{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GI66IIHPL5ARGH5NHKKUJWPXD5","short_pith_number":"pith:GI66IIHP","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"},"canonical_sha256":"323de420ef5f41131fad3a9544d9f71f66b055a94c18f3994efa215739a9efd7","source":{"kind":"arxiv","id":"2608.00582","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GI66IIHPL5ARGH5NHKKUJWPXD5","target":"record","payload":{"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"},"canonical_sha256":"323de420ef5f41131fad3a9544d9f71f66b055a94c18f3994efa215739a9efd7","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"},"source_kind":"arxiv","source_id":"2608.00582","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":"2026-08-04T00:37:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MHY93bABw55cIx8kL2+6RSn3LBiJbxr1lzjsdwPLtByuks/O4BkodngqVKZY75PBitSPmNcIzVtRjcEOo+6QBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:38:21.892036Z"},"content_sha256":"1ed68a46d666a866df58285598a0fdda598f40edc8db15996b414eb83059bfb4","schema_version":"1.0","event_id":"sha256:1ed68a46d666a866df58285598a0fdda598f40edc8db15996b414eb83059bfb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GI66IIHPL5ARGH5NHKKUJWPXD5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T00:37:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvlZPnVva9jLvI2jqWytmwCBOLYPL/+V/tiE4VVojNNS8J02TjmrFgHjz7+qVJV+FQe6RXSeUcfBq8XZe41nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:38:21.892609Z"},"content_sha256":"4be79a484b3f440b6baccc9fb203ba767a2d17af111a701d95d532dba6179cd6","schema_version":"1.0","event_id":"sha256:4be79a484b3f440b6baccc9fb203ba767a2d17af111a701d95d532dba6179cd6"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:GI66IIHPL5ARGH5NHKKUJWPXD5","target":"integrity","payload":{"note":"Identifier '10.18653/v1/2020' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"doi: 10.18653/v1/2020. findings-emnlp.119. Anna Wegmann, Dong Nguyen, and David Jurgens. Tokenization is sensitive to language variation. InFindings of ACL, pp. 10958–10983,","arxiv_id":"2608.00582","detector":"doi_compliance","evidence":{"doi":"10.18653/v1/2020","arxiv_id":null,"ref_index":16,"raw_excerpt":"doi: 10.18653/v1/2020. findings-emnlp.119. Anna Wegmann, Dong Nguyen, and David Jurgens. Tokenization is sensitive to language variation. InFindings of ACL, pp. 10958–10983,","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":16,"audited_at":"2026-08-05T00:48:16.005316Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2020","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"db6fa85c76b46b364755c8f1a6fb65d7529de4659cf9edd962909a34d929fb4d","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17996,"payload_sha256":"4a92514f317fb5e54dae30d59fdb950758bb9d5a93cc295870b7d58e27060786","signature_b64":"FK8/WSdOdI0Fa9Mpo+OEzBJarSrafgXUVjiZdj6Q/CUvP1GZsgF7ibfD2Ua+qfO02Gm8D6FplHezhAhdwgavDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T00:48:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VoWJid07h8hvH73B7bh//TvV9KtMWAyeAp3snpNgAyDJLZyjxAKrNO9OTkxzMlnabtK+lmgnB4j4WAcubKC8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:38:21.934024Z"},"content_sha256":"791ee080926887d2f9e9e941213293ceb39f5f83ebf5fbe15159251d2cb56a9a","schema_version":"1.0","event_id":"sha256:791ee080926887d2f9e9e941213293ceb39f5f83ebf5fbe15159251d2cb56a9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/bundle.json","state_url":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/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":"2026-08-06T16:38:21Z","links":{"resolver":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5","bundle":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/bundle.json","state":"https://pith.science/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GI66IIHPL5ARGH5NHKKUJWPXD5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbMOrp3fl6Wyi6Eh90PD+RoNvDTH8jcZWoAnwg2wucxF4Fe6jNyeGbFtIpLoGiVDXVEEaWqMMvEPkb7epYdrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:38:21.936851Z","bundle_sha256":"d5732865da7b2690b59b2c93511ec39e19eecc1d5d0a9b34c469226b5240d9a7"}}