{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LUKY2WXHJ5PSEVLC33GPHXUVXB","short_pith_number":"pith:LUKY2WXH","schema_version":"1.0","canonical_sha256":"5d158d5ae74f5f225562deccf3de95b8446851739683972a7f26c882e78aac19","source":{"kind":"arxiv","id":"2101.09635","version":2},"attestation_state":"computed","paper":{"title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charin Polpanumas, Lalita Lowphansirikul, Nawat Jantrakulchai, Sarana Nutanong","submitted_at":"2021-01-24T03:06:34Z","abstract_excerpt":"Transformer-based language models, more specifically BERT-based architectures have achieved state-of-the-art performance in many downstream tasks. However, for a relatively low-resource language such as Thai, the choices of models are limited to training a BERT-based model based on a much smaller dataset or finetuning multi-lingual models, both of which yield suboptimal downstream performance. Moreover, large-scale multi-lingual pretraining does not take into account language-specific features for Thai. To overcome these limitations, we pretrain a language model based on RoBERTa-base architect"},"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":"2101.09635","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-24T03:06:34Z","cross_cats_sorted":[],"title_canon_sha256":"9d1c157278aa46880f78fb43a51a823a3bc24b9fe3e8b5a52e3ba54e19cc4349","abstract_canon_sha256":"c7ebf82ca497b751e9729a8c851d98c0d79bbc794c2b604a4164a709228a9aee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:53.611217Z","signature_b64":"RmGY8vVqQUJuI/nKGVsmz5byiRlMmnGxyhrtHQI65I62ceNT27F4ut2gi/Dh40ySAm1X+djxIQ3gkpNYf5cpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d158d5ae74f5f225562deccf3de95b8446851739683972a7f26c882e78aac19","last_reissued_at":"2026-07-05T02:24:53.610748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:53.610748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charin Polpanumas, Lalita Lowphansirikul, Nawat Jantrakulchai, Sarana Nutanong","submitted_at":"2021-01-24T03:06:34Z","abstract_excerpt":"Transformer-based language models, more specifically BERT-based architectures have achieved state-of-the-art performance in many downstream tasks. However, for a relatively low-resource language such as Thai, the choices of models are limited to training a BERT-based model based on a much smaller dataset or finetuning multi-lingual models, both of which yield suboptimal downstream performance. Moreover, large-scale multi-lingual pretraining does not take into account language-specific features for Thai. To overcome these limitations, we pretrain a language model based on RoBERTa-base architect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09635","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/2101.09635/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":"2101.09635","created_at":"2026-07-05T02:24:53.610818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09635v2","created_at":"2026-07-05T02:24:53.610818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09635","created_at":"2026-07-05T02:24:53.610818+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUKY2WXHJ5PS","created_at":"2026-07-05T02:24:53.610818+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUKY2WXHJ5PSEVLC","created_at":"2026-07-05T02:24:53.610818+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUKY2WXH","created_at":"2026-07-05T02:24:53.610818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24609","citing_title":"Explainable Depression Detection using Masked Hard Instance Mining","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB","json":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB.json","graph_json":"https://pith.science/api/pith-number/LUKY2WXHJ5PSEVLC33GPHXUVXB/graph.json","events_json":"https://pith.science/api/pith-number/LUKY2WXHJ5PSEVLC33GPHXUVXB/events.json","paper":"https://pith.science/paper/LUKY2WXH"},"agent_actions":{"view_html":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB","download_json":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB.json","view_paper":"https://pith.science/paper/LUKY2WXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09635&json=true","fetch_graph":"https://pith.science/api/pith-number/LUKY2WXHJ5PSEVLC33GPHXUVXB/graph.json","fetch_events":"https://pith.science/api/pith-number/LUKY2WXHJ5PSEVLC33GPHXUVXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/action/storage_attestation","attest_author":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/action/author_attestation","sign_citation":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/action/citation_signature","submit_replication":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/action/replication_record"}},"created_at":"2026-07-05T02:24:53.610818+00:00","updated_at":"2026-07-05T02:24:53.610818+00:00"}