{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PBA4S3YLTXHWPT7HM66ZAK7GZT","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":"25f89ff6840385b642c7ee52ec9fe9622b7a52be6021c2d0662379febaff3549","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-12T01:16:45Z","title_canon_sha256":"76ea00d7b8184e9a4a998c653c33f23d3814fa293ee7746f3c3ad2e3d6d69bf4"},"schema_version":"1.0","source":{"id":"2008.05055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.05055","created_at":"2026-07-05T01:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2008.05055v1","created_at":"2026-07-05T01:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05055","created_at":"2026-07-05T01:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"PBA4S3YLTXHW","created_at":"2026-07-05T01:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"PBA4S3YLTXHWPT7H","created_at":"2026-07-05T01:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"PBA4S3YL","created_at":"2026-07-05T01:26:43Z"}],"graph_snapshots":[{"event_id":"sha256:8d58f1ec7196ca1b8a2049dc91e339f2701e88481e206e73d629e91a44f366f4","target":"graph","created_at":"2026-07-05T01:26:43Z","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/2008.05055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Charun Phrombut, Dhanon Leenoi, Kanyanat Kriengket, Krit Kosawat, Monthika Boriboon, Prachya Boonkwan, Sitthaa Phaholphinyo, Thepchai Supnithi, Vorapon Luantangsrisuk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-12T01:16:45Z","title":"The Annotation Guideline of LST20 Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05055","kind":"arxiv","version":1},"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":"sha256:5cf763f996117bb92415880db8589ea6f565803eca6ffd62ecc6e1d0414000b4","target":"record","created_at":"2026-07-05T01:26:43Z","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":"25f89ff6840385b642c7ee52ec9fe9622b7a52be6021c2d0662379febaff3549","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-12T01:16:45Z","title_canon_sha256":"76ea00d7b8184e9a4a998c653c33f23d3814fa293ee7746f3c3ad2e3d6d69bf4"},"schema_version":"1.0","source":{"id":"2008.05055","kind":"arxiv","version":1}},"canonical_sha256":"7841c96f0b9dcf67cfe767bd902be6ccddb7ead360f93c739e6e675ae59dc2fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7841c96f0b9dcf67cfe767bd902be6ccddb7ead360f93c739e6e675ae59dc2fd","first_computed_at":"2026-07-05T01:26:43.125593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:26:43.125593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BGHv25S919KaJoumXaL6wlxquEHcvCHZSWncagWJOIW7NsvNanVroqgLIRdTYBJ/ZpHwEIliiDfMIBbf45vOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:26:43.126015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.05055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cf763f996117bb92415880db8589ea6f565803eca6ffd62ecc6e1d0414000b4","sha256:8d58f1ec7196ca1b8a2049dc91e339f2701e88481e206e73d629e91a44f366f4"],"state_sha256":"91a16a9e7863e07e89250bdcfb50b1d316edf8f6e53ca6b9eddfd05d818ce977"}