{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T62Q4IZCJRLEU4Z3JNH3TWTYI7","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":"2ae11f2f6df5756460cd4f58bb180ea630545b2b3e498a9c4982976a2fddc9c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T01:22:32Z","title_canon_sha256":"9345f9d5ccf07c2c7a1b932858ca2aff4226ea5511ec374def69f0f7e66aa8ed"},"schema_version":"1.0","source":{"id":"2306.09572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09572","created_at":"2026-07-05T06:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09572v1","created_at":"2026-07-05T06:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09572","created_at":"2026-07-05T06:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"T62Q4IZCJRLE","created_at":"2026-07-05T06:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"T62Q4IZCJRLEU4Z3","created_at":"2026-07-05T06:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"T62Q4IZC","created_at":"2026-07-05T06:21:21Z"}],"graph_snapshots":[{"event_id":"sha256:6f897959e55146b3aad09464f30f873890f27e09e28e75ccaf107cbebb1fd2f2","target":"graph","created_at":"2026-07-05T06:21:21Z","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/2306.09572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the effect of tokenizers on the downstream performance of pretrained language models (PLMs) in scriptio continua languages where no explicit spaces exist between words, using Japanese as a case study. The tokenizer for such languages often consists of a morphological analyzer and a subword tokenizer, requiring us to conduct a comprehensive study of all possible pairs. However, previous studies lack this comprehensiveness. We therefore train extensive sets of tokenizers, build a PLM using each, and measure the downstream performance on a wide range of tasks. Our results ","authors_text":"Atsuki Yamaguchi, Koki Shibata, Takuro Fujii, Terufumi Morishita, Yasuhiro Sogawa","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T01:22:32Z","title":"How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09572","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:fd9fa6ffdd23fc9673f7396b1869f5a7c0f74dc6ee6292bd9b7504f96765e7d8","target":"record","created_at":"2026-07-05T06:21:21Z","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":"2ae11f2f6df5756460cd4f58bb180ea630545b2b3e498a9c4982976a2fddc9c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T01:22:32Z","title_canon_sha256":"9345f9d5ccf07c2c7a1b932858ca2aff4226ea5511ec374def69f0f7e66aa8ed"},"schema_version":"1.0","source":{"id":"2306.09572","kind":"arxiv","version":1}},"canonical_sha256":"9fb50e23224c564a733b4b4fb9da7847c944a0a94595ac61ec13046823f17214","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fb50e23224c564a733b4b4fb9da7847c944a0a94595ac61ec13046823f17214","first_computed_at":"2026-07-05T06:21:21.205774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:21.205774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZW2mVCCEUvwVOMn/apr5z7S+6UUYQMtZaR78k4Cf1KET1eG22OEG7WQx0g4SddMtYgz7fUkHZ7TrnKn3xPu2DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:21.206130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd9fa6ffdd23fc9673f7396b1869f5a7c0f74dc6ee6292bd9b7504f96765e7d8","sha256:6f897959e55146b3aad09464f30f873890f27e09e28e75ccaf107cbebb1fd2f2"],"state_sha256":"743535a8ad775b7ab66006641704ec9690ad33148333422d5396669cf858599c"}