{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AQSY4CN3VUU3I5UTB2VQB3UTBW","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":"62ca5649830823cb1c896b6057f5cda9087bcbe49411cd21ed14ead3b7b4363b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T03:47:24Z","title_canon_sha256":"87bd2f33f322f1a2ff7a5b3bd4c0be90dbf74f4ce01a1198e77dd21f0809ac28"},"schema_version":"1.0","source":{"id":"2406.06000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06000","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06000v1","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06000","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"AQSY4CN3VUU3","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"AQSY4CN3VUU3I5UT","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"AQSY4CN3","created_at":"2026-07-05T08:29:36Z"}],"graph_snapshots":[{"event_id":"sha256:0ec3307b6b3154ab8ee7fa16ddeca382b8831a3f3ef63550e23b8db0cd9f39f3","target":"graph","created_at":"2026-07-05T08:29:36Z","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/2406.06000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While coreference resolution is a well-established research area in Natural Language Processing (NLP), research focusing on Thai language remains limited due to the lack of large annotated corpora. In this work, we introduce ThaiCoref, a dataset for Thai coreference resolution. Our dataset comprises 777,271 tokens, 44,082 mentions and 10,429 entities across four text genres: university essays, newspapers, speeches, and Wikipedia. Our annotation scheme is built upon the OntoNotes benchmark with adjustments to address Thai-specific phenomena. Utilizing ThaiCoref, we train models employing a mult","authors_text":"Attapol T. Rutherford, Charin Polpanumas, Jitkapat Sawatphol, Pontakorn Trakuekul, Wei Qi Leong, William Chandra Tjhi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T03:47:24Z","title":"ThaiCoref: Thai Coreference Resolution Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06000","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:f73e00d2ca1b7e350dadfd268b4b9fad9902958c5fb3e13dfa38841ff3b4a400","target":"record","created_at":"2026-07-05T08:29:36Z","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":"62ca5649830823cb1c896b6057f5cda9087bcbe49411cd21ed14ead3b7b4363b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T03:47:24Z","title_canon_sha256":"87bd2f33f322f1a2ff7a5b3bd4c0be90dbf74f4ce01a1198e77dd21f0809ac28"},"schema_version":"1.0","source":{"id":"2406.06000","kind":"arxiv","version":1}},"canonical_sha256":"04258e09bbad29b476930eab00ee930d8a071c142f1fa613aad6f143025fb9a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04258e09bbad29b476930eab00ee930d8a071c142f1fa613aad6f143025fb9a9","first_computed_at":"2026-07-05T08:29:36.257727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:36.257727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BP7GJOdsDVAc9J/pv8xhFH1WyMNarl77x5DzOmTFY04bKsFmPhf/N/OL2g+yQD+tvS3yyoZ8btc0Q951gPPjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:36.258114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f73e00d2ca1b7e350dadfd268b4b9fad9902958c5fb3e13dfa38841ff3b4a400","sha256:0ec3307b6b3154ab8ee7fa16ddeca382b8831a3f3ef63550e23b8db0cd9f39f3"],"state_sha256":"eeb64577f85007d8bf521f8ffaf6f455a44058ad97bcb839f12622ba1559628d"}