{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MYYUX34P5YYMH6QR57NNPBPKZP","short_pith_number":"pith:MYYUX34P","canonical_record":{"source":{"id":"2503.23091","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-29T14:24:02Z","cross_cats_sorted":[],"title_canon_sha256":"b6dc6249fef7df104cb127ab61b087190a008c073e0126ba5f03e909fce3eaea","abstract_canon_sha256":"438a16b13be4bc2a164a90997ae23da23c124c32dcaa4e9a9c9e9e20aa0fba1d"},"schema_version":"1.0"},"canonical_sha256":"66314bef8fee30c3fa11efdad785eacbc8d72b31d9b235ae1d62bd275e2b6de4","source":{"kind":"arxiv","id":"2503.23091","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23091","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23091v2","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23091","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"pith_short_12","alias_value":"MYYUX34P5YYM","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"pith_short_16","alias_value":"MYYUX34P5YYMH6QR","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"pith_short_8","alias_value":"MYYUX34P","created_at":"2026-07-05T11:32:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MYYUX34P5YYMH6QR57NNPBPKZP","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23091","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-29T14:24:02Z","cross_cats_sorted":[],"title_canon_sha256":"b6dc6249fef7df104cb127ab61b087190a008c073e0126ba5f03e909fce3eaea","abstract_canon_sha256":"438a16b13be4bc2a164a90997ae23da23c124c32dcaa4e9a9c9e9e20aa0fba1d"},"schema_version":"1.0"},"canonical_sha256":"66314bef8fee30c3fa11efdad785eacbc8d72b31d9b235ae1d62bd275e2b6de4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:27.141847Z","signature_b64":"JlTpAlcSf2Uy24TP24WIlBoJWQKfEBcpFeeUn+9tjrMyg15HCedO+js79YbTU3FmSDNvMImM+B0Z4vCkpEivBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66314bef8fee30c3fa11efdad785eacbc8d72b31d9b235ae1d62bd275e2b6de4","last_reissued_at":"2026-07-05T11:32:27.141352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:27.141352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23091","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Ny2a08NwXLO02PYr49XRDNwjXobzozrmV2uVV8MATPe0Iri1EfNpDnilVskChxhBU8SGsfqpL6Sj5DLqjTSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:48:12.732952Z"},"content_sha256":"3a1ec4c01d19791ffb9dc5d48453d949143d5358805bb9f6758621426fb6dfd7","schema_version":"1.0","event_id":"sha256:3a1ec4c01d19791ffb9dc5d48453d949143d5358805bb9f6758621426fb6dfd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MYYUX34P5YYMH6QR57NNPBPKZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parsing Through Boundaries in Chinese Word Segmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ai Ka Lee, Amandisa Cady, Changbing Yang, Cindy Zhang, Eunkyul Leah Jo, Haihua Pan, Jungyeul Park, Yige Chen, Zejiao Zeng, Zelong Li","submitted_at":"2025-03-29T14:24:02Z","abstract_excerpt":"Chinese word segmentation is a foundational task in natural language processing (NLP), with far-reaching effects on syntactic analysis. Unlike alphabetic languages like English, Chinese lacks explicit word boundaries, making segmentation both necessary and inherently ambiguous. This study highlights the intricate relationship between word segmentation and syntactic parsing, providing a clearer understanding of how different segmentation strategies shape dependency structures in Chinese. Focusing on the Chinese GSD treebank, we analyze multiple word boundary schemes, each reflecting distinct li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23091","kind":"arxiv","version":2},"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/2503.23091/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":"2026-07-05T11:32:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BCsxRB3LJEtP6JtvU55MIfUp8u8vvUV5hwZWPzZUzKWn3oYG6qB5VAbJYw+DJc4YS93HFom0mDGK58UTek8jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:48:12.733292Z"},"content_sha256":"b875b8c598adca04697eeb0ff4dd56e625fcfb31838395dc68c48ee8e605918a","schema_version":"1.0","event_id":"sha256:b875b8c598adca04697eeb0ff4dd56e625fcfb31838395dc68c48ee8e605918a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYYUX34P5YYMH6QR57NNPBPKZP/bundle.json","state_url":"https://pith.science/pith/MYYUX34P5YYMH6QR57NNPBPKZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYYUX34P5YYMH6QR57NNPBPKZP/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":"2026-08-21T17:48:12Z","links":{"resolver":"https://pith.science/pith/MYYUX34P5YYMH6QR57NNPBPKZP","bundle":"https://pith.science/pith/MYYUX34P5YYMH6QR57NNPBPKZP/bundle.json","state":"https://pith.science/pith/MYYUX34P5YYMH6QR57NNPBPKZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYYUX34P5YYMH6QR57NNPBPKZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MYYUX34P5YYMH6QR57NNPBPKZP","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":"438a16b13be4bc2a164a90997ae23da23c124c32dcaa4e9a9c9e9e20aa0fba1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-29T14:24:02Z","title_canon_sha256":"b6dc6249fef7df104cb127ab61b087190a008c073e0126ba5f03e909fce3eaea"},"schema_version":"1.0","source":{"id":"2503.23091","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23091","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23091v2","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23091","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"pith_short_12","alias_value":"MYYUX34P5YYM","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"pith_short_16","alias_value":"MYYUX34P5YYMH6QR","created_at":"2026-07-05T11:32:27Z"},{"alias_kind":"pith_short_8","alias_value":"MYYUX34P","created_at":"2026-07-05T11:32:27Z"}],"graph_snapshots":[{"event_id":"sha256:b875b8c598adca04697eeb0ff4dd56e625fcfb31838395dc68c48ee8e605918a","target":"graph","created_at":"2026-07-05T11:32:27Z","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/2503.23091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chinese word segmentation is a foundational task in natural language processing (NLP), with far-reaching effects on syntactic analysis. Unlike alphabetic languages like English, Chinese lacks explicit word boundaries, making segmentation both necessary and inherently ambiguous. This study highlights the intricate relationship between word segmentation and syntactic parsing, providing a clearer understanding of how different segmentation strategies shape dependency structures in Chinese. Focusing on the Chinese GSD treebank, we analyze multiple word boundary schemes, each reflecting distinct li","authors_text":"Ai Ka Lee, Amandisa Cady, Changbing Yang, Cindy Zhang, Eunkyul Leah Jo, Haihua Pan, Jungyeul Park, Yige Chen, Zejiao Zeng, Zelong Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-29T14:24:02Z","title":"Parsing Through Boundaries in Chinese Word Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23091","kind":"arxiv","version":2},"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":"sha256:3a1ec4c01d19791ffb9dc5d48453d949143d5358805bb9f6758621426fb6dfd7","target":"record","created_at":"2026-07-05T11:32:27Z","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":"438a16b13be4bc2a164a90997ae23da23c124c32dcaa4e9a9c9e9e20aa0fba1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-29T14:24:02Z","title_canon_sha256":"b6dc6249fef7df104cb127ab61b087190a008c073e0126ba5f03e909fce3eaea"},"schema_version":"1.0","source":{"id":"2503.23091","kind":"arxiv","version":2}},"canonical_sha256":"66314bef8fee30c3fa11efdad785eacbc8d72b31d9b235ae1d62bd275e2b6de4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66314bef8fee30c3fa11efdad785eacbc8d72b31d9b235ae1d62bd275e2b6de4","first_computed_at":"2026-07-05T11:32:27.141352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:27.141352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JlTpAlcSf2Uy24TP24WIlBoJWQKfEBcpFeeUn+9tjrMyg15HCedO+js79YbTU3FmSDNvMImM+B0Z4vCkpEivBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:27.141847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23091","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a1ec4c01d19791ffb9dc5d48453d949143d5358805bb9f6758621426fb6dfd7","sha256:b875b8c598adca04697eeb0ff4dd56e625fcfb31838395dc68c48ee8e605918a"],"state_sha256":"6dddbf36c3d7df7c8f93ee65735e0c8fc9b177fad39c8a9c3a698cc892d0e3f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEvMpHWh5Ayf1EZMY4QT97qmtiWcwFVf6iqrRV26dijSuZeYH0TJPHVyq41xdHEyBpsmWNkJRheJWn+mi1TDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:48:12.736654Z","bundle_sha256":"9d432136dfea3f5a299189035be2f5f4d6e704499219083b58f5b8d1ecb31aca"}}