{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3GXQJUNLRTXR2BO4FPYJVF5H4S","short_pith_number":"pith:3GXQJUNL","canonical_record":{"source":{"id":"1807.05849","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-11T04:51:41Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3dfb82e59f6f5f846d9934ccde95452eba302699ab4a21ad8cceacca7e19ef1f","abstract_canon_sha256":"6c4b19373360afc5ceb6bce4c3c8f8edbcd7752136b55d711dcc0f808e44d4c8"},"schema_version":"1.0"},"canonical_sha256":"d9af04d1ab8cef1d05dc2bf09a97a7e4b5e3fdaa5c0cdd4a731c5ce4626198da","source":{"kind":"arxiv","id":"1807.05849","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05849","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05849v1","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05849","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"3GXQJUNLRTXR","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3GXQJUNLRTXR2BO4","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3GXQJUNL","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3GXQJUNLRTXR2BO4FPYJVF5H4S","target":"record","payload":{"canonical_record":{"source":{"id":"1807.05849","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-11T04:51:41Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3dfb82e59f6f5f846d9934ccde95452eba302699ab4a21ad8cceacca7e19ef1f","abstract_canon_sha256":"6c4b19373360afc5ceb6bce4c3c8f8edbcd7752136b55d711dcc0f808e44d4c8"},"schema_version":"1.0"},"canonical_sha256":"d9af04d1ab8cef1d05dc2bf09a97a7e4b5e3fdaa5c0cdd4a731c5ce4626198da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:42.415615Z","signature_b64":"yeqkSlWEqc99ulR5egpRVargVS8VhhhHB0sh6SzhvhOTs8aQjBq5Kqj2+Dveh3ibQtDoxPFaYQKnkpZpyz1TAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9af04d1ab8cef1d05dc2bf09a97a7e4b5e3fdaa5c0cdd4a731c5ce4626198da","last_reissued_at":"2026-05-18T00:10:42.415094Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:42.415094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.05849","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":"2026-05-18T00:10:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPKBNn+n5pGtjBDlxbTyFhjkXNeGFDIecokGkYKRlXHl7R9ScxRYop/g2qlJZ6hlTOxc18OUBAmX6dzhGjLFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:42:02.464013Z"},"content_sha256":"6d1940a10b33a53da0f2b902a5a7d96b95f3a0c321a7a799a59333817b05cca0","schema_version":"1.0","event_id":"sha256:6d1940a10b33a53da0f2b902a5a7d96b95f3a0c321a7a799a59333817b05cca0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3GXQJUNLRTXR2BO4FPYJVF5H4S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Chinese Word Segmentation with Dictionary Knowledge","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":"2018-07-11T04:51:41Z","abstract_excerpt":"Chinese word segmentation (CWS) is an important task for Chinese NLP. Recently, many neural network based methods have been proposed for CWS. However, these methods require a large number of labeled sentences for model training, and usually cannot utilize the useful information in Chinese dictionary. In this paper, we propose two methods to exploit the dictionary information for CWS. The first one is based on pseudo labeled data generation, and the second one is based on multi-task learning. The experimental results on two benchmark datasets validate that our approach can effectively improve t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05849","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":"2026-05-18T00:10:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zMQ8WGIXJ5TWoWhwXZyq8Hh2p5MxlKFGpSxUea/0+lXEmJVMVKMmp+Td5/mUwUDkI4sftyznfYjSNe+wxOw8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:42:02.464715Z"},"content_sha256":"17980dcba762e561e02966d81ca8da881d71da996463a6ed0d3a2f5352c901dc","schema_version":"1.0","event_id":"sha256:17980dcba762e561e02966d81ca8da881d71da996463a6ed0d3a2f5352c901dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GXQJUNLRTXR2BO4FPYJVF5H4S/bundle.json","state_url":"https://pith.science/pith/3GXQJUNLRTXR2BO4FPYJVF5H4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GXQJUNLRTXR2BO4FPYJVF5H4S/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":"2026-06-11T21:42:02Z","links":{"resolver":"https://pith.science/pith/3GXQJUNLRTXR2BO4FPYJVF5H4S","bundle":"https://pith.science/pith/3GXQJUNLRTXR2BO4FPYJVF5H4S/bundle.json","state":"https://pith.science/pith/3GXQJUNLRTXR2BO4FPYJVF5H4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GXQJUNLRTXR2BO4FPYJVF5H4S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3GXQJUNLRTXR2BO4FPYJVF5H4S","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":"6c4b19373360afc5ceb6bce4c3c8f8edbcd7752136b55d711dcc0f808e44d4c8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-11T04:51:41Z","title_canon_sha256":"3dfb82e59f6f5f846d9934ccde95452eba302699ab4a21ad8cceacca7e19ef1f"},"schema_version":"1.0","source":{"id":"1807.05849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05849","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05849v1","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05849","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"3GXQJUNLRTXR","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3GXQJUNLRTXR2BO4","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3GXQJUNL","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:17980dcba762e561e02966d81ca8da881d71da996463a6ed0d3a2f5352c901dc","target":"graph","created_at":"2026-05-18T00:10:42Z","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":"Chinese word segmentation (CWS) is an important task for Chinese NLP. Recently, many neural network based methods have been proposed for CWS. However, these methods require a large number of labeled sentences for model training, and usually cannot utilize the useful information in Chinese dictionary. In this paper, we propose two methods to exploit the dictionary information for CWS. The first one is based on pseudo labeled data generation, and the second one is based on multi-task learning. The experimental results on two benchmark datasets validate that our approach can effectively improve t","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":"2018-07-11T04:51:41Z","title":"Neural Chinese Word Segmentation with Dictionary Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05849","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":"sha256:6d1940a10b33a53da0f2b902a5a7d96b95f3a0c321a7a799a59333817b05cca0","target":"record","created_at":"2026-05-18T00:10:42Z","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":"6c4b19373360afc5ceb6bce4c3c8f8edbcd7752136b55d711dcc0f808e44d4c8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-11T04:51:41Z","title_canon_sha256":"3dfb82e59f6f5f846d9934ccde95452eba302699ab4a21ad8cceacca7e19ef1f"},"schema_version":"1.0","source":{"id":"1807.05849","kind":"arxiv","version":1}},"canonical_sha256":"d9af04d1ab8cef1d05dc2bf09a97a7e4b5e3fdaa5c0cdd4a731c5ce4626198da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9af04d1ab8cef1d05dc2bf09a97a7e4b5e3fdaa5c0cdd4a731c5ce4626198da","first_computed_at":"2026-05-18T00:10:42.415094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:42.415094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yeqkSlWEqc99ulR5egpRVargVS8VhhhHB0sh6SzhvhOTs8aQjBq5Kqj2+Dveh3ibQtDoxPFaYQKnkpZpyz1TAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:42.415615Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d1940a10b33a53da0f2b902a5a7d96b95f3a0c321a7a799a59333817b05cca0","sha256:17980dcba762e561e02966d81ca8da881d71da996463a6ed0d3a2f5352c901dc"],"state_sha256":"2df72d488b4dbabc32813aa308153e9b21db546d1cc9b996a10775d0241448f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lG3muOO0bQ0Aqt7Zvk9Wk7h339laama0IHONbnYBuPVHaHpXqUlEyNfwokMO94XrBCT+DNTvGjD/+ZonYuvsBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T21:42:02.468466Z","bundle_sha256":"f25d6bbecf8411af2ae5b3e0e38f660d85f9a787d91cba23e92dfafe2027250d"}}