{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CCOX4HLOU74KEDNNIFBXXNTJSD","short_pith_number":"pith:CCOX4HLO","canonical_record":{"source":{"id":"1709.06307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-19T09:16:09Z","cross_cats_sorted":[],"title_canon_sha256":"fda30940cf81c3c94b8ab6091f8cebcb8317b82a0aa5e8ef037f569ddd03b2f3","abstract_canon_sha256":"986ee3e57dfe16ca62a387af67f198bbcc4d1d7e50fc768a72162780ccd92d4d"},"schema_version":"1.0"},"canonical_sha256":"109d7e1d6ea7f8a20dad41437bb66990d394bcd9eae1c3422c95fb8177298ec5","source":{"kind":"arxiv","id":"1709.06307","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06307","created_at":"2026-05-18T00:27:18Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06307v2","created_at":"2026-05-18T00:27:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06307","created_at":"2026-05-18T00:27:18Z"},{"alias_kind":"pith_short_12","alias_value":"CCOX4HLOU74K","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CCOX4HLOU74KEDNN","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CCOX4HLO","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CCOX4HLOU74KEDNNIFBXXNTJSD","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-19T09:16:09Z","cross_cats_sorted":[],"title_canon_sha256":"fda30940cf81c3c94b8ab6091f8cebcb8317b82a0aa5e8ef037f569ddd03b2f3","abstract_canon_sha256":"986ee3e57dfe16ca62a387af67f198bbcc4d1d7e50fc768a72162780ccd92d4d"},"schema_version":"1.0"},"canonical_sha256":"109d7e1d6ea7f8a20dad41437bb66990d394bcd9eae1c3422c95fb8177298ec5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:18.952818Z","signature_b64":"RRAESjbC4SGRYNnLlZ/+CLFriC6ZYISihf2YK/z3SptAt5/nlPNPGDQKnNHvyl7YNMVSXd6wjBdlU3jsG1KCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"109d7e1d6ea7f8a20dad41437bb66990d394bcd9eae1c3422c95fb8177298ec5","last_reissued_at":"2026-05-18T00:27:18.952300Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:18.952300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06307","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":"2026-05-18T00:27:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGORKhMWW9NR867P4B8+y4hgJcVmeEJpQbc/n0XFKzfD5zuBgyTzVIBlt6R66JNmRI+YH5BpFjBiC4kFWFxtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:23:54.708286Z"},"content_sha256":"b90bf2ead010e9bc812aad87a572b8037e20fe16236151907009f9e35c7a78d2","schema_version":"1.0","event_id":"sha256:b90bf2ead010e9bc812aad87a572b8037e20fe16236151907009f9e35c7a78d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CCOX4HLOU74KEDNNIFBXXNTJSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Fast and Accurate Vietnamese Word Segmenter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dai Quoc Nguyen, Dat Quoc Nguyen, Mark Dras, Mark Johnson, Thanh Vu","submitted_at":"2017-09-19T09:16:09Z","abstract_excerpt":"We propose a novel approach to Vietnamese word segmentation. Our approach is based on the Single Classification Ripple Down Rules methodology (Compton and Jansen, 1990), where rules are stored in an exception structure and new rules are only added to correct segmentation errors given by existing rules. Experimental results on the benchmark Vietnamese treebank show that our approach outperforms previous state-of-the-art approaches JVnSegmenter, vnTokenizer, DongDu and UETsegmenter in terms of both accuracy and performance speed. Our code is open-source and available at: https://github.com/datqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06307","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":""},"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":"2026-05-18T00:27:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1Lg4q5lLPce49gBrswnVGA6cn1ptWY7Azp9H/aWJNjhrmras0+7ijxDdWOPU97LHqGdE5CFwOIm9To8maeCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:23:54.708744Z"},"content_sha256":"38286e78cbd9d4b0a57c44a98a7270e303630d06f04a5a31a60de75ec3afce8d","schema_version":"1.0","event_id":"sha256:38286e78cbd9d4b0a57c44a98a7270e303630d06f04a5a31a60de75ec3afce8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCOX4HLOU74KEDNNIFBXXNTJSD/bundle.json","state_url":"https://pith.science/pith/CCOX4HLOU74KEDNNIFBXXNTJSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCOX4HLOU74KEDNNIFBXXNTJSD/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":"2026-05-26T14:23:54Z","links":{"resolver":"https://pith.science/pith/CCOX4HLOU74KEDNNIFBXXNTJSD","bundle":"https://pith.science/pith/CCOX4HLOU74KEDNNIFBXXNTJSD/bundle.json","state":"https://pith.science/pith/CCOX4HLOU74KEDNNIFBXXNTJSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCOX4HLOU74KEDNNIFBXXNTJSD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CCOX4HLOU74KEDNNIFBXXNTJSD","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":"986ee3e57dfe16ca62a387af67f198bbcc4d1d7e50fc768a72162780ccd92d4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-19T09:16:09Z","title_canon_sha256":"fda30940cf81c3c94b8ab6091f8cebcb8317b82a0aa5e8ef037f569ddd03b2f3"},"schema_version":"1.0","source":{"id":"1709.06307","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06307","created_at":"2026-05-18T00:27:18Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06307v2","created_at":"2026-05-18T00:27:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06307","created_at":"2026-05-18T00:27:18Z"},{"alias_kind":"pith_short_12","alias_value":"CCOX4HLOU74K","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CCOX4HLOU74KEDNN","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CCOX4HLO","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:38286e78cbd9d4b0a57c44a98a7270e303630d06f04a5a31a60de75ec3afce8d","target":"graph","created_at":"2026-05-18T00:27:18Z","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"},"paper":{"abstract_excerpt":"We propose a novel approach to Vietnamese word segmentation. Our approach is based on the Single Classification Ripple Down Rules methodology (Compton and Jansen, 1990), where rules are stored in an exception structure and new rules are only added to correct segmentation errors given by existing rules. Experimental results on the benchmark Vietnamese treebank show that our approach outperforms previous state-of-the-art approaches JVnSegmenter, vnTokenizer, DongDu and UETsegmenter in terms of both accuracy and performance speed. Our code is open-source and available at: https://github.com/datqu","authors_text":"Dai Quoc Nguyen, Dat Quoc Nguyen, Mark Dras, Mark Johnson, Thanh Vu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-19T09:16:09Z","title":"A Fast and Accurate Vietnamese Word Segmenter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06307","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:b90bf2ead010e9bc812aad87a572b8037e20fe16236151907009f9e35c7a78d2","target":"record","created_at":"2026-05-18T00:27:18Z","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":"986ee3e57dfe16ca62a387af67f198bbcc4d1d7e50fc768a72162780ccd92d4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-19T09:16:09Z","title_canon_sha256":"fda30940cf81c3c94b8ab6091f8cebcb8317b82a0aa5e8ef037f569ddd03b2f3"},"schema_version":"1.0","source":{"id":"1709.06307","kind":"arxiv","version":2}},"canonical_sha256":"109d7e1d6ea7f8a20dad41437bb66990d394bcd9eae1c3422c95fb8177298ec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"109d7e1d6ea7f8a20dad41437bb66990d394bcd9eae1c3422c95fb8177298ec5","first_computed_at":"2026-05-18T00:27:18.952300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:18.952300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RRAESjbC4SGRYNnLlZ/+CLFriC6ZYISihf2YK/z3SptAt5/nlPNPGDQKnNHvyl7YNMVSXd6wjBdlU3jsG1KCDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:18.952818Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06307","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b90bf2ead010e9bc812aad87a572b8037e20fe16236151907009f9e35c7a78d2","sha256:38286e78cbd9d4b0a57c44a98a7270e303630d06f04a5a31a60de75ec3afce8d"],"state_sha256":"13cf7b9150d4eac7b50670b08a92cda60e0af8fabb1ebdcc07ae2378dbfa3c47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PBvO9/jf0ojAYY5e2lAvT4wRGJfoM62lCKQbYocZvXsv8hW+BQrWO1VIRktCAVPmQ8nmbnjMwu7b+2ZvhRJFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T14:23:54.711269Z","bundle_sha256":"0b31db3a3bfdfa73fafb1fb784b74398cfa5023a16d0e63ce2e3fabe3b0f4c94"}}