{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RDMBUWEDVCXYU4BR6OFPDI6SPZ","short_pith_number":"pith:RDMBUWED","canonical_record":{"source":{"id":"2006.07804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T05:19:46Z","cross_cats_sorted":[],"title_canon_sha256":"5bdce031a5ce16334e74fac8b9a10353e6ca4599d722ede2a5410f550124a58e","abstract_canon_sha256":"b5ab46f3873b56feb69e0367a0776782f6234d42f1a198761d784dd224d0a1e1"},"schema_version":"1.0"},"canonical_sha256":"88d81a5883a8af8a7031f38af1a3d27e667ab48cc9744a4893a4759fbfdd8648","source":{"kind":"arxiv","id":"2006.07804","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07804","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07804v1","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07804","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"RDMBUWEDVCXY","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"RDMBUWEDVCXYU4BR","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"RDMBUWED","created_at":"2026-07-05T01:10:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RDMBUWEDVCXYU4BR6OFPDI6SPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T05:19:46Z","cross_cats_sorted":[],"title_canon_sha256":"5bdce031a5ce16334e74fac8b9a10353e6ca4599d722ede2a5410f550124a58e","abstract_canon_sha256":"b5ab46f3873b56feb69e0367a0776782f6234d42f1a198761d784dd224d0a1e1"},"schema_version":"1.0"},"canonical_sha256":"88d81a5883a8af8a7031f38af1a3d27e667ab48cc9744a4893a4759fbfdd8648","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:03.529258Z","signature_b64":"46PxBaJ4Pzs4rxlL+mPnPTYiGACOQLgoz/vFl+pmf+Vhs28xnV3PwzMsDk5Vkel1LFRozUaUXhlpJ2DfMqDrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88d81a5883a8af8a7031f38af1a3d27e667ab48cc9744a4893a4759fbfdd8648","last_reissued_at":"2026-07-05T01:10:03.528860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:03.528860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07804","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":"2026-07-05T01:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDFiAvJvBpTW1cyRx2pdUbKGLA+3oNiFe6ysT7anXja6uPvgqBtmwVroyTxSJ+V2opW64EXUaFP9mUmPA9XWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:12:04.229442Z"},"content_sha256":"18e8f1dbd74ead0d73c1f65c61742cc55e30d33d07f4ae331434410cd13d7569","schema_version":"1.0","event_id":"sha256:18e8f1dbd74ead0d73c1f65c61742cc55e30d33d07f4ae331434410cd13d7569"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RDMBUWEDVCXYU4BR6OFPDI6SPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vietnamese Word Segmentation with SVM: Ambiguity Reduction and Suffix Capture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dang Van Thin, Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen","submitted_at":"2020-06-14T05:19:46Z","abstract_excerpt":"In this paper, we approach Vietnamese word segmentation as a binary classification by using the Support Vector Machine classifier. We inherit features from prior works such as n-gram of syllables, n-gram of syllable types, and checking conjunction of adjacent syllables in the dictionary. We propose two novel ways to feature extraction, one to reduce the overlap ambiguity and the other to increase the ability to predict unknown words containing suffixes. Different from UETsegmenter and RDRsegmenter, two state-of-the-art Vietnamese word segmentation methods, we do not employ the longest matching"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07804","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.07804/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":"2026-07-05T01:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+tAwp/x/Xz0Im1XCUWuMMDlN5pvxwBPMZfZ+orGUMt4la4iErBWxZG1sFYKdZ4UuoL8Ct0Zy3cLCi97VyvkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:12:04.229956Z"},"content_sha256":"6e42c56b01d274c62d4b7cc7461445c07d0ec6ebb49dac9b40dbb464b5a5d9dd","schema_version":"1.0","event_id":"sha256:6e42c56b01d274c62d4b7cc7461445c07d0ec6ebb49dac9b40dbb464b5a5d9dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDMBUWEDVCXYU4BR6OFPDI6SPZ/bundle.json","state_url":"https://pith.science/pith/RDMBUWEDVCXYU4BR6OFPDI6SPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDMBUWEDVCXYU4BR6OFPDI6SPZ/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":"2026-08-21T19:12:04Z","links":{"resolver":"https://pith.science/pith/RDMBUWEDVCXYU4BR6OFPDI6SPZ","bundle":"https://pith.science/pith/RDMBUWEDVCXYU4BR6OFPDI6SPZ/bundle.json","state":"https://pith.science/pith/RDMBUWEDVCXYU4BR6OFPDI6SPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDMBUWEDVCXYU4BR6OFPDI6SPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RDMBUWEDVCXYU4BR6OFPDI6SPZ","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":"b5ab46f3873b56feb69e0367a0776782f6234d42f1a198761d784dd224d0a1e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T05:19:46Z","title_canon_sha256":"5bdce031a5ce16334e74fac8b9a10353e6ca4599d722ede2a5410f550124a58e"},"schema_version":"1.0","source":{"id":"2006.07804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07804","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07804v1","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07804","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"RDMBUWEDVCXY","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"RDMBUWEDVCXYU4BR","created_at":"2026-07-05T01:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"RDMBUWED","created_at":"2026-07-05T01:10:03Z"}],"graph_snapshots":[{"event_id":"sha256:6e42c56b01d274c62d4b7cc7461445c07d0ec6ebb49dac9b40dbb464b5a5d9dd","target":"graph","created_at":"2026-07-05T01:10:03Z","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/2006.07804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we approach Vietnamese word segmentation as a binary classification by using the Support Vector Machine classifier. We inherit features from prior works such as n-gram of syllables, n-gram of syllable types, and checking conjunction of adjacent syllables in the dictionary. We propose two novel ways to feature extraction, one to reduce the overlap ambiguity and the other to increase the ability to predict unknown words containing suffixes. Different from UETsegmenter and RDRsegmenter, two state-of-the-art Vietnamese word segmentation methods, we do not employ the longest matching","authors_text":"Dang Van Thin, 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":"2020-06-14T05:19:46Z","title":"Vietnamese Word Segmentation with SVM: Ambiguity Reduction and Suffix Capture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07804","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":"sha256:18e8f1dbd74ead0d73c1f65c61742cc55e30d33d07f4ae331434410cd13d7569","target":"record","created_at":"2026-07-05T01:10:03Z","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":"b5ab46f3873b56feb69e0367a0776782f6234d42f1a198761d784dd224d0a1e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T05:19:46Z","title_canon_sha256":"5bdce031a5ce16334e74fac8b9a10353e6ca4599d722ede2a5410f550124a58e"},"schema_version":"1.0","source":{"id":"2006.07804","kind":"arxiv","version":1}},"canonical_sha256":"88d81a5883a8af8a7031f38af1a3d27e667ab48cc9744a4893a4759fbfdd8648","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88d81a5883a8af8a7031f38af1a3d27e667ab48cc9744a4893a4759fbfdd8648","first_computed_at":"2026-07-05T01:10:03.528860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:03.528860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"46PxBaJ4Pzs4rxlL+mPnPTYiGACOQLgoz/vFl+pmf+Vhs28xnV3PwzMsDk5Vkel1LFRozUaUXhlpJ2DfMqDrDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:03.529258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18e8f1dbd74ead0d73c1f65c61742cc55e30d33d07f4ae331434410cd13d7569","sha256:6e42c56b01d274c62d4b7cc7461445c07d0ec6ebb49dac9b40dbb464b5a5d9dd"],"state_sha256":"f8fb8feb8d3a412da32314f482ee05ed5a2b920f253e1038b56a594ae59a455c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GIUKTxgFr4IEYv+8bPUlXH6NiNaLGdvZC5KY4M/QKVqucbVeCnpfWG0tMu0IHR4fqOA+LU2ZVI+RSfZSVIDGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:12:04.238086Z","bundle_sha256":"6d31db1c8aadbf345ad295412d5d37bc1c7e0352d02e99c57e85ae66520d3614"}}