{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IHNNR67CVJIDAZZC2URHUZK2LO","short_pith_number":"pith:IHNNR67C","canonical_record":{"source":{"id":"1912.01580","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T18:26:13Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"a5b3c839670c584439aa5b68c468a9a08ee465026f9a0630d40fdc9efcc26dde","abstract_canon_sha256":"3c71a84fba9e94c20e149fa3aabbe8bca6897d9b598f9e928dbfa5733414378e"},"schema_version":"1.0"},"canonical_sha256":"41dad8fbe2aa50306722d5227a655a5bae8ebfa71e5ee73682f29e0cc8e2ec4d","source":{"kind":"arxiv","id":"1912.01580","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.01580","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"arxiv_version","alias_value":"1912.01580v2","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01580","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"pith_short_12","alias_value":"IHNNR67CVJID","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"IHNNR67CVJIDAZZC","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"IHNNR67C","created_at":"2026-07-05T00:26:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IHNNR67CVJIDAZZC2URHUZK2LO","target":"record","payload":{"canonical_record":{"source":{"id":"1912.01580","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T18:26:13Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"a5b3c839670c584439aa5b68c468a9a08ee465026f9a0630d40fdc9efcc26dde","abstract_canon_sha256":"3c71a84fba9e94c20e149fa3aabbe8bca6897d9b598f9e928dbfa5733414378e"},"schema_version":"1.0"},"canonical_sha256":"41dad8fbe2aa50306722d5227a655a5bae8ebfa71e5ee73682f29e0cc8e2ec4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:44.977543Z","signature_b64":"vWELYedWpca3cd8VXnk3ZJKKPXMpkMeku6LNjK4SxwJtjl4P7OLCUK4J7i6y18RRnPDPvBQUz2IPZF3CNFjsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41dad8fbe2aa50306722d5227a655a5bae8ebfa71e5ee73682f29e0cc8e2ec4d","last_reissued_at":"2026-07-05T00:26:44.977038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:44.977038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.01580","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":"2026-07-05T00:26:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSovsRwraDhicO6QyMzkIxDMW3ylGMsASO+uosKOYzP4oTFmTv0M/jydjz+hZ4dZGpbcndJlyRTstht4JTxpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:37:31.900421Z"},"content_sha256":"5325340cf3db20dca4a14a24681fcce6555a610a2907264a105214e2ebded0b8","schema_version":"1.0","event_id":"sha256:5325340cf3db20dca4a14a24681fcce6555a610a2907264a105214e2ebded0b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IHNNR67CVJIDAZZC2URHUZK2LO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Pretrained Language Models on Thai Social Text Categorization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boonserm Kijsirikul, Kasidis Kanwatchara, Peerapon Vateekul, Thanapapas Horsuwan","submitted_at":"2019-12-03T18:26:13Z","abstract_excerpt":"The ever-growing volume of data of user-generated content on social media provides a nearly unlimited corpus of unlabeled data even in languages where resources are scarce. In this paper, we demonstrate that state-of-the-art results on two Thai social text categorization tasks can be realized by pretraining a language model on a large noisy Thai social media corpus of over 1.26 billion tokens and later fine-tuned on the downstream classification tasks. Due to the linguistically noisy and domain-specific nature of the content, our unique data preprocessing steps designed for Thai social media w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01580","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/1912.01580/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":"2026-07-05T00:26:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M5dZBLU6rtfNCC6p272692oXFqrcE/aEU0sQL/3IFkJ22uKWOTFFAzYQcFoBfa3c0zkc32uP307xCX3ku5UoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:37:31.901056Z"},"content_sha256":"7f3367938cdf50fee8868af225e95d89204f2a604c315e790af6fee68f72e997","schema_version":"1.0","event_id":"sha256:7f3367938cdf50fee8868af225e95d89204f2a604c315e790af6fee68f72e997"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IHNNR67CVJIDAZZC2URHUZK2LO/bundle.json","state_url":"https://pith.science/pith/IHNNR67CVJIDAZZC2URHUZK2LO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IHNNR67CVJIDAZZC2URHUZK2LO/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":"2026-07-07T07:37:31Z","links":{"resolver":"https://pith.science/pith/IHNNR67CVJIDAZZC2URHUZK2LO","bundle":"https://pith.science/pith/IHNNR67CVJIDAZZC2URHUZK2LO/bundle.json","state":"https://pith.science/pith/IHNNR67CVJIDAZZC2URHUZK2LO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IHNNR67CVJIDAZZC2URHUZK2LO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IHNNR67CVJIDAZZC2URHUZK2LO","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":"3c71a84fba9e94c20e149fa3aabbe8bca6897d9b598f9e928dbfa5733414378e","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T18:26:13Z","title_canon_sha256":"a5b3c839670c584439aa5b68c468a9a08ee465026f9a0630d40fdc9efcc26dde"},"schema_version":"1.0","source":{"id":"1912.01580","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.01580","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"arxiv_version","alias_value":"1912.01580v2","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01580","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"pith_short_12","alias_value":"IHNNR67CVJID","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"IHNNR67CVJIDAZZC","created_at":"2026-07-05T00:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"IHNNR67C","created_at":"2026-07-05T00:26:44Z"}],"graph_snapshots":[{"event_id":"sha256:7f3367938cdf50fee8868af225e95d89204f2a604c315e790af6fee68f72e997","target":"graph","created_at":"2026-07-05T00:26:44Z","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/1912.01580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ever-growing volume of data of user-generated content on social media provides a nearly unlimited corpus of unlabeled data even in languages where resources are scarce. In this paper, we demonstrate that state-of-the-art results on two Thai social text categorization tasks can be realized by pretraining a language model on a large noisy Thai social media corpus of over 1.26 billion tokens and later fine-tuned on the downstream classification tasks. Due to the linguistically noisy and domain-specific nature of the content, our unique data preprocessing steps designed for Thai social media w","authors_text":"Boonserm Kijsirikul, Kasidis Kanwatchara, Peerapon Vateekul, Thanapapas Horsuwan","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T18:26:13Z","title":"A Comparative Study of Pretrained Language Models on Thai Social Text Categorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01580","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":"sha256:5325340cf3db20dca4a14a24681fcce6555a610a2907264a105214e2ebded0b8","target":"record","created_at":"2026-07-05T00:26:44Z","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":"3c71a84fba9e94c20e149fa3aabbe8bca6897d9b598f9e928dbfa5733414378e","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T18:26:13Z","title_canon_sha256":"a5b3c839670c584439aa5b68c468a9a08ee465026f9a0630d40fdc9efcc26dde"},"schema_version":"1.0","source":{"id":"1912.01580","kind":"arxiv","version":2}},"canonical_sha256":"41dad8fbe2aa50306722d5227a655a5bae8ebfa71e5ee73682f29e0cc8e2ec4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41dad8fbe2aa50306722d5227a655a5bae8ebfa71e5ee73682f29e0cc8e2ec4d","first_computed_at":"2026-07-05T00:26:44.977038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:26:44.977038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vWELYedWpca3cd8VXnk3ZJKKPXMpkMeku6LNjK4SxwJtjl4P7OLCUK4J7i6y18RRnPDPvBQUz2IPZF3CNFjsBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:26:44.977543Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.01580","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5325340cf3db20dca4a14a24681fcce6555a610a2907264a105214e2ebded0b8","sha256:7f3367938cdf50fee8868af225e95d89204f2a604c315e790af6fee68f72e997"],"state_sha256":"3d5079298e7b933303cb310f7288fded179738e128ac7f856b1bda6a0f037354"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7OG0qEzgYONdotyZgbHOpYY1T2bBljaLMYFmIPfWtNFMmoJlHaVG/YOrYBG+fqLpbjkJ5vOGCfn6BojrLXI8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:37:31.904529Z","bundle_sha256":"aa1aef8828e199dd27f2d7a4d597a1322ac278208c42eb3b222fd6f6d41374ab"}}