{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RS4K2CIL6OHHSK4QANYWNIDPYX","short_pith_number":"pith:RS4K2CIL","canonical_record":{"source":{"id":"2505.24689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T15:12:41Z","cross_cats_sorted":[],"title_canon_sha256":"6bec071f28294bbf0473c1639ec4f87a5175f6020299f0768f8ed2c600450a8b","abstract_canon_sha256":"a884b3b190531d2b30482c04230f4521a2445f80a76c97733f72c2579a33c572"},"schema_version":"1.0"},"canonical_sha256":"8cb8ad090bf38e792b90037166a06fc5c6f4b081260c0e709ff7bc20b2dc4833","source":{"kind":"arxiv","id":"2505.24689","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RS4K2CIL6OHHSK4QANYWNIDPYX","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T15:12:41Z","cross_cats_sorted":[],"title_canon_sha256":"6bec071f28294bbf0473c1639ec4f87a5175f6020299f0768f8ed2c600450a8b","abstract_canon_sha256":"a884b3b190531d2b30482c04230f4521a2445f80a76c97733f72c2579a33c572"},"schema_version":"1.0"},"canonical_sha256":"8cb8ad090bf38e792b90037166a06fc5c6f4b081260c0e709ff7bc20b2dc4833","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:54.741974Z","signature_b64":"GdOtc5eSpFNQUYD7j5Try+zS/oydGJ1i3TRn9tk93IlubaZsCpePuzf8G/FeTXMh1HqGv1YRmYag4n8n1ddbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cb8ad090bf38e792b90037166a06fc5c6f4b081260c0e709ff7bc20b2dc4833","last_reissued_at":"2026-07-05T11:12:54.741391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:54.741391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24689","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":"2026-07-05T11:12:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"goVZsm1O3Plj4SwjCs1HzJ0zCa3whPMaPkCrsvDgzgjB9KtH5CkWnSn/G1Ochlkj2jf7sfvEoITpWPRYe7WTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:44.487374Z"},"content_sha256":"c48f3708b33cffa2a75b3af718b6a586c0320f46fc665ab73fd43b10101bfd50","schema_version":"1.0","event_id":"sha256:c48f3708b33cffa2a75b3af718b6a586c0320f46fc665ab73fd43b10101bfd50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RS4K2CIL6OHHSK4QANYWNIDPYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Catherine Arnett, Sander Land","submitted_at":"2025-05-30T15:12:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24689","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/2505.24689/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":"2026-07-05T11:12:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1DEeeny8f05FkZLEAzrLz6M422kSi4fq8ZggE9oDQU1FvWlglEbf/7rS92JRflP/n6tUGp3FBMg/mGCSmTC0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:44.487872Z"},"content_sha256":"51f73dcf3d0a3cb0234582f67a49d880cc4ff5d995188572ee87a73e7df4a4bd","schema_version":"1.0","event_id":"sha256:51f73dcf3d0a3cb0234582f67a49d880cc4ff5d995188572ee87a73e7df4a4bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RS4K2CIL6OHHSK4QANYWNIDPYX/bundle.json","state_url":"https://pith.science/pith/RS4K2CIL6OHHSK4QANYWNIDPYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RS4K2CIL6OHHSK4QANYWNIDPYX/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":"2026-08-08T08:52:44Z","links":{"resolver":"https://pith.science/pith/RS4K2CIL6OHHSK4QANYWNIDPYX","bundle":"https://pith.science/pith/RS4K2CIL6OHHSK4QANYWNIDPYX/bundle.json","state":"https://pith.science/pith/RS4K2CIL6OHHSK4QANYWNIDPYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RS4K2CIL6OHHSK4QANYWNIDPYX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzcSYc0O/ebkOSJX6yOmOS1ur7pf3VJ2wtz9nfe8G4CYZDHLVOgONLz+gFBopdq9r7lJh1hGOe9ti8RefYF6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:52:44.491399Z","bundle_sha256":"0b6927a44f648281c12c9feb986ff742b4308754d1aa2a7c00971fe67d5f00c1"}}