{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RS4K2CIL6OHHSK4QANYWNIDPYX","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":"a884b3b190531d2b30482c04230f4521a2445f80a76c97733f72c2579a33c572","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T15:12:41Z","title_canon_sha256":"6bec071f28294bbf0473c1639ec4f87a5175f6020299f0768f8ed2c600450a8b"},"schema_version":"1.0","source":{"id":"2505.24689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24689","created_at":"2026-07-05T11:12:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24689v1","created_at":"2026-07-05T11:12:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24689","created_at":"2026-07-05T11:12:54Z"},{"alias_kind":"pith_short_12","alias_value":"RS4K2CIL6OHH","created_at":"2026-07-05T11:12:54Z"},{"alias_kind":"pith_short_16","alias_value":"RS4K2CIL6OHHSK4Q","created_at":"2026-07-05T11:12:54Z"},{"alias_kind":"pith_short_8","alias_value":"RS4K2CIL","created_at":"2026-07-05T11:12:54Z"}],"graph_snapshots":[{"event_id":"sha256:51f73dcf3d0a3cb0234582f67a49d880cc4ff5d995188572ee87a73e7df4a4bd","target":"graph","created_at":"2026-07-05T11:12:54Z","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/2505.24689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Byte Pair Encoding (BPE) tokenizers, widely used in Large Language Models, face challenges in multilingual settings, including penalization of non-Western scripts and the creation of tokens with partial UTF-8 sequences. Pretokenization, often reliant on complex regular expressions, can also introduce fragility and unexpected edge cases. We propose SCRIPT (Script Category Representation in PreTokenization), a novel encoding scheme that bypasses UTF-8 byte conversion by using initial tokens based on Unicode script and category properties. This approach enables a simple, rule-based pretokenizatio","authors_text":"Catherine Arnett, Sander Land","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T15:12:41Z","title":"BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24689","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:c48f3708b33cffa2a75b3af718b6a586c0320f46fc665ab73fd43b10101bfd50","target":"record","created_at":"2026-07-05T11:12:54Z","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":"a884b3b190531d2b30482c04230f4521a2445f80a76c97733f72c2579a33c572","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T15:12:41Z","title_canon_sha256":"6bec071f28294bbf0473c1639ec4f87a5175f6020299f0768f8ed2c600450a8b"},"schema_version":"1.0","source":{"id":"2505.24689","kind":"arxiv","version":1}},"canonical_sha256":"8cb8ad090bf38e792b90037166a06fc5c6f4b081260c0e709ff7bc20b2dc4833","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cb8ad090bf38e792b90037166a06fc5c6f4b081260c0e709ff7bc20b2dc4833","first_computed_at":"2026-07-05T11:12:54.741391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:54.741391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdOtc5eSpFNQUYD7j5Try+zS/oydGJ1i3TRn9tk93IlubaZsCpePuzf8G/FeTXMh1HqGv1YRmYag4n8n1ddbBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:54.741974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c48f3708b33cffa2a75b3af718b6a586c0320f46fc665ab73fd43b10101bfd50","sha256:51f73dcf3d0a3cb0234582f67a49d880cc4ff5d995188572ee87a73e7df4a4bd"],"state_sha256":"a713e3517a13f014e7e29eddbf204db664c44da699beed3a95e110af2b7a3d65"}