{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UOCJYTDTHJXPEJ4J4RFJXTTWCX","short_pith_number":"pith:UOCJYTDT","canonical_record":{"source":{"id":"1804.01778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T11:02:38Z","cross_cats_sorted":[],"title_canon_sha256":"58680d5a07953e7e8fd0407322114b79a2f6cb97e0cd648b1ca5421b281bfe2b","abstract_canon_sha256":"2f8126253cbbac0b6113586bcf9521a72228701f9e339ce917b98c7df7eab944"},"schema_version":"1.0"},"canonical_sha256":"a3849c4c733a6ef22789e44a9bce7615d0416044b2f9879d913759031f4c571f","source":{"kind":"arxiv","id":"1804.01778","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01778","created_at":"2026-05-18T00:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01778v1","created_at":"2026-05-18T00:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01778","created_at":"2026-05-18T00:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"UOCJYTDTHJXP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UOCJYTDTHJXPEJ4J","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UOCJYTDT","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UOCJYTDTHJXPEJ4J4RFJXTTWCX","target":"record","payload":{"canonical_record":{"source":{"id":"1804.01778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T11:02:38Z","cross_cats_sorted":[],"title_canon_sha256":"58680d5a07953e7e8fd0407322114b79a2f6cb97e0cd648b1ca5421b281bfe2b","abstract_canon_sha256":"2f8126253cbbac0b6113586bcf9521a72228701f9e339ce917b98c7df7eab944"},"schema_version":"1.0"},"canonical_sha256":"a3849c4c733a6ef22789e44a9bce7615d0416044b2f9879d913759031f4c571f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:09.987224Z","signature_b64":"yB1BfVgwJr8l2movfLVUPCGBBnAKgQxsCTYCNc/BOZsNUyrNiJNATaxAjqeCFW1eILEvONlgzRb0X+oqRAn0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3849c4c733a6ef22789e44a9bce7615d0416044b2f9879d913759031f4c571f","last_reissued_at":"2026-05-18T00:19:09.986622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:09.986622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.01778","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":"2026-05-18T00:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k83J3w6zpys1VGkz6q8POje978wuNEre/cUfHLaYiwG1yxGiYC9Rj+IiDx+P8u9sYPTsGTp0u/B8etIJtC1lCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:40:51.428505Z"},"content_sha256":"bb9bdb7e5ed685d530fb419b0f53c3cd5f351d126e6dc11cfdc23817060a79f4","schema_version":"1.0","event_id":"sha256:bb9bdb7e5ed685d530fb419b0f53c3cd5f351d126e6dc11cfdc23817060a79f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UOCJYTDTHJXPEJ4J4RFJXTTWCX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Segmentation as Graph Partition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sheng Yu, Yuanhao Liu","submitted_at":"2018-04-05T11:02:38Z","abstract_excerpt":"We propose a new approach to the Chinese word segmentation problem that considers the sentence as an undirected graph, whose nodes are the characters. One can use various techniques to compute the edge weights that measure the connection strength between characters. Spectral graph partition algorithms are used to group the characters and achieve word segmentation. We follow the graph partition approach and design several unsupervised algorithms, and we show their inspiring segmentation results on two corpora: (1) electronic health records in Chinese, and (2) benchmark data from the Second Inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01778","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":"2026-05-18T00:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yJZPVJJ6w+3CBVJVF4Q35oayJNcKlgiM/mZegyn/STN43FibwpNPPATx42hCoeBGSUOTvjh944nQSUss0G9xCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:40:51.429328Z"},"content_sha256":"6264ca59b7fc7f6ebfb7b52af80c23292c495f071f8056d95b077e66149b06f9","schema_version":"1.0","event_id":"sha256:6264ca59b7fc7f6ebfb7b52af80c23292c495f071f8056d95b077e66149b06f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOCJYTDTHJXPEJ4J4RFJXTTWCX/bundle.json","state_url":"https://pith.science/pith/UOCJYTDTHJXPEJ4J4RFJXTTWCX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOCJYTDTHJXPEJ4J4RFJXTTWCX/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":"2026-06-09T08:40:51Z","links":{"resolver":"https://pith.science/pith/UOCJYTDTHJXPEJ4J4RFJXTTWCX","bundle":"https://pith.science/pith/UOCJYTDTHJXPEJ4J4RFJXTTWCX/bundle.json","state":"https://pith.science/pith/UOCJYTDTHJXPEJ4J4RFJXTTWCX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOCJYTDTHJXPEJ4J4RFJXTTWCX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UOCJYTDTHJXPEJ4J4RFJXTTWCX","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":"2f8126253cbbac0b6113586bcf9521a72228701f9e339ce917b98c7df7eab944","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T11:02:38Z","title_canon_sha256":"58680d5a07953e7e8fd0407322114b79a2f6cb97e0cd648b1ca5421b281bfe2b"},"schema_version":"1.0","source":{"id":"1804.01778","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01778","created_at":"2026-05-18T00:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01778v1","created_at":"2026-05-18T00:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01778","created_at":"2026-05-18T00:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"UOCJYTDTHJXP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UOCJYTDTHJXPEJ4J","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UOCJYTDT","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:6264ca59b7fc7f6ebfb7b52af80c23292c495f071f8056d95b077e66149b06f9","target":"graph","created_at":"2026-05-18T00:19:09Z","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":"We propose a new approach to the Chinese word segmentation problem that considers the sentence as an undirected graph, whose nodes are the characters. One can use various techniques to compute the edge weights that measure the connection strength between characters. Spectral graph partition algorithms are used to group the characters and achieve word segmentation. We follow the graph partition approach and design several unsupervised algorithms, and we show their inspiring segmentation results on two corpora: (1) electronic health records in Chinese, and (2) benchmark data from the Second Inte","authors_text":"Sheng Yu, Yuanhao Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T11:02:38Z","title":"Word Segmentation as Graph Partition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01778","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:bb9bdb7e5ed685d530fb419b0f53c3cd5f351d126e6dc11cfdc23817060a79f4","target":"record","created_at":"2026-05-18T00:19:09Z","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":"2f8126253cbbac0b6113586bcf9521a72228701f9e339ce917b98c7df7eab944","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T11:02:38Z","title_canon_sha256":"58680d5a07953e7e8fd0407322114b79a2f6cb97e0cd648b1ca5421b281bfe2b"},"schema_version":"1.0","source":{"id":"1804.01778","kind":"arxiv","version":1}},"canonical_sha256":"a3849c4c733a6ef22789e44a9bce7615d0416044b2f9879d913759031f4c571f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3849c4c733a6ef22789e44a9bce7615d0416044b2f9879d913759031f4c571f","first_computed_at":"2026-05-18T00:19:09.986622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:09.986622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yB1BfVgwJr8l2movfLVUPCGBBnAKgQxsCTYCNc/BOZsNUyrNiJNATaxAjqeCFW1eILEvONlgzRb0X+oqRAn0CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:09.987224Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01778","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb9bdb7e5ed685d530fb419b0f53c3cd5f351d126e6dc11cfdc23817060a79f4","sha256:6264ca59b7fc7f6ebfb7b52af80c23292c495f071f8056d95b077e66149b06f9"],"state_sha256":"fa9cccaf2059ed06bbad5a68aa3687968261d20cdc862b1ae600f187258e26da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3G1OB6XgoZA9Te9CvoFhxE9P3JeZJ19chzjNVvyQY9mc77SGgIPV0hHZfycL1SdBZ/fiz+PseGfjCUiYBuFJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T08:40:51.432872Z","bundle_sha256":"31061661f037b79f527c264e48f6ae7a0c76d9678d9ff231fdfd0eb35383bcd0"}}