{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RTYD7IHFMBD5XQSJNXCM4RELZK","short_pith_number":"pith:RTYD7IHF","canonical_record":{"source":{"id":"2605.24718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T20:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"7e167d70224cbe69ea902124a017032ca201d1b357e79c456225a8fcff5b40bf","abstract_canon_sha256":"a195f8dc5f076bd36a4d833d10df4557a8f5eb28c748633c20c4b4aa2698f36a"},"schema_version":"1.0"},"canonical_sha256":"8cf03fa0e56047dbc2496dc4ce448bca861be65c5afad080983e0ae07f25eb8e","source":{"kind":"arxiv","id":"2605.24718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24718","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24718v1","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24718","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"RTYD7IHFMBD5","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"RTYD7IHFMBD5XQSJ","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"RTYD7IHF","created_at":"2026-05-26T01:03:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RTYD7IHFMBD5XQSJNXCM4RELZK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T20:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"7e167d70224cbe69ea902124a017032ca201d1b357e79c456225a8fcff5b40bf","abstract_canon_sha256":"a195f8dc5f076bd36a4d833d10df4557a8f5eb28c748633c20c4b4aa2698f36a"},"schema_version":"1.0"},"canonical_sha256":"8cf03fa0e56047dbc2496dc4ce448bca861be65c5afad080983e0ae07f25eb8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:54.981101Z","signature_b64":"NeFCIB+o6ujG5yF8ODiucDjXA72ywKOtJSU9EgisvQE7kgqhzW1T6SCLJD7JVgCgorVnLhtuGsCO3azABbBgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cf03fa0e56047dbc2496dc4ce448bca861be65c5afad080983e0ae07f25eb8e","last_reissued_at":"2026-05-26T01:03:54.980351Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:54.980351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24718","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":"2026-05-26T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4E1V8PzDaTwzdmDO3XX8cVfQqel8D7wi1asx+FwnWJ6fk56YbAyORfNfkcRjctLymNGYhADO8fTy/CPj1lyhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:41:14.055888Z"},"content_sha256":"fdb840351bbfdeb6eb871a196506f997deb27230d36d22e7076bac31ecaf9e1c","schema_version":"1.0","event_id":"sha256:fdb840351bbfdeb6eb871a196506f997deb27230d36d22e7076bac31ecaf9e1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RTYD7IHFMBD5XQSJNXCM4RELZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Volodymyr Ovcharov","submitted_at":"2026-05-23T20:13:44Z","abstract_excerpt":"Tokenizer fertility the number of tokens per word imposes a hidden cost on non-English NLP. We measure fertility for ten foundation models across 25 European languages on parallel text, producing the first controlled tokenizer tax map for the continent. The tax spans 2.5x from English (1.2 tokens/word) to Greek/Maltese (~3.1), following a clear hierarchy: Romance (1.5-1.7), Germanic (1.7-1.9), Slavic (2.2-2.5), Uralic/Baltic (2.7-3.0). Ukrainian (2.7) pays 15-18% more than cognate Slavic languages, reflecting underrepresentation in pre-training data. Fertility rankings are domain-invariant acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24718","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/2605.24718/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":"2026-05-26T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"he0CYYta3QUb9hAYM2ZCsiMDKn3ucH26eW6qTSeTVvI4y0Qg67sFnabeGFt5scw1NhtaHwNkEN5OSEtElDfiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T02:41:14.056279Z"},"content_sha256":"906b60ece6720f49870955f27219afe9454eeaf3a9791eb8df43a17d49d90730","schema_version":"1.0","event_id":"sha256:906b60ece6720f49870955f27219afe9454eeaf3a9791eb8df43a17d49d90730"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RTYD7IHFMBD5XQSJNXCM4RELZK/bundle.json","state_url":"https://pith.science/pith/RTYD7IHFMBD5XQSJNXCM4RELZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RTYD7IHFMBD5XQSJNXCM4RELZK/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":"2026-06-30T02:41:14Z","links":{"resolver":"https://pith.science/pith/RTYD7IHFMBD5XQSJNXCM4RELZK","bundle":"https://pith.science/pith/RTYD7IHFMBD5XQSJNXCM4RELZK/bundle.json","state":"https://pith.science/pith/RTYD7IHFMBD5XQSJNXCM4RELZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RTYD7IHFMBD5XQSJNXCM4RELZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RTYD7IHFMBD5XQSJNXCM4RELZK","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":"a195f8dc5f076bd36a4d833d10df4557a8f5eb28c748633c20c4b4aa2698f36a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T20:13:44Z","title_canon_sha256":"7e167d70224cbe69ea902124a017032ca201d1b357e79c456225a8fcff5b40bf"},"schema_version":"1.0","source":{"id":"2605.24718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24718","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24718v1","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24718","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"RTYD7IHFMBD5","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"RTYD7IHFMBD5XQSJ","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"RTYD7IHF","created_at":"2026-05-26T01:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:906b60ece6720f49870955f27219afe9454eeaf3a9791eb8df43a17d49d90730","target":"graph","created_at":"2026-05-26T01:03:54Z","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/2605.24718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenizer fertility the number of tokens per word imposes a hidden cost on non-English NLP. We measure fertility for ten foundation models across 25 European languages on parallel text, producing the first controlled tokenizer tax map for the continent. The tax spans 2.5x from English (1.2 tokens/word) to Greek/Maltese (~3.1), following a clear hierarchy: Romance (1.5-1.7), Germanic (1.7-1.9), Slavic (2.2-2.5), Uralic/Baltic (2.7-3.0). Ukrainian (2.7) pays 15-18% more than cognate Slavic languages, reflecting underrepresentation in pre-training data. Fertility rankings are domain-invariant acr","authors_text":"Volodymyr Ovcharov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T20:13:44Z","title":"The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24718","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:fdb840351bbfdeb6eb871a196506f997deb27230d36d22e7076bac31ecaf9e1c","target":"record","created_at":"2026-05-26T01:03:54Z","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":"a195f8dc5f076bd36a4d833d10df4557a8f5eb28c748633c20c4b4aa2698f36a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T20:13:44Z","title_canon_sha256":"7e167d70224cbe69ea902124a017032ca201d1b357e79c456225a8fcff5b40bf"},"schema_version":"1.0","source":{"id":"2605.24718","kind":"arxiv","version":1}},"canonical_sha256":"8cf03fa0e56047dbc2496dc4ce448bca861be65c5afad080983e0ae07f25eb8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cf03fa0e56047dbc2496dc4ce448bca861be65c5afad080983e0ae07f25eb8e","first_computed_at":"2026-05-26T01:03:54.980351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:54.980351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NeFCIB+o6ujG5yF8ODiucDjXA72ywKOtJSU9EgisvQE7kgqhzW1T6SCLJD7JVgCgorVnLhtuGsCO3azABbBgDA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:54.981101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdb840351bbfdeb6eb871a196506f997deb27230d36d22e7076bac31ecaf9e1c","sha256:906b60ece6720f49870955f27219afe9454eeaf3a9791eb8df43a17d49d90730"],"state_sha256":"0291a029aa86e6057c920eb1dc29860f0aab4ff8268909a4640bb500394445fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lw9NPPg0esPLraXUqAiJTQLZSry2x2Rtv6lfGJ+gFrar3494qVL/aRKx2ehIi5w/mDZmaYAjZ+SEWD4ffRW7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T02:41:14.058560Z","bundle_sha256":"b41c2f3c89b0f9fc690c4a9ec44ced802ca3b6ec16f146bfb8fc18ea75c48325"}}