{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GI66IIHPL5ARGH5NHKKUJWPXD5","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b27100590e17e319b6d1313c0d49744605ae2a8e37887dad4e3fb562627c62a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T10:38:23Z","title_canon_sha256":"ac3a502346ea4c59ca0e3a6907559ebf55b2b0ce6c0b0d033e25730a4005d19a"},"schema_version":"1.0","source":{"id":"2608.00582","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00582","created_at":"2026-08-04T00:37:34Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00582v1","created_at":"2026-08-04T00:37:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00582","created_at":"2026-08-04T00:37:34Z"},{"alias_kind":"pith_short_12","alias_value":"GI66IIHPL5AR","created_at":"2026-08-04T00:37:34Z"},{"alias_kind":"pith_short_16","alias_value":"GI66IIHPL5ARGH5N","created_at":"2026-08-04T00:37:34Z"},{"alias_kind":"pith_short_8","alias_value":"GI66IIHP","created_at":"2026-08-04T00:37:34Z"}],"graph_snapshots":[{"event_id":"sha256:4be79a484b3f440b6baccc9fb203ba767a2d17af111a701d95d532dba6179cd6","target":"graph","created_at":"2026-08-04T00:37:34Z","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/2608.00582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained byte-level BPE tokenizers can segment underrepresented languages inefficiently. Replacing a tokenizer changes the meaning of nearly every token ID, while vocabulary expansion enlarges the model's embedding and output matrices. We study post-hoc adaptation that keeps the model-vocabulary size fixed and preserves most existing token-to-ID assignments as a construction-time compatibility property. Directly transferring tokens from a language-specific tokenizer does not guarantee derivability through the target BPE merge graph: an inserted entry can conflict with the target's greedy mer","authors_text":"Bohdan Didenko (Lviv Polytechnic National University)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T10:38:23Z","title":"Writing-System-Level Tokenizer Adaptation for Byte-Level BPE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00582","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":"sha256:1ed68a46d666a866df58285598a0fdda598f40edc8db15996b414eb83059bfb4","target":"record","created_at":"2026-08-04T00:37:34Z","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":"b27100590e17e319b6d1313c0d49744605ae2a8e37887dad4e3fb562627c62a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T10:38:23Z","title_canon_sha256":"ac3a502346ea4c59ca0e3a6907559ebf55b2b0ce6c0b0d033e25730a4005d19a"},"schema_version":"1.0","source":{"id":"2608.00582","kind":"arxiv","version":1}},"canonical_sha256":"323de420ef5f41131fad3a9544d9f71f66b055a94c18f3994efa215739a9efd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"323de420ef5f41131fad3a9544d9f71f66b055a94c18f3994efa215739a9efd7","first_computed_at":"2026-08-04T00:37:34.477819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:37:34.477819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PYBHeoW8HpqAzDdWBgJXD8uRU94dlri048AMf+q4+jbttoB1+yUMn+WS+pYgRIb/sdtN6FNY8KyXsZ2GAomRAA==","signature_status":"signed_v1","signed_at":"2026-08-04T00:37:34.479259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00582","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ed68a46d666a866df58285598a0fdda598f40edc8db15996b414eb83059bfb4","sha256:4be79a484b3f440b6baccc9fb203ba767a2d17af111a701d95d532dba6179cd6","sha256:791ee080926887d2f9e9e941213293ceb39f5f83ebf5fbe15159251d2cb56a9a"],"state_sha256":"5de3ab524efac4360d5bf67efbd7946be6089070a4161bf9b050e8917a9c4e1e"}