{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PBA4S3YLTXHWPT7HM66ZAK7GZT","short_pith_number":"pith:PBA4S3YL","schema_version":"1.0","canonical_sha256":"7841c96f0b9dcf67cfe767bd902be6ccddb7ead360f93c739e6e675ae59dc2fd","source":{"kind":"arxiv","id":"2008.05055","version":1},"attestation_state":"computed","paper":{"title":"The Annotation Guideline of LST20 Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charun Phrombut, Dhanon Leenoi, Kanyanat Kriengket, Krit Kosawat, Monthika Boriboon, Prachya Boonkwan, Sitthaa Phaholphinyo, Thepchai Supnithi, Vorapon Luantangsrisuk","submitted_at":"2020-08-12T01:16:45Z","abstract_excerpt":"This report presents the annotation guideline for LST20, a large-scale corpus with multiple layers of linguistic annotation for Thai language processing. Our guideline consists of five layers of linguistic annotation: word segmentation, POS tagging, named entities, clause boundaries, and sentence boundaries. The dataset complies to the CoNLL-2003-style format for ease of use. LST20 Corpus offers five layers of linguistic annotation as aforementioned. At a large scale, it consists of 3,164,864 words, 288,020 named entities, 248,962 clauses, and 74,180 sentences, while it is annotated with 16 di"},"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":"2008.05055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-12T01:16:45Z","cross_cats_sorted":[],"title_canon_sha256":"76ea00d7b8184e9a4a998c653c33f23d3814fa293ee7746f3c3ad2e3d6d69bf4","abstract_canon_sha256":"25f89ff6840385b642c7ee52ec9fe9622b7a52be6021c2d0662379febaff3549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:43.126015Z","signature_b64":"BGHv25S919KaJoumXaL6wlxquEHcvCHZSWncagWJOIW7NsvNanVroqgLIRdTYBJ/ZpHwEIliiDfMIBbf45vOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7841c96f0b9dcf67cfe767bd902be6ccddb7ead360f93c739e6e675ae59dc2fd","last_reissued_at":"2026-07-05T01:26:43.125593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:43.125593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Annotation Guideline of LST20 Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charun Phrombut, Dhanon Leenoi, Kanyanat Kriengket, Krit Kosawat, Monthika Boriboon, Prachya Boonkwan, Sitthaa Phaholphinyo, Thepchai Supnithi, Vorapon Luantangsrisuk","submitted_at":"2020-08-12T01:16:45Z","abstract_excerpt":"This report presents the annotation guideline for LST20, a large-scale corpus with multiple layers of linguistic annotation for Thai language processing. Our guideline consists of five layers of linguistic annotation: word segmentation, POS tagging, named entities, clause boundaries, and sentence boundaries. The dataset complies to the CoNLL-2003-style format for ease of use. LST20 Corpus offers five layers of linguistic annotation as aforementioned. At a large scale, it consists of 3,164,864 words, 288,020 named entities, 248,962 clauses, and 74,180 sentences, while it is annotated with 16 di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05055","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/2008.05055/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":"2008.05055","created_at":"2026-07-05T01:26:43.125653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.05055v1","created_at":"2026-07-05T01:26:43.125653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05055","created_at":"2026-07-05T01:26:43.125653+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBA4S3YLTXHW","created_at":"2026-07-05T01:26:43.125653+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBA4S3YLTXHWPT7H","created_at":"2026-07-05T01:26:43.125653+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBA4S3YL","created_at":"2026-07-05T01:26:43.125653+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/PBA4S3YLTXHWPT7HM66ZAK7GZT","json":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT.json","graph_json":"https://pith.science/api/pith-number/PBA4S3YLTXHWPT7HM66ZAK7GZT/graph.json","events_json":"https://pith.science/api/pith-number/PBA4S3YLTXHWPT7HM66ZAK7GZT/events.json","paper":"https://pith.science/paper/PBA4S3YL"},"agent_actions":{"view_html":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT","download_json":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT.json","view_paper":"https://pith.science/paper/PBA4S3YL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.05055&json=true","fetch_graph":"https://pith.science/api/pith-number/PBA4S3YLTXHWPT7HM66ZAK7GZT/graph.json","fetch_events":"https://pith.science/api/pith-number/PBA4S3YLTXHWPT7HM66ZAK7GZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT/action/storage_attestation","attest_author":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT/action/author_attestation","sign_citation":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT/action/citation_signature","submit_replication":"https://pith.science/pith/PBA4S3YLTXHWPT7HM66ZAK7GZT/action/replication_record"}},"created_at":"2026-07-05T01:26:43.125653+00:00","updated_at":"2026-07-05T01:26:43.125653+00:00"}