{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QDRATSV6HFAOCD5DLL3BUDGRCT","short_pith_number":"pith:QDRATSV6","canonical_record":{"source":{"id":"1711.04951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-14T05:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"52818ce5c9e3cce5bffbd2a343371d9ea28cfd038d6added4f135293b3e1e652","abstract_canon_sha256":"6bdb08c93ea16c50d661ee95eb2ff39f37da219f33423eaecb47595131963268"},"schema_version":"1.0"},"canonical_sha256":"80e209cabe3940e10fa35af61a0cd114f4223fc460af77af03d21cf3c3980d64","source":{"kind":"arxiv","id":"1711.04951","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04951","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04951v1","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04951","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"QDRATSV6HFAO","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QDRATSV6HFAOCD5D","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QDRATSV6","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QDRATSV6HFAOCD5DLL3BUDGRCT","target":"record","payload":{"canonical_record":{"source":{"id":"1711.04951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-14T05:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"52818ce5c9e3cce5bffbd2a343371d9ea28cfd038d6added4f135293b3e1e652","abstract_canon_sha256":"6bdb08c93ea16c50d661ee95eb2ff39f37da219f33423eaecb47595131963268"},"schema_version":"1.0"},"canonical_sha256":"80e209cabe3940e10fa35af61a0cd114f4223fc460af77af03d21cf3c3980d64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:35.345133Z","signature_b64":"IXPYTdq1Aao6oNiQ8A2JMqN/juwncIydHrDhcPFtkQDl6aMbfG3gDTOXJJncQnpNNEhqvGG0DXv/MIYBr9lYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e209cabe3940e10fa35af61a0cd114f4223fc460af77af03d21cf3c3980d64","last_reissued_at":"2026-05-18T00:30:35.344240Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:35.344240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.04951","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":"2026-05-18T00:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z3rxrVUcxIU2B6WDo9rjxLuTeMm7d22gvkQuKM5aIO08c2Qq2KtR0+s+35DXbuRLWEr8tLStCtXfSuvbFy1qBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:48:39.430476Z"},"content_sha256":"8bc2d4067c0bd8c06d0972252086985383784da18d23864235c615d9ab435e8d","schema_version":"1.0","event_id":"sha256:8bc2d4067c0bd8c06d0972252086985383784da18d23864235c615d9ab435e8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QDRATSV6HFAOCD5DLL3BUDGRCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Word Segmentation to POS Tagging for Vietnamese","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":"2017-11-14T05:19:45Z","abstract_excerpt":"This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable. We also make a comparison between state-of-the-art (SOTA) feature-based and neural network-based models. On the benchmark Vietnamese treebank (Nguyen et al., 2009), experimental results show that the pipeline strategy produces better scores of POS tagging from unsegment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04951","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":"2026-05-18T00:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xzHzV+YKbzytfrahOjmI+kBYhAqKsKUe82B30nX20uex8+GM2ql/75F1oZL+AXQOEFlN7TJkEme6v59UaRHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:48:39.431156Z"},"content_sha256":"d19c485bf843c2aaae09198fe5f677c3e934782582fdcb6691c979d1dfa7d4da","schema_version":"1.0","event_id":"sha256:d19c485bf843c2aaae09198fe5f677c3e934782582fdcb6691c979d1dfa7d4da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/bundle.json","state_url":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/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":"2026-05-27T02:48:39Z","links":{"resolver":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT","bundle":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/bundle.json","state":"https://pith.science/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDRATSV6HFAOCD5DLL3BUDGRCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QDRATSV6HFAOCD5DLL3BUDGRCT","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":"6bdb08c93ea16c50d661ee95eb2ff39f37da219f33423eaecb47595131963268","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-14T05:19:45Z","title_canon_sha256":"52818ce5c9e3cce5bffbd2a343371d9ea28cfd038d6added4f135293b3e1e652"},"schema_version":"1.0","source":{"id":"1711.04951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04951","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04951v1","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04951","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"QDRATSV6HFAO","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QDRATSV6HFAOCD5D","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QDRATSV6","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:d19c485bf843c2aaae09198fe5f677c3e934782582fdcb6691c979d1dfa7d4da","target":"graph","created_at":"2026-05-18T00:30:35Z","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":"This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable. We also make a comparison between state-of-the-art (SOTA) feature-based and neural network-based models. On the benchmark Vietnamese treebank (Nguyen et al., 2009), experimental results show that the pipeline strategy produces better scores of POS tagging from unsegment","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":"2017-11-14T05:19:45Z","title":"From Word Segmentation to POS Tagging for Vietnamese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04951","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":"sha256:8bc2d4067c0bd8c06d0972252086985383784da18d23864235c615d9ab435e8d","target":"record","created_at":"2026-05-18T00:30:35Z","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":"6bdb08c93ea16c50d661ee95eb2ff39f37da219f33423eaecb47595131963268","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-14T05:19:45Z","title_canon_sha256":"52818ce5c9e3cce5bffbd2a343371d9ea28cfd038d6added4f135293b3e1e652"},"schema_version":"1.0","source":{"id":"1711.04951","kind":"arxiv","version":1}},"canonical_sha256":"80e209cabe3940e10fa35af61a0cd114f4223fc460af77af03d21cf3c3980d64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80e209cabe3940e10fa35af61a0cd114f4223fc460af77af03d21cf3c3980d64","first_computed_at":"2026-05-18T00:30:35.344240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:35.344240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IXPYTdq1Aao6oNiQ8A2JMqN/juwncIydHrDhcPFtkQDl6aMbfG3gDTOXJJncQnpNNEhqvGG0DXv/MIYBr9lYAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:35.345133Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.04951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bc2d4067c0bd8c06d0972252086985383784da18d23864235c615d9ab435e8d","sha256:d19c485bf843c2aaae09198fe5f677c3e934782582fdcb6691c979d1dfa7d4da"],"state_sha256":"91f766656bc524ec2934a36a286c6db2cccab176ed16b16be75550000915d3a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UDr206DRJvmok4oz4FuLJjZ3eAkYb2FxLkbcInmbER8GTBjNsu4hHpQQCzmnVTNxasN2tuOB+akW3leZCDV6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:48:39.434551Z","bundle_sha256":"9e2a1429aa7a235b10bf560e4e8da8cc6b5ccdc3c7642b155b9252da4dab3880"}}