{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:G7UJG4NZTGLD5HHP7MXU6UETAV","short_pith_number":"pith:G7UJG4NZ","canonical_record":{"source":{"id":"1906.11455","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-27T06:40:42Z","cross_cats_sorted":[],"title_canon_sha256":"2a6b5d613ea263f3d6362e54f5c02ea3fc69046ebca446719379d052acd53b3c","abstract_canon_sha256":"8a653be6dcc3fbf3ba9377f27d0f47f3ca515c91c11077fb582a8f2d3e493cdb"},"schema_version":"1.0"},"canonical_sha256":"37e89371b999963e9ceffb2f4f5093054b1bf31dd87d7a2d43151ed5ef0a6c89","source":{"kind":"arxiv","id":"1906.11455","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11455","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11455v3","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11455","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"G7UJG4NZTGLD","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"G7UJG4NZTGLD5HHP","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"G7UJG4NZ","created_at":"2026-07-05T04:27:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:G7UJG4NZTGLD5HHP7MXU6UETAV","target":"record","payload":{"canonical_record":{"source":{"id":"1906.11455","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-27T06:40:42Z","cross_cats_sorted":[],"title_canon_sha256":"2a6b5d613ea263f3d6362e54f5c02ea3fc69046ebca446719379d052acd53b3c","abstract_canon_sha256":"8a653be6dcc3fbf3ba9377f27d0f47f3ca515c91c11077fb582a8f2d3e493cdb"},"schema_version":"1.0"},"canonical_sha256":"37e89371b999963e9ceffb2f4f5093054b1bf31dd87d7a2d43151ed5ef0a6c89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:02.897872Z","signature_b64":"CRPrt9MOBWaNsl35O8v4ApSdxKxhtlX6GTHAA8h0cGxZCAfMEPtQcNncMNlxt7/LDF5/gBa7IENzTCkMMCNJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37e89371b999963e9ceffb2f4f5093054b1bf31dd87d7a2d43151ed5ef0a6c89","last_reissued_at":"2026-07-05T04:27:02.897245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:02.897245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.11455","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ICp4mJI9eoC6VlV9B/Fyd2NJYF2CLVn7Ahzg1IxvByqWnWDAeCgeXK/dLOBAKQL465LnyYQOgyGb482qzdbSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:13:47.623320Z"},"content_sha256":"d7f5795865fadc055cd891ee0404ec932d5f87a2f58669fe1e93312073c950eb","schema_version":"1.0","event_id":"sha256:d7f5795865fadc055cd891ee0404ec932d5f87a2f58669fe1e93312073c950eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:G7UJG4NZTGLD5HHP7MXU6UETAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingjing Xu, Ruixuan Luo, Xuancheng Ren, Xu Sun, Yi Zhang, Zhiyuan Zhang","submitted_at":"2019-06-27T06:40:42Z","abstract_excerpt":"Chinese word segmentation (CWS) is a fundamental step of Chinese natural language processing. In this paper, we build a new toolkit, named PKUSEG, for multi-domain word segmentation. Unlike existing single-model toolkits, PKUSEG targets multi-domain word segmentation and provides separate models for different domains, such as web, medicine, and tourism. Besides, due to the lack of labeled data in many domains, we propose a domain adaptation paradigm to introduce cross-domain semantic knowledge via a translation system. Through this method, we generate synthetic data using a large amount of unl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11455","kind":"arxiv","version":3},"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/1906.11455/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":"2026-07-05T04:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQSgFyzWi+rNSTxoMHJLunQcoqFkZhRpCYR4FerSRHWD9FsIqp0/Jx/bgbrWKg7F7Dpde4MjA5OlYuHXyAY+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:13:47.623823Z"},"content_sha256":"aa1ecb0aa82c15910036f82eb56f820e84d3e2e0229cfab09dc56e2db98047d5","schema_version":"1.0","event_id":"sha256:aa1ecb0aa82c15910036f82eb56f820e84d3e2e0229cfab09dc56e2db98047d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7UJG4NZTGLD5HHP7MXU6UETAV/bundle.json","state_url":"https://pith.science/pith/G7UJG4NZTGLD5HHP7MXU6UETAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7UJG4NZTGLD5HHP7MXU6UETAV/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":"2026-08-09T06:13:47Z","links":{"resolver":"https://pith.science/pith/G7UJG4NZTGLD5HHP7MXU6UETAV","bundle":"https://pith.science/pith/G7UJG4NZTGLD5HHP7MXU6UETAV/bundle.json","state":"https://pith.science/pith/G7UJG4NZTGLD5HHP7MXU6UETAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7UJG4NZTGLD5HHP7MXU6UETAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:G7UJG4NZTGLD5HHP7MXU6UETAV","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":"8a653be6dcc3fbf3ba9377f27d0f47f3ca515c91c11077fb582a8f2d3e493cdb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-27T06:40:42Z","title_canon_sha256":"2a6b5d613ea263f3d6362e54f5c02ea3fc69046ebca446719379d052acd53b3c"},"schema_version":"1.0","source":{"id":"1906.11455","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11455","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11455v3","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11455","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"G7UJG4NZTGLD","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"G7UJG4NZTGLD5HHP","created_at":"2026-07-05T04:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"G7UJG4NZ","created_at":"2026-07-05T04:27:02Z"}],"graph_snapshots":[{"event_id":"sha256:aa1ecb0aa82c15910036f82eb56f820e84d3e2e0229cfab09dc56e2db98047d5","target":"graph","created_at":"2026-07-05T04:27:02Z","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/1906.11455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chinese word segmentation (CWS) is a fundamental step of Chinese natural language processing. In this paper, we build a new toolkit, named PKUSEG, for multi-domain word segmentation. Unlike existing single-model toolkits, PKUSEG targets multi-domain word segmentation and provides separate models for different domains, such as web, medicine, and tourism. Besides, due to the lack of labeled data in many domains, we propose a domain adaptation paradigm to introduce cross-domain semantic knowledge via a translation system. Through this method, we generate synthetic data using a large amount of unl","authors_text":"Jingjing Xu, Ruixuan Luo, Xuancheng Ren, Xu Sun, Yi Zhang, Zhiyuan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-27T06:40:42Z","title":"PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11455","kind":"arxiv","version":3},"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:d7f5795865fadc055cd891ee0404ec932d5f87a2f58669fe1e93312073c950eb","target":"record","created_at":"2026-07-05T04:27:02Z","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":"8a653be6dcc3fbf3ba9377f27d0f47f3ca515c91c11077fb582a8f2d3e493cdb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-27T06:40:42Z","title_canon_sha256":"2a6b5d613ea263f3d6362e54f5c02ea3fc69046ebca446719379d052acd53b3c"},"schema_version":"1.0","source":{"id":"1906.11455","kind":"arxiv","version":3}},"canonical_sha256":"37e89371b999963e9ceffb2f4f5093054b1bf31dd87d7a2d43151ed5ef0a6c89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37e89371b999963e9ceffb2f4f5093054b1bf31dd87d7a2d43151ed5ef0a6c89","first_computed_at":"2026-07-05T04:27:02.897245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:02.897245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CRPrt9MOBWaNsl35O8v4ApSdxKxhtlX6GTHAA8h0cGxZCAfMEPtQcNncMNlxt7/LDF5/gBa7IENzTCkMMCNJAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:02.897872Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.11455","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7f5795865fadc055cd891ee0404ec932d5f87a2f58669fe1e93312073c950eb","sha256:aa1ecb0aa82c15910036f82eb56f820e84d3e2e0229cfab09dc56e2db98047d5"],"state_sha256":"35a45326e6d1edb217f64d37ad44e618f1ae86e20ea09e1b2636c6f2a5a0d115"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aGeTYWsvulYDH8tpAHlHyaXVo9NhSirBe+lvYWbtJhh5qwzmMhvbtMtrutW2Y2befbVgs4NyDuXhvNwTTBKcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:13:47.629453Z","bundle_sha256":"9a2043e512aceecdb5932e7504343e8dac2799e9462324ced08ae4e074bf1de4"}}