{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MXP3BADMCQBHW6C6KMVPA32DSD","short_pith_number":"pith:MXP3BADM","schema_version":"1.0","canonical_sha256":"65dfb0806c14027b785e532af06f4390dfb6bf62e8cc0b237a6c5f9f068eb53b","source":{"kind":"arxiv","id":"2410.20838","version":1},"attestation_state":"computed","paper":{"title":"A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aimin Yang, Lixian Xiao, Meiyu Zeng, Nankai Lin, Shengyi Jiang, Wentao Huang","submitted_at":"2024-10-28T08:44:56Z","abstract_excerpt":"Currently, the majority of research in grammatical error correction (GEC) is concentrated on universal languages, such as English and Chinese. Many low-resource languages lack accessible evaluation corpora. How to efficiently construct high-quality evaluation corpora for GEC in low-resource languages has become a significant challenge. To fill these gaps, in this paper, we present a framework for constructing GEC corpora. Specifically, we focus on Indonesian as our research language and construct an evaluation corpus for Indonesian GEC using the proposed framework, addressing the limitations o"},"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":"2410.20838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T08:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"e523c77a7afc88e045c3faa74963723870a94e2d2a390c93ddfe9edc14d97196","abstract_canon_sha256":"eef0306251e67c1e15a38f5c3d06d5d38299bed6617486d054515e6c34e50c7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:11.919231Z","signature_b64":"5O2/eXq/J+SQb0hUQhCu3IvBKEeF5OGMWzBlCXVvnLinhTjgs+T0lUm1qLUsbwDxsJkaxZLt9tWrop4Miwa7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65dfb0806c14027b785e532af06f4390dfb6bf62e8cc0b237a6c5f9f068eb53b","last_reissued_at":"2026-07-05T09:27:11.918874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:11.918874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aimin Yang, Lixian Xiao, Meiyu Zeng, Nankai Lin, Shengyi Jiang, Wentao Huang","submitted_at":"2024-10-28T08:44:56Z","abstract_excerpt":"Currently, the majority of research in grammatical error correction (GEC) is concentrated on universal languages, such as English and Chinese. Many low-resource languages lack accessible evaluation corpora. How to efficiently construct high-quality evaluation corpora for GEC in low-resource languages has become a significant challenge. To fill these gaps, in this paper, we present a framework for constructing GEC corpora. Specifically, we focus on Indonesian as our research language and construct an evaluation corpus for Indonesian GEC using the proposed framework, addressing the limitations o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20838","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/2410.20838/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":"2410.20838","created_at":"2026-07-05T09:27:11.918930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20838v1","created_at":"2026-07-05T09:27:11.918930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20838","created_at":"2026-07-05T09:27:11.918930+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXP3BADMCQBH","created_at":"2026-07-05T09:27:11.918930+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXP3BADMCQBHW6C6","created_at":"2026-07-05T09:27:11.918930+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXP3BADM","created_at":"2026-07-05T09:27:11.918930+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/MXP3BADMCQBHW6C6KMVPA32DSD","json":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD.json","graph_json":"https://pith.science/api/pith-number/MXP3BADMCQBHW6C6KMVPA32DSD/graph.json","events_json":"https://pith.science/api/pith-number/MXP3BADMCQBHW6C6KMVPA32DSD/events.json","paper":"https://pith.science/paper/MXP3BADM"},"agent_actions":{"view_html":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD","download_json":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD.json","view_paper":"https://pith.science/paper/MXP3BADM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20838&json=true","fetch_graph":"https://pith.science/api/pith-number/MXP3BADMCQBHW6C6KMVPA32DSD/graph.json","fetch_events":"https://pith.science/api/pith-number/MXP3BADMCQBHW6C6KMVPA32DSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD/action/storage_attestation","attest_author":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD/action/author_attestation","sign_citation":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD/action/citation_signature","submit_replication":"https://pith.science/pith/MXP3BADMCQBHW6C6KMVPA32DSD/action/replication_record"}},"created_at":"2026-07-05T09:27:11.918930+00:00","updated_at":"2026-07-05T09:27:11.918930+00:00"}