{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BCYFYYLIQEFXUIXT4HE6RTFNYZ","short_pith_number":"pith:BCYFYYLI","canonical_record":{"source":{"id":"1908.01294","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-04T08:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"6f680eb9f61db5c6bf9c0f5f0a16ce5fd4f47661e993cc09cc5185b40e158cad","abstract_canon_sha256":"4db4fec1c518f02d6dcea01fb7b45092229c808388287d552a6073e565eca550"},"schema_version":"1.0"},"canonical_sha256":"08b05c6168810b7a22f3e1c9e8ccadc67a70bb312e696182a45a8b7292173c43","source":{"kind":"arxiv","id":"1908.01294","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BCYFYYLIQEFXUIXT4HE6RTFNYZ","target":"record","payload":{"canonical_record":{"source":{"id":"1908.01294","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-04T08:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"6f680eb9f61db5c6bf9c0f5f0a16ce5fd4f47661e993cc09cc5185b40e158cad","abstract_canon_sha256":"4db4fec1c518f02d6dcea01fb7b45092229c808388287d552a6073e565eca550"},"schema_version":"1.0"},"canonical_sha256":"08b05c6168810b7a22f3e1c9e8ccadc67a70bb312e696182a45a8b7292173c43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:34.313808Z","signature_b64":"7RUWNnzVLQl+hTboqDK1NjF+JvS56f2LJ00EZicXL/WHVWR4+EvEOtLN3CtrtngCFJcBv9lpCBnhKmryBYNyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b05c6168810b7a22f3e1c9e8ccadc67a70bb312e696182a45a8b7292173c43","last_reissued_at":"2026-07-04T23:59:34.313435Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:34.313435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.01294","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":"2026-07-04T23:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyEMM9ZM84cHKP40ZryFmqMKmxIv8/rkT35bzjsZEI141fRQFznmjOvgEEucw8r6nOzniHht+EcxOeYddxW1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:47:27.696385Z"},"content_sha256":"b05efd5b06a9745e1e9bc11bcb3b17d053acc4912d251a7b9bb1ec37ba75b987","schema_version":"1.0","event_id":"sha256:b05efd5b06a9745e1e9bc11bcb3b17d053acc4912d251a7b9bb1ec37ba75b987"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BCYFYYLIQEFXUIXT4HE6RTFNYZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanatip Saetia, Ekapol Chuangsuwanich, Peerapon Vateekul, Tawunrat Chalothorn","submitted_at":"2019-08-04T08:24:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01294","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/1908.01294/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":"2026-07-04T23:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8rJ1vstA48ffFVmd1H/EKT+G5KcEtqo5XfElltIVwURogjtTPnzI7GiIvquG343kYdHhO4RJ+nQhdYnICP/zBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:47:27.696762Z"},"content_sha256":"a0ff612e9ccb05660bfb5f283b620e09d317ed1ea1e4ca95431243f9a677a3f4","schema_version":"1.0","event_id":"sha256:a0ff612e9ccb05660bfb5f283b620e09d317ed1ea1e4ca95431243f9a677a3f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/bundle.json","state_url":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/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":"2026-07-06T15:47:27Z","links":{"resolver":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ","bundle":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/bundle.json","state":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c2uT2gV/p/+4efWp7Vfu5LyuBQRKmdNb86nFEuLJZqk7mfWUPYF8aPBPUaTKt/tM/FP7ua/a0B6TB4LvJ9n0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:47:27.698739Z","bundle_sha256":"549dae13899fba1af07777effa563e79424729fb77cff70009bf6280150242a5"}}