{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KQEYSGJEUUPNXBWG2PC7THRRTT","short_pith_number":"pith:KQEYSGJE","canonical_record":{"source":{"id":"2505.19631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T07:48:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1dc396e0b6493d96edfb483d4c9b3a391f2f566a57c7868ece1a56830e29a466","abstract_canon_sha256":"4b8c26bfec0ba450a59a317f7ac5748a9eece6eb60d441eab5f534e06f28bdde"},"schema_version":"1.0"},"canonical_sha256":"5409891924a51edb86c6d3c5f99e319ce111a786a52a65e80cc6d5fb580a03b2","source":{"kind":"arxiv","id":"2505.19631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19631","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19631v1","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19631","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"KQEYSGJEUUPN","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"KQEYSGJEUUPNXBWG","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"KQEYSGJE","created_at":"2026-07-05T11:09:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KQEYSGJEUUPNXBWG2PC7THRRTT","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T07:48:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1dc396e0b6493d96edfb483d4c9b3a391f2f566a57c7868ece1a56830e29a466","abstract_canon_sha256":"4b8c26bfec0ba450a59a317f7ac5748a9eece6eb60d441eab5f534e06f28bdde"},"schema_version":"1.0"},"canonical_sha256":"5409891924a51edb86c6d3c5f99e319ce111a786a52a65e80cc6d5fb580a03b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:33.806106Z","signature_b64":"BO5ern+Gh9CiTR5pFG559Gr4/8GJwiQx5VxIqZP1WzbQBeic5igO2IQfLhr90ax4bqAhDcKX7uX9FBF7Unt5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5409891924a51edb86c6d3c5f99e319ce111a786a52a65e80cc6d5fb580a03b2","last_reissued_at":"2026-07-05T11:09:33.805591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:33.805591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19631","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":"2026-07-05T11:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HI3vchuFxaVa7xdaVj3tBOhIWQ1rdh8dNEdC7Xq4jwTqPnXhEBnTuple3+npn+HFkYZ+Fh9zhvjSDQDR5X+FDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:15:06.660943Z"},"content_sha256":"2c8841263827ab4e677261dd89b49750a3f493e5451c00781b87d2be59cbf37d","schema_version":"1.0","event_id":"sha256:2c8841263827ab4e677261dd89b49750a3f493e5451c00781b87d2be59cbf37d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KQEYSGJEUUPNXBWG2PC7THRRTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Liqi He, Zihong Zhang, Zuchao Li","submitted_at":"2025-05-26T07:48:15Z","abstract_excerpt":"Word segmentation stands as a cornerstone of Natural Language Processing (NLP). Based on the concept of \"comprehend first, segment later\", we propose a new framework to explore the limit of unsupervised word segmentation with Large Language Models (LLMs) and evaluate the semantic understanding capabilities of LLMs based on word segmentation. We employ current mainstream LLMs to perform word segmentation across multiple languages to assess LLMs' \"comprehension\". Our findings reveal that LLMs are capable of following simple prompts to segment raw text into words. There is a trend suggesting that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19631","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.19631/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":"2026-07-05T11:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QfFNowapJMtIMZbVZ/2jWYsFEMAPcX/Q2ZUPHBz5zEk3ziK09P6Ap6hO98p//CBGwLqMi/VlC+qfv2UJtKLYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:15:06.661731Z"},"content_sha256":"9551fd8b2d85e7536165d3d133ac2aa9600d51ac347c062439e0b0621ff0a73d","schema_version":"1.0","event_id":"sha256:9551fd8b2d85e7536165d3d133ac2aa9600d51ac347c062439e0b0621ff0a73d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQEYSGJEUUPNXBWG2PC7THRRTT/bundle.json","state_url":"https://pith.science/pith/KQEYSGJEUUPNXBWG2PC7THRRTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQEYSGJEUUPNXBWG2PC7THRRTT/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":"2026-08-08T14:15:06Z","links":{"resolver":"https://pith.science/pith/KQEYSGJEUUPNXBWG2PC7THRRTT","bundle":"https://pith.science/pith/KQEYSGJEUUPNXBWG2PC7THRRTT/bundle.json","state":"https://pith.science/pith/KQEYSGJEUUPNXBWG2PC7THRRTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQEYSGJEUUPNXBWG2PC7THRRTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KQEYSGJEUUPNXBWG2PC7THRRTT","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":"4b8c26bfec0ba450a59a317f7ac5748a9eece6eb60d441eab5f534e06f28bdde","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T07:48:15Z","title_canon_sha256":"1dc396e0b6493d96edfb483d4c9b3a391f2f566a57c7868ece1a56830e29a466"},"schema_version":"1.0","source":{"id":"2505.19631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19631","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19631v1","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19631","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"KQEYSGJEUUPN","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"KQEYSGJEUUPNXBWG","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"KQEYSGJE","created_at":"2026-07-05T11:09:33Z"}],"graph_snapshots":[{"event_id":"sha256:9551fd8b2d85e7536165d3d133ac2aa9600d51ac347c062439e0b0621ff0a73d","target":"graph","created_at":"2026-07-05T11:09:33Z","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/2505.19631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word segmentation stands as a cornerstone of Natural Language Processing (NLP). Based on the concept of \"comprehend first, segment later\", we propose a new framework to explore the limit of unsupervised word segmentation with Large Language Models (LLMs) and evaluate the semantic understanding capabilities of LLMs based on word segmentation. We employ current mainstream LLMs to perform word segmentation across multiple languages to assess LLMs' \"comprehension\". Our findings reveal that LLMs are capable of following simple prompts to segment raw text into words. There is a trend suggesting that","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Liqi He, Zihong Zhang, Zuchao Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T07:48:15Z","title":"Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19631","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":"sha256:2c8841263827ab4e677261dd89b49750a3f493e5451c00781b87d2be59cbf37d","target":"record","created_at":"2026-07-05T11:09:33Z","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":"4b8c26bfec0ba450a59a317f7ac5748a9eece6eb60d441eab5f534e06f28bdde","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T07:48:15Z","title_canon_sha256":"1dc396e0b6493d96edfb483d4c9b3a391f2f566a57c7868ece1a56830e29a466"},"schema_version":"1.0","source":{"id":"2505.19631","kind":"arxiv","version":1}},"canonical_sha256":"5409891924a51edb86c6d3c5f99e319ce111a786a52a65e80cc6d5fb580a03b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5409891924a51edb86c6d3c5f99e319ce111a786a52a65e80cc6d5fb580a03b2","first_computed_at":"2026-07-05T11:09:33.805591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:33.805591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BO5ern+Gh9CiTR5pFG559Gr4/8GJwiQx5VxIqZP1WzbQBeic5igO2IQfLhr90ax4bqAhDcKX7uX9FBF7Unt5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:33.806106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c8841263827ab4e677261dd89b49750a3f493e5451c00781b87d2be59cbf37d","sha256:9551fd8b2d85e7536165d3d133ac2aa9600d51ac347c062439e0b0621ff0a73d"],"state_sha256":"f416637eec5f1717f6ccfcddbced4b164a12b47cdb6908d80531f57e8a2175b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xju3lCLVEH2WfgC7X1zZWA6BfZNbrP+k1PwRfmgT6RLijpnqcY976ZswWte39N7LgtWjCc3fD4fnuouu7EH8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:15:06.667544Z","bundle_sha256":"6d4a9a537c1de8bf952403a39e055380edafac7cbef403143d7b49e1b2c0682b"}}