{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QIUH6RSMW6IGQZ2YHBCVH5CVW4","short_pith_number":"pith:QIUH6RSM","canonical_record":{"source":{"id":"1901.06079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-18T04:16:56Z","cross_cats_sorted":[],"title_canon_sha256":"a51bc66febd406410b288f087e0f461196982cda3749a099c1f7905f7f13fc7e","abstract_canon_sha256":"acfabffaea9b42a4613f1522e93851e672916f7b238d55b5f82807962b684f5b"},"schema_version":"1.0"},"canonical_sha256":"82287f464cb790686758384553f455b7080520b56b4e6e8cc47f902950fe7a43","source":{"kind":"arxiv","id":"1901.06079","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.06079","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"1901.06079v1","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.06079","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"QIUH6RSMW6IG","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QIUH6RSMW6IGQZ2Y","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QIUH6RSM","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QIUH6RSMW6IGQZ2YHBCVH5CVW4","target":"record","payload":{"canonical_record":{"source":{"id":"1901.06079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-18T04:16:56Z","cross_cats_sorted":[],"title_canon_sha256":"a51bc66febd406410b288f087e0f461196982cda3749a099c1f7905f7f13fc7e","abstract_canon_sha256":"acfabffaea9b42a4613f1522e93851e672916f7b238d55b5f82807962b684f5b"},"schema_version":"1.0"},"canonical_sha256":"82287f464cb790686758384553f455b7080520b56b4e6e8cc47f902950fe7a43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:04.638168Z","signature_b64":"qnaFjZKxmDyWEhSpMG/EbXpZJSFJLAim9gtUWzqjkK3Tr4guymE3Gzo4V4zOJFm3irgQ97E05iWE/2YNYjmEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82287f464cb790686758384553f455b7080520b56b4e6e8cc47f902950fe7a43","last_reissued_at":"2026-05-17T23:56:04.637551Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:04.637551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.06079","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":"2026-05-17T23:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xrSfzdGYT1gzBMb3TpluRgKkHAbys9OPquOMXOLYOjE4r+8Z/sFepfyHgJjtMP4ivkvU6dCfl7unRdx2PCW0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:35:40.970355Z"},"content_sha256":"f0684d920075b1b7af4ffa2e2b0067b4b76dea146377d490527d7b04394bec07","schema_version":"1.0","event_id":"sha256:f0684d920075b1b7af4ffa2e2b0067b4b76dea146377d490527d7b04394bec07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QIUH6RSMW6IGQZ2YHBCVH5CVW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chinese Word Segmentation: Another Decade Review (2007-2017)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changning Huang, Chunyu Kit, Deng Cai, Hai Zhao","submitted_at":"2019-01-18T04:16:56Z","abstract_excerpt":"This paper reviews the development of Chinese word segmentation (CWS) in the most recent decade, 2007-2017. Special attention was paid to the deep learning technologies that has already permeated into most areas of natural language processing (NLP). The basic view we have arrived at is that compared to traditional supervised learning methods, neural network based methods have not shown any superior performance. The most critical challenge still lies on balancing of recognition of in-vocabulary (IV) and out-of-vocabulary (OOV) words. However, as neural models have potentials to capture the esse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.06079","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":"2026-05-17T23:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2MCxTGOtREcyWHifs9RUwGM/qzI7Kg8pDsQN0a8CLP+WtiOJiaTzTBpivD9qbmAEyrl3TX47NHdKuVn8RGcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:35:40.970746Z"},"content_sha256":"7c8c3d2a04d54b64080162b7e356e314a3f59a82bc4a433d3cc5c7704c9d289f","schema_version":"1.0","event_id":"sha256:7c8c3d2a04d54b64080162b7e356e314a3f59a82bc4a433d3cc5c7704c9d289f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QIUH6RSMW6IGQZ2YHBCVH5CVW4/bundle.json","state_url":"https://pith.science/pith/QIUH6RSMW6IGQZ2YHBCVH5CVW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QIUH6RSMW6IGQZ2YHBCVH5CVW4/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":"2026-06-05T15:35:40Z","links":{"resolver":"https://pith.science/pith/QIUH6RSMW6IGQZ2YHBCVH5CVW4","bundle":"https://pith.science/pith/QIUH6RSMW6IGQZ2YHBCVH5CVW4/bundle.json","state":"https://pith.science/pith/QIUH6RSMW6IGQZ2YHBCVH5CVW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QIUH6RSMW6IGQZ2YHBCVH5CVW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QIUH6RSMW6IGQZ2YHBCVH5CVW4","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":"acfabffaea9b42a4613f1522e93851e672916f7b238d55b5f82807962b684f5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-18T04:16:56Z","title_canon_sha256":"a51bc66febd406410b288f087e0f461196982cda3749a099c1f7905f7f13fc7e"},"schema_version":"1.0","source":{"id":"1901.06079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.06079","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"1901.06079v1","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.06079","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"QIUH6RSMW6IG","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QIUH6RSMW6IGQZ2Y","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QIUH6RSM","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:7c8c3d2a04d54b64080162b7e356e314a3f59a82bc4a433d3cc5c7704c9d289f","target":"graph","created_at":"2026-05-17T23:56:04Z","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 reviews the development of Chinese word segmentation (CWS) in the most recent decade, 2007-2017. Special attention was paid to the deep learning technologies that has already permeated into most areas of natural language processing (NLP). The basic view we have arrived at is that compared to traditional supervised learning methods, neural network based methods have not shown any superior performance. The most critical challenge still lies on balancing of recognition of in-vocabulary (IV) and out-of-vocabulary (OOV) words. However, as neural models have potentials to capture the esse","authors_text":"Changning Huang, Chunyu Kit, Deng Cai, Hai Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-18T04:16:56Z","title":"Chinese Word Segmentation: Another Decade Review (2007-2017)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.06079","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:f0684d920075b1b7af4ffa2e2b0067b4b76dea146377d490527d7b04394bec07","target":"record","created_at":"2026-05-17T23:56:04Z","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":"acfabffaea9b42a4613f1522e93851e672916f7b238d55b5f82807962b684f5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-18T04:16:56Z","title_canon_sha256":"a51bc66febd406410b288f087e0f461196982cda3749a099c1f7905f7f13fc7e"},"schema_version":"1.0","source":{"id":"1901.06079","kind":"arxiv","version":1}},"canonical_sha256":"82287f464cb790686758384553f455b7080520b56b4e6e8cc47f902950fe7a43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82287f464cb790686758384553f455b7080520b56b4e6e8cc47f902950fe7a43","first_computed_at":"2026-05-17T23:56:04.637551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:04.637551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qnaFjZKxmDyWEhSpMG/EbXpZJSFJLAim9gtUWzqjkK3Tr4guymE3Gzo4V4zOJFm3irgQ97E05iWE/2YNYjmEBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:04.638168Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.06079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0684d920075b1b7af4ffa2e2b0067b4b76dea146377d490527d7b04394bec07","sha256:7c8c3d2a04d54b64080162b7e356e314a3f59a82bc4a433d3cc5c7704c9d289f"],"state_sha256":"f499ce14adb87f4a51303e88d40fdcac1e48f6883e893d43f108017bb2efd7d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tDCneXUw2raAxs+LnE1F/0ayHenYJ2uj5V2qg0Kb5qJdbOOSOI9TPFDmoFJDlSsNBrv+0iwPhdpcx+DzD+sNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T15:35:40.972948Z","bundle_sha256":"437bb4671ded97b8cb6fd0b2d5c746015f756a05e9bb696801469678761b8205"}}