58c6d38455e685d97591961dd56c741651bf3bcbbb49a"},"schema_version":"1.0","source":{"id":"2109.01293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01293","created_at":"2026-07-05T03:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01293v1","created_at":"2026-07-05T03:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01293","created_at":"2026-07-05T03:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"MCAWRM5675R3","created_at":"2026-07-05T03:11:17Z"},{"alias_kind":"pith_short_16","alias_value":"MCAWRM5675R3THKW","created_at":"2026-07-05T03:11:17Z"},{"alias_kind":"pith_short_8","alias_value":"MCAWRM56","created_at":"2026-07-05T03:11:17Z"}],"graph_snapshots":[{"event_id":"sha256:8e76282571d393a3e59a08ddc828d205ead4f9483f537fdfef1e155924e267d6","target":"graph","created_at":"2026-07-05T03:11:17Z","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/2109.01293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Nankai Lin, Shengyi Jiang, Yingwen Fu, Zhihe Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T03:29:25Z","title":"An Open-Source Dataset and A Multi-Task Model for Malay Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01293","kind":"arxiv","version":1},"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:ba73fd0bf3525913ba472aa5884962cf8c0655d70c0c7d0668be3eab670acc54","target":"record","created_at":"2026-07-05T03:11:17Z","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":"bddbdcbced1690a392234ba377f9043fff51fa42c9d5d70b383ccd0552ac9442","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T03:29:25Z","title_canon_sha256":"9d5959e4d250eb2363e58c6d38455e685d97591961dd56c741651bf3bcbbb49a"},"schema_version":"1.0","source":{"id":"2109.01293","kind":"arxiv","version":1}},"canonical_sha256":"608168b3beff63b99d563dfa0abb076e1c067a81699d88ac900eb7c4793ff070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"608168b3beff63b99d563dfa0abb076e1c067a81699d88ac900eb7c4793ff070","first_computed_at":"2026-07-05T03:11:17.164530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:17.164530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VqxMeEZvFuHpiM+yshajdAvcYGxdd1ThmO0/6dKwx/A6h/Vp1HwBru8U0r1GzbLe+h2BKePzVoXDT+0mEmTEAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:17.165136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.01293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba73fd0bf3525913ba472aa5884962cf8c0655d70c0c7d0668be3eab670acc54","sha256:8e76282571d393a3e59a08ddc828d205ead4f9483f537fdfef1e155924e267d6"],"state_sha256":"c3b0a88d2cea487d86be3312061e5af325842f5c02a0cb19763759c129e29aa9"}