{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EEPK2H2RQQJCKPGNJZNHKPGJYQ","short_pith_number":"pith:EEPK2H2R","canonical_record":{"source":{"id":"1803.04375","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-03-12T17:07:40Z","cross_cats_sorted":[],"title_canon_sha256":"4704ef62e58de71a1aa019eef036b2a3a109aa7a2f7da73a08dc7f611f86d6fa","abstract_canon_sha256":"3a6b9dc9a5f85f2c50b356c2b5adfffd76acd5d9bf042d67d8797901a5def80e"},"schema_version":"1.0"},"canonical_sha256":"211ead1f518412253ccd4e5a753cc9c4108dc11bdf5711de4968c6044489116b","source":{"kind":"arxiv","id":"1803.04375","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04375","created_at":"2026-05-18T00:21:29Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04375v1","created_at":"2026-05-18T00:21:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04375","created_at":"2026-05-18T00:21:29Z"},{"alias_kind":"pith_short_12","alias_value":"EEPK2H2RQQJC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EEPK2H2RQQJCKPGN","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EEPK2H2R","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EEPK2H2RQQJCKPGNJZNHKPGJYQ","target":"record","payload":{"canonical_record":{"source":{"id":"1803.04375","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-03-12T17:07:40Z","cross_cats_sorted":[],"title_canon_sha256":"4704ef62e58de71a1aa019eef036b2a3a109aa7a2f7da73a08dc7f611f86d6fa","abstract_canon_sha256":"3a6b9dc9a5f85f2c50b356c2b5adfffd76acd5d9bf042d67d8797901a5def80e"},"schema_version":"1.0"},"canonical_sha256":"211ead1f518412253ccd4e5a753cc9c4108dc11bdf5711de4968c6044489116b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:29.835231Z","signature_b64":"kzG1X9eop2RX0BqcsS8SOMbozeosDlbLBdvMqclMrJ+WoDEQ6Hdt3qFBPMIP4ipI8sJ1zEy6HewIrmnIgOX0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"211ead1f518412253ccd4e5a753cc9c4108dc11bdf5711de4968c6044489116b","last_reissued_at":"2026-05-18T00:21:29.834627Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:29.834627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.04375","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:21:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y5cRu1TnFgaOAgtUTLK41+RaX2kxNSOXYTQcwRTh7fdOjxDlTtVgt5hghtcEDj3zTvRu/UdO4LVxuKSV8XB4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:08:55.082430Z"},"content_sha256":"a000f96a3945bf423c204ef5ef7d36c5f4a4a9cc570d0cd2ab11585ab01c9c92","schema_version":"1.0","event_id":"sha256:a000f96a3945bf423c204ef5ef7d36c5f4a4a9cc570d0cd2ab11585ab01c9c92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EEPK2H2RQQJCKPGNJZNHKPGJYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Feature-Rich Vietnamese Named-Entity Recognition Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pham Quang Nhat Minh","submitted_at":"2018-03-12T17:07:40Z","abstract_excerpt":"In this paper, we present a feature-based named-entity recognition (NER) model that achieves the start-of-the-art accuracy for Vietnamese language. We combine word, word-shape features, PoS, chunk, Brown-cluster-based features, and word-embedding-based features in the Conditional Random Fields (CRF) model. We also explore the effects of word segmentation, PoS tagging, and chunking results of many popular Vietnamese NLP toolkits on the accuracy of the proposed feature-based NER model. Up to now, our work is the first work that systematically performs an extrinsic evaluation of basic Vietnamese "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04375","kind":"arxiv","version":1},"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":"2026-05-18T00:21:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eU3kaMMLBSVSTSpRqS+lahbmIUYlbxUL39a0TQHTxsjSziUZJ+5ftjYvbLWpbFurv9rdbv9ChZZ6M0BT7Ew/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:08:55.083255Z"},"content_sha256":"a3c6d9d23e82cdd07b5eb22ea047f3a19555595106864ab4381dbe0b6ead8408","schema_version":"1.0","event_id":"sha256:a3c6d9d23e82cdd07b5eb22ea047f3a19555595106864ab4381dbe0b6ead8408"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EEPK2H2RQQJCKPGNJZNHKPGJYQ/bundle.json","state_url":"https://pith.science/pith/EEPK2H2RQQJCKPGNJZNHKPGJYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EEPK2H2RQQJCKPGNJZNHKPGJYQ/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":"2026-08-04T23:08:55Z","links":{"resolver":"https://pith.science/pith/EEPK2H2RQQJCKPGNJZNHKPGJYQ","bundle":"https://pith.science/pith/EEPK2H2RQQJCKPGNJZNHKPGJYQ/bundle.json","state":"https://pith.science/pith/EEPK2H2RQQJCKPGNJZNHKPGJYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EEPK2H2RQQJCKPGNJZNHKPGJYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EEPK2H2RQQJCKPGNJZNHKPGJYQ","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":"3a6b9dc9a5f85f2c50b356c2b5adfffd76acd5d9bf042d67d8797901a5def80e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-03-12T17:07:40Z","title_canon_sha256":"4704ef62e58de71a1aa019eef036b2a3a109aa7a2f7da73a08dc7f611f86d6fa"},"schema_version":"1.0","source":{"id":"1803.04375","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04375","created_at":"2026-05-18T00:21:29Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04375v1","created_at":"2026-05-18T00:21:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04375","created_at":"2026-05-18T00:21:29Z"},{"alias_kind":"pith_short_12","alias_value":"EEPK2H2RQQJC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EEPK2H2RQQJCKPGN","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EEPK2H2R","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:a3c6d9d23e82cdd07b5eb22ea047f3a19555595106864ab4381dbe0b6ead8408","target":"graph","created_at":"2026-05-18T00:21:29Z","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":"In this paper, we present a feature-based named-entity recognition (NER) model that achieves the start-of-the-art accuracy for Vietnamese language. We combine word, word-shape features, PoS, chunk, Brown-cluster-based features, and word-embedding-based features in the Conditional Random Fields (CRF) model. We also explore the effects of word segmentation, PoS tagging, and chunking results of many popular Vietnamese NLP toolkits on the accuracy of the proposed feature-based NER model. Up to now, our work is the first work that systematically performs an extrinsic evaluation of basic Vietnamese ","authors_text":"Pham Quang Nhat Minh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-03-12T17:07:40Z","title":"A Feature-Rich Vietnamese Named-Entity Recognition Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04375","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:a000f96a3945bf423c204ef5ef7d36c5f4a4a9cc570d0cd2ab11585ab01c9c92","target":"record","created_at":"2026-05-18T00:21:29Z","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":"3a6b9dc9a5f85f2c50b356c2b5adfffd76acd5d9bf042d67d8797901a5def80e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-03-12T17:07:40Z","title_canon_sha256":"4704ef62e58de71a1aa019eef036b2a3a109aa7a2f7da73a08dc7f611f86d6fa"},"schema_version":"1.0","source":{"id":"1803.04375","kind":"arxiv","version":1}},"canonical_sha256":"211ead1f518412253ccd4e5a753cc9c4108dc11bdf5711de4968c6044489116b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"211ead1f518412253ccd4e5a753cc9c4108dc11bdf5711de4968c6044489116b","first_computed_at":"2026-05-18T00:21:29.834627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:29.834627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kzG1X9eop2RX0BqcsS8SOMbozeosDlbLBdvMqclMrJ+WoDEQ6Hdt3qFBPMIP4ipI8sJ1zEy6HewIrmnIgOX0Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:29.835231Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.04375","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a000f96a3945bf423c204ef5ef7d36c5f4a4a9cc570d0cd2ab11585ab01c9c92","sha256:a3c6d9d23e82cdd07b5eb22ea047f3a19555595106864ab4381dbe0b6ead8408"],"state_sha256":"a25463cc27eaaf489c3fb4bc94ce4f4e10fb4b124ffaf00b0d9c8eccd73a57ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f36h4ShVhoP8UjhFp1uXvfXiBQOVpDD/K9KAJy9dmX2f9aLIAKp1/1Tr54HTshAj4zGU9ZZ4XBNzjoChiwShDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:08:55.088092Z","bundle_sha256":"fcbe32d31ca2e29bb38544da05a5b72f32912f50a4988fc64cea1780000ad041"}}