{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WLK2YLMQ7ATJUSFCY2AOAK5Q3A","short_pith_number":"pith:WLK2YLMQ","canonical_record":{"source":{"id":"1905.01963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-26T08:21:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a6fef03333e6d92c4a7ed0b14eed3d3786edf4becbcb79c819b56bb390ae4b3c","abstract_canon_sha256":"a23f1ffffe70949d331ffe5b2ca4d586a39678151148d675938cd71351bed577"},"schema_version":"1.0"},"canonical_sha256":"b2d5ac2d90f8269a48a2c680e02bb0d8004b9b42130d549ec700b02ff47cd5d8","source":{"kind":"arxiv","id":"1905.01963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01963","created_at":"2026-05-17T23:46:56Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01963v1","created_at":"2026-05-17T23:46:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01963","created_at":"2026-05-17T23:46:56Z"},{"alias_kind":"pith_short_12","alias_value":"WLK2YLMQ7ATJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WLK2YLMQ7ATJUSFC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WLK2YLMQ","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WLK2YLMQ7ATJUSFCY2AOAK5Q3A","target":"record","payload":{"canonical_record":{"source":{"id":"1905.01963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-26T08:21:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a6fef03333e6d92c4a7ed0b14eed3d3786edf4becbcb79c819b56bb390ae4b3c","abstract_canon_sha256":"a23f1ffffe70949d331ffe5b2ca4d586a39678151148d675938cd71351bed577"},"schema_version":"1.0"},"canonical_sha256":"b2d5ac2d90f8269a48a2c680e02bb0d8004b9b42130d549ec700b02ff47cd5d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:56.883475Z","signature_b64":"+DjbhjjUfdOY/zOkIX8qQt7MzM1FDBVp8fQTu3l0LKEGKuojDbgbMw+Nt5xRQT8a/2VabZCacqBR+8EjtrYPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2d5ac2d90f8269a48a2c680e02bb0d8004b9b42130d549ec700b02ff47cd5d8","last_reissued_at":"2026-05-17T23:46:56.882940Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:56.882940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.01963","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":"2026-05-17T23:46:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJLipRZXc2sHjKT2BK0h+9Ehm1+r6q5jln0v2+PeZULVaJir3tOqJnobP4wz6yt0+UZmDjqAVJRC7t0wzRxHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:11:25.552240Z"},"content_sha256":"c9265f622f064fd10514460b023aba5b81b3f9058a47ba150e43549a86e987f6","schema_version":"1.0","event_id":"sha256:c9265f622f064fd10514460b023aba5b81b3f9058a47ba150e43549a86e987f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WLK2YLMQ7ATJUSFCY2AOAK5Q3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Chuhan Wu, Fangzhao Wu, Junxin Liu, Xing Xie, Yongfeng Huang","submitted_at":"2019-04-26T08:21:08Z","abstract_excerpt":"Existing methods for CWS usually rely on a large number of labeled sentences to train word segmentation models, which are expensive and time-consuming to annotate. Luckily, the unlabeled data is usually easy to collect and many high-quality Chinese lexicons are off-the-shelf, both of which can provide useful information for CWS. In this paper, we propose a neural approach for Chinese word segmentation which can exploit both lexicon and unlabeled data. Our approach is based on a variant of posterior regularization algorithm, and the unlabeled data and lexicon are incorporated into model trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01963","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":"2026-05-17T23:46:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6iIQOxSHYotYCWVTYt59RabXmVbunOb5zakRlQfeXFPWxmzXlbQ9pXs5dFtX772rcLGmqfNjJ3yjcLy32QO5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:11:25.552619Z"},"content_sha256":"6d9ba59f78a864e243cd407a72f0141add40be3650889badbd3a29470a859f4d","schema_version":"1.0","event_id":"sha256:6d9ba59f78a864e243cd407a72f0141add40be3650889badbd3a29470a859f4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLK2YLMQ7ATJUSFCY2AOAK5Q3A/bundle.json","state_url":"https://pith.science/pith/WLK2YLMQ7ATJUSFCY2AOAK5Q3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLK2YLMQ7ATJUSFCY2AOAK5Q3A/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":"2026-06-12T06:11:25Z","links":{"resolver":"https://pith.science/pith/WLK2YLMQ7ATJUSFCY2AOAK5Q3A","bundle":"https://pith.science/pith/WLK2YLMQ7ATJUSFCY2AOAK5Q3A/bundle.json","state":"https://pith.science/pith/WLK2YLMQ7ATJUSFCY2AOAK5Q3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLK2YLMQ7ATJUSFCY2AOAK5Q3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WLK2YLMQ7ATJUSFCY2AOAK5Q3A","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":"a23f1ffffe70949d331ffe5b2ca4d586a39678151148d675938cd71351bed577","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-26T08:21:08Z","title_canon_sha256":"a6fef03333e6d92c4a7ed0b14eed3d3786edf4becbcb79c819b56bb390ae4b3c"},"schema_version":"1.0","source":{"id":"1905.01963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01963","created_at":"2026-05-17T23:46:56Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01963v1","created_at":"2026-05-17T23:46:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01963","created_at":"2026-05-17T23:46:56Z"},{"alias_kind":"pith_short_12","alias_value":"WLK2YLMQ7ATJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WLK2YLMQ7ATJUSFC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WLK2YLMQ","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:6d9ba59f78a864e243cd407a72f0141add40be3650889badbd3a29470a859f4d","target":"graph","created_at":"2026-05-17T23:46:56Z","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":"Existing methods for CWS usually rely on a large number of labeled sentences to train word segmentation models, which are expensive and time-consuming to annotate. Luckily, the unlabeled data is usually easy to collect and many high-quality Chinese lexicons are off-the-shelf, both of which can provide useful information for CWS. In this paper, we propose a neural approach for Chinese word segmentation which can exploit both lexicon and unlabeled data. Our approach is based on a variant of posterior regularization algorithm, and the unlabeled data and lexicon are incorporated into model trainin","authors_text":"Chuhan Wu, Fangzhao Wu, Junxin Liu, Xing Xie, Yongfeng Huang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-26T08:21:08Z","title":"Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01963","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:c9265f622f064fd10514460b023aba5b81b3f9058a47ba150e43549a86e987f6","target":"record","created_at":"2026-05-17T23:46:56Z","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":"a23f1ffffe70949d331ffe5b2ca4d586a39678151148d675938cd71351bed577","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-26T08:21:08Z","title_canon_sha256":"a6fef03333e6d92c4a7ed0b14eed3d3786edf4becbcb79c819b56bb390ae4b3c"},"schema_version":"1.0","source":{"id":"1905.01963","kind":"arxiv","version":1}},"canonical_sha256":"b2d5ac2d90f8269a48a2c680e02bb0d8004b9b42130d549ec700b02ff47cd5d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2d5ac2d90f8269a48a2c680e02bb0d8004b9b42130d549ec700b02ff47cd5d8","first_computed_at":"2026-05-17T23:46:56.882940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:56.882940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+DjbhjjUfdOY/zOkIX8qQt7MzM1FDBVp8fQTu3l0LKEGKuojDbgbMw+Nt5xRQT8a/2VabZCacqBR+8EjtrYPAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:56.883475Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9265f622f064fd10514460b023aba5b81b3f9058a47ba150e43549a86e987f6","sha256:6d9ba59f78a864e243cd407a72f0141add40be3650889badbd3a29470a859f4d"],"state_sha256":"91a36ec09e21e2852b50096af37224b0346329e17b5ed555d4c12391a19256ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ilrMx2GFmYc8A5H2auViwuBWxGEzea5rU5udg9d/Y0/PRvM0091dnNBvZ1/e+5nK3+blVNP4MIwc7xZITR8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T06:11:25.555067Z","bundle_sha256":"df21e7e66f42981d26cc46da11414bccf12037fe77a18ebdd3dc5acb995a5493"}}