{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PQUWQPEIH5KXIKB2IGXWYJE5S3","short_pith_number":"pith:PQUWQPEI","canonical_record":{"source":{"id":"2102.12136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-24T08:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"1889489559fbdc80c3d99b24130fe12e5ebefae6b8a76595d3d159a138092ff6","abstract_canon_sha256":"cf14315b1d2315fe710899bfcd1144d0cf048f9f572850f8c01bcf84fcdda2f7"},"schema_version":"1.0"},"canonical_sha256":"7c29683c883f5574283a41af6c249d96dcde7093662c52813b678ff497739ef9","source":{"kind":"arxiv","id":"2102.12136","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12136","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12136v2","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12136","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"pith_short_12","alias_value":"PQUWQPEIH5KX","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"pith_short_16","alias_value":"PQUWQPEIH5KXIKB2","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"pith_short_8","alias_value":"PQUWQPEI","created_at":"2026-07-05T02:49:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PQUWQPEIH5KXIKB2IGXWYJE5S3","target":"record","payload":{"canonical_record":{"source":{"id":"2102.12136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-24T08:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"1889489559fbdc80c3d99b24130fe12e5ebefae6b8a76595d3d159a138092ff6","abstract_canon_sha256":"cf14315b1d2315fe710899bfcd1144d0cf048f9f572850f8c01bcf84fcdda2f7"},"schema_version":"1.0"},"canonical_sha256":"7c29683c883f5574283a41af6c249d96dcde7093662c52813b678ff497739ef9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:53.483764Z","signature_b64":"GLEudaSussxad9FJK5NQphIKT5k4jsxznIicTvNVOeaqt9PJAcIN2GHJcMNtiZ3Ts9IWhk/Jul0X3T/OmBuXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c29683c883f5574283a41af6c249d96dcde7093662c52813b678ff497739ef9","last_reissued_at":"2026-07-05T02:49:53.483213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:53.483213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.12136","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":"2026-07-05T02:49:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eToxQh+BFGVND4OjVGsswt5QXgKyj6Ndk7WEJmuXRtDCVMEBndNFgW7Vi4cnR/Y+yPzOGmPM5Tesrd7oQGG2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:56:19.331098Z"},"content_sha256":"37d493437f5cf98cff84157454e549e006678b33573ac5e538cb10a0d3f29c07","schema_version":"1.0","event_id":"sha256:37d493437f5cf98cff84157454e549e006678b33573ac5e538cb10a0d3f29c07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PQUWQPEIH5KXIKB2IGXWYJE5S3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting Part-of-speech Tagging with Syntactic Information for Vietnamese and Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen","submitted_at":"2021-02-24T08:57:02Z","abstract_excerpt":"Word segmentation and part-of-speech tagging are two critical preliminary steps for downstream tasks in Vietnamese natural language processing. In reality, people tend to consider also the phrase boundary when performing word segmentation and part of speech tagging rather than solely process word by word from left to right. In this paper, we implement this idea to improve word segmentation and part of speech tagging the Vietnamese language by employing a simplified constituency parser. Our neural model for joint word segmentation and part-of-speech tagging has the architecture of the syllable-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12136","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/2102.12136/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":"2026-07-05T02:49:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6VPm0WIQQ8w3+ZS+VhBsJrOP67rpx/0fP9XDKAcni58WKNcfQNEHZdtP7Rmb2+iJJN+3G1r6H2wkBe56NmQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:56:19.331435Z"},"content_sha256":"f91b8a17da909e8e532826a436183136ecee4f4e69fe4fb2c36fd2f984626f4c","schema_version":"1.0","event_id":"sha256:f91b8a17da909e8e532826a436183136ecee4f4e69fe4fb2c36fd2f984626f4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQUWQPEIH5KXIKB2IGXWYJE5S3/bundle.json","state_url":"https://pith.science/pith/PQUWQPEIH5KXIKB2IGXWYJE5S3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQUWQPEIH5KXIKB2IGXWYJE5S3/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":"2026-08-21T17:56:19Z","links":{"resolver":"https://pith.science/pith/PQUWQPEIH5KXIKB2IGXWYJE5S3","bundle":"https://pith.science/pith/PQUWQPEIH5KXIKB2IGXWYJE5S3/bundle.json","state":"https://pith.science/pith/PQUWQPEIH5KXIKB2IGXWYJE5S3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQUWQPEIH5KXIKB2IGXWYJE5S3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PQUWQPEIH5KXIKB2IGXWYJE5S3","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":"cf14315b1d2315fe710899bfcd1144d0cf048f9f572850f8c01bcf84fcdda2f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-24T08:57:02Z","title_canon_sha256":"1889489559fbdc80c3d99b24130fe12e5ebefae6b8a76595d3d159a138092ff6"},"schema_version":"1.0","source":{"id":"2102.12136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12136","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12136v2","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12136","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"pith_short_12","alias_value":"PQUWQPEIH5KX","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"pith_short_16","alias_value":"PQUWQPEIH5KXIKB2","created_at":"2026-07-05T02:49:53Z"},{"alias_kind":"pith_short_8","alias_value":"PQUWQPEI","created_at":"2026-07-05T02:49:53Z"}],"graph_snapshots":[{"event_id":"sha256:f91b8a17da909e8e532826a436183136ecee4f4e69fe4fb2c36fd2f984626f4c","target":"graph","created_at":"2026-07-05T02:49:53Z","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/2102.12136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word segmentation and part-of-speech tagging are two critical preliminary steps for downstream tasks in Vietnamese natural language processing. In reality, people tend to consider also the phrase boundary when performing word segmentation and part of speech tagging rather than solely process word by word from left to right. In this paper, we implement this idea to improve word segmentation and part of speech tagging the Vietnamese language by employing a simplified constituency parser. Our neural model for joint word segmentation and part-of-speech tagging has the architecture of the syllable-","authors_text":"Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-24T08:57:02Z","title":"Augmenting Part-of-speech Tagging with Syntactic Information for Vietnamese and Chinese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12136","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":"sha256:37d493437f5cf98cff84157454e549e006678b33573ac5e538cb10a0d3f29c07","target":"record","created_at":"2026-07-05T02:49:53Z","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":"cf14315b1d2315fe710899bfcd1144d0cf048f9f572850f8c01bcf84fcdda2f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-24T08:57:02Z","title_canon_sha256":"1889489559fbdc80c3d99b24130fe12e5ebefae6b8a76595d3d159a138092ff6"},"schema_version":"1.0","source":{"id":"2102.12136","kind":"arxiv","version":2}},"canonical_sha256":"7c29683c883f5574283a41af6c249d96dcde7093662c52813b678ff497739ef9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c29683c883f5574283a41af6c249d96dcde7093662c52813b678ff497739ef9","first_computed_at":"2026-07-05T02:49:53.483213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:53.483213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GLEudaSussxad9FJK5NQphIKT5k4jsxznIicTvNVOeaqt9PJAcIN2GHJcMNtiZ3Ts9IWhk/Jul0X3T/OmBuXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:53.483764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.12136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37d493437f5cf98cff84157454e549e006678b33573ac5e538cb10a0d3f29c07","sha256:f91b8a17da909e8e532826a436183136ecee4f4e69fe4fb2c36fd2f984626f4c"],"state_sha256":"bb4e8851bd0465b074383c698a3e37671decc11e4ba3613cebafafe5d8de8681"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuqpxqGIYcfck6tjolWqbPEYhqdKPabl0uZSpstCVBmCYwezS6IeysSqyeYesZJvsGVpmJksG+5zxpV+4i00Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:56:19.335023Z","bundle_sha256":"4af4ee3d29e5374e32b1ac26ac1820820652e39d5a5eec99464255bb54cd8907"}}