{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BCYFYYLIQEFXUIXT4HE6RTFNYZ","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":"4db4fec1c518f02d6dcea01fb7b45092229c808388287d552a6073e565eca550","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-04T08:24:05Z","title_canon_sha256":"6f680eb9f61db5c6bf9c0f5f0a16ce5fd4f47661e993cc09cc5185b40e158cad"},"schema_version":"1.0","source":{"id":"1908.01294","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01294","created_at":"2026-07-04T23:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01294v2","created_at":"2026-07-04T23:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01294","created_at":"2026-07-04T23:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"BCYFYYLIQEFX","created_at":"2026-07-04T23:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"BCYFYYLIQEFXUIXT","created_at":"2026-07-04T23:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"BCYFYYLI","created_at":"2026-07-04T23:59:34Z"}],"graph_snapshots":[{"event_id":"sha256:a0ff612e9ccb05660bfb5f283b620e09d317ed1ea1e4ca95431243f9a677a3f4","target":"graph","created_at":"2026-07-04T23:59:34Z","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/1908.01294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep learning model for the task of sentence segmentation that includes three main contributions. First, we integrate n-gram embedding as a local representation to capture word groups near sentence boundaries. Second, to focus on the keywords of dependent clauses, we combine the model with a distant representation obtained from self-attention modules. Finally, due to the scarcity of la","authors_text":"Chanatip Saetia, Ekapol Chuangsuwanich, Peerapon Vateekul, Tawunrat Chalothorn","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-04T08:24:05Z","title":"Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01294","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:b05efd5b06a9745e1e9bc11bcb3b17d053acc4912d251a7b9bb1ec37ba75b987","target":"record","created_at":"2026-07-04T23:59:34Z","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":"4db4fec1c518f02d6dcea01fb7b45092229c808388287d552a6073e565eca550","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-04T08:24:05Z","title_canon_sha256":"6f680eb9f61db5c6bf9c0f5f0a16ce5fd4f47661e993cc09cc5185b40e158cad"},"schema_version":"1.0","source":{"id":"1908.01294","kind":"arxiv","version":2}},"canonical_sha256":"08b05c6168810b7a22f3e1c9e8ccadc67a70bb312e696182a45a8b7292173c43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08b05c6168810b7a22f3e1c9e8ccadc67a70bb312e696182a45a8b7292173c43","first_computed_at":"2026-07-04T23:59:34.313435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:34.313435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7RUWNnzVLQl+hTboqDK1NjF+JvS56f2LJ00EZicXL/WHVWR4+EvEOtLN3CtrtngCFJcBv9lpCBnhKmryBYNyBg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:34.313808Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01294","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b05efd5b06a9745e1e9bc11bcb3b17d053acc4912d251a7b9bb1ec37ba75b987","sha256:a0ff612e9ccb05660bfb5f283b620e09d317ed1ea1e4ca95431243f9a677a3f4"],"state_sha256":"9e944b8d3749230d708eb2f19590cbe24639788f0b9c60377ecdf16d939ca768"}