{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LUKY2WXHJ5PSEVLC33GPHXUVXB","short_pith_number":"pith:LUKY2WXH","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"},"canonical_sha256":"5d158d5ae74f5f225562deccf3de95b8446851739683972a7f26c882e78aac19","source":{"kind":"arxiv","id":"2101.09635","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09635","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09635v2","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09635","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"LUKY2WXHJ5PS","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"pith_short_16","alias_value":"LUKY2WXHJ5PSEVLC","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"pith_short_8","alias_value":"LUKY2WXH","created_at":"2026-07-05T02:24:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LUKY2WXHJ5PSEVLC33GPHXUVXB","target":"record","payload":{"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"},"canonical_sha256":"5d158d5ae74f5f225562deccf3de95b8446851739683972a7f26c882e78aac19","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"},"source_kind":"arxiv","source_id":"2101.09635","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:24:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SNGhN3TtCsqgYczqf/DJ8XKtCOmpZB0b7aujs2Z/niqbrutCZOgo0hVp56WqS78mBAJUKcpfBr3SBVceFi8AAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:55:11.039619Z"},"content_sha256":"03b56a85783c341dc5ed48ea8da34a409d9b9f9b9dfbf2a576e90a8597d791d8","schema_version":"1.0","event_id":"sha256:03b56a85783c341dc5ed48ea8da34a409d9b9f9b9dfbf2a576e90a8597d791d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LUKY2WXHJ5PSEVLC33GPHXUVXB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:24:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNi9CvZkuzKYZCwWaiTwEIiXYwkwKW5f9uvamw90VyeCr1gT6HOZqLGOgJGOrMu8DILvW3FoavOmiG2LUpK4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:55:11.040186Z"},"content_sha256":"bfefc6da5567da07b69fd6aecd0a55a8e0696cc70a9569da2c70e32429a8f7a1","schema_version":"1.0","event_id":"sha256:bfefc6da5567da07b69fd6aecd0a55a8e0696cc70a9569da2c70e32429a8f7a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/bundle.json","state_url":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T05:55:11Z","links":{"resolver":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB","bundle":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/bundle.json","state":"https://pith.science/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LUKY2WXHJ5PSEVLC33GPHXUVXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LUKY2WXHJ5PSEVLC33GPHXUVXB","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":"c7ebf82ca497b751e9729a8c851d98c0d79bbc794c2b604a4164a709228a9aee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-24T03:06:34Z","title_canon_sha256":"9d1c157278aa46880f78fb43a51a823a3bc24b9fe3e8b5a52e3ba54e19cc4349"},"schema_version":"1.0","source":{"id":"2101.09635","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09635","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09635v2","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09635","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"LUKY2WXHJ5PS","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"pith_short_16","alias_value":"LUKY2WXHJ5PSEVLC","created_at":"2026-07-05T02:24:53Z"},{"alias_kind":"pith_short_8","alias_value":"LUKY2WXH","created_at":"2026-07-05T02:24:53Z"}],"graph_snapshots":[{"event_id":"sha256:bfefc6da5567da07b69fd6aecd0a55a8e0696cc70a9569da2c70e32429a8f7a1","target":"graph","created_at":"2026-07-05T02:24:53Z","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/2101.09635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Charin Polpanumas, Lalita Lowphansirikul, Nawat Jantrakulchai, Sarana Nutanong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-24T03:06:34Z","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09635","kind":"arxiv","version":2},"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":"sha256:03b56a85783c341dc5ed48ea8da34a409d9b9f9b9dfbf2a576e90a8597d791d8","target":"record","created_at":"2026-07-05T02:24:53Z","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":"c7ebf82ca497b751e9729a8c851d98c0d79bbc794c2b604a4164a709228a9aee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-24T03:06:34Z","title_canon_sha256":"9d1c157278aa46880f78fb43a51a823a3bc24b9fe3e8b5a52e3ba54e19cc4349"},"schema_version":"1.0","source":{"id":"2101.09635","kind":"arxiv","version":2}},"canonical_sha256":"5d158d5ae74f5f225562deccf3de95b8446851739683972a7f26c882e78aac19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d158d5ae74f5f225562deccf3de95b8446851739683972a7f26c882e78aac19","first_computed_at":"2026-07-05T02:24:53.610748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:53.610748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RmGY8vVqQUJuI/nKGVsmz5byiRlMmnGxyhrtHQI65I62ceNT27F4ut2gi/Dh40ySAm1X+djxIQ3gkpNYf5cpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:53.611217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.09635","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03b56a85783c341dc5ed48ea8da34a409d9b9f9b9dfbf2a576e90a8597d791d8","sha256:bfefc6da5567da07b69fd6aecd0a55a8e0696cc70a9569da2c70e32429a8f7a1"],"state_sha256":"f40e67bd44a2d8613a5230818fe671607ca7efdb9253bb4519cd10c975b38937"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qx/aQQNMPUTQL3D/PourO0qPl6kJ+JD4PzDb+4Q/it4qJQg8Z/cykGzXQV53Dkr+GWJ4S1UuuqisqZp30IhTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:55:11.045429Z","bundle_sha256":"4abff0fa9d722837fdc716295e35e690c9b293079234d79b25b98eb57e407bae"}}