{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GI66IIHPL5ARGH5NHKKUJWPXD5","short_pith_number":"pith:GI66IIHP","schema_version":"1.0","canonical_sha256":"323de420ef5f41131fad3a9544d9f71f66b055a94c18f3994efa215739a9efd7","source":{"kind":"arxiv","id":"2608.00582","version":1},"attestation_state":"computed","paper":{"title":"Writing-System-Level Tokenizer Adaptation for Byte-Level BPE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohdan Didenko (Lviv Polytechnic National University)","submitted_at":"2026-08-01T10:38:23Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.00582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T10:38:23Z","cross_cats_sorted":[],"title_canon_sha256":"ac3a502346ea4c59ca0e3a6907559ebf55b2b0ce6c0b0d033e25730a4005d19a","abstract_canon_sha256":"b27100590e17e319b6d1313c0d49744605ae2a8e37887dad4e3fb562627c62a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:37:34.479259Z","signature_b64":"PYBHeoW8HpqAzDdWBgJXD8uRU94dlri048AMf+q4+jbttoB1+yUMn+WS+pYgRIb/sdtN6FNY8KyXsZ2GAomRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"323de420ef5f41131fad3a9544d9f71f66b055a94c18f3994efa215739a9efd7","last_reissued_at":"2026-08-04T00:37:34.477819Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:37:34.477819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Writing-System-Level Tokenizer Adaptation for Byte-Level BPE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohdan Didenko (Lviv Polytechnic National University)","submitted_at":"2026-08-01T10:38:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00582","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/2608.00582/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.00582","created_at":"2026-08-04T00:37:34.479021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00582v1","created_at":"2026-08-04T00:37:34.479021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00582","created_at":"2026-08-04T00:37:34.479021+00:00"},{"alias_kind":"pith_short_12","alias_value":"GI66IIHPL5AR","created_at":"2026-08-04T00:37:34.479021+00:00"},{"alias_kind":"pith_short_16","alias_value":"GI66IIHPL5ARGH5N","created_at":"2026-08-04T00:37:34.479021+00:00"},{"alias_kind":"pith_short_8","alias_value":"GI66IIHP","created_at":"2026-08-04T00:37:34.479021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5","json":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5.json","graph_json":"https://pith.science/api/pith-number/GI66IIHPL5ARGH5NHKKUJWPXD5/graph.json","events_json":"https://pith.science/api/pith-number/GI66IIHPL5ARGH5NHKKUJWPXD5/events.json","paper":"https://pith.science/paper/GI66IIHP"},"agent_actions":{"view_html":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5","download_json":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5.json","view_paper":"https://pith.science/paper/GI66IIHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00582&json=true","fetch_graph":"https://pith.science/api/pith-number/GI66IIHPL5ARGH5NHKKUJWPXD5/graph.json","fetch_events":"https://pith.science/api/pith-number/GI66IIHPL5ARGH5NHKKUJWPXD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/action/storage_attestation","attest_author":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/action/author_attestation","sign_citation":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/action/citation_signature","submit_replication":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/action/replication_record"}},"created_at":"2026-08-04T00:37:34.479021+00:00","updated_at":"2026-08-04T00:37:34.479021+00:00"}