{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TYEQY3D62IR46SBT7WHWZJDVO4","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":"4ed822335daca52b2d6286467f2af4aaf13b773486789d5b54d3e64733db86dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T14:35:05Z","title_canon_sha256":"746f07cef7336087ecc1ba4809157a72f36434d9aebf27be5dbb9d2deebc2223"},"schema_version":"1.0","source":{"id":"2605.14890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14890","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14890v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14890","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"TYEQY3D62IR4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TYEQY3D62IR46SBT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TYEQY3D6","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c3c3b74d1fa6e3a67e50414dbf61b3652886c85988c85d06832de1ffc0bf3e4e","target":"graph","created_at":"2026-05-17T23:38:55Z","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"},"paper":{"abstract_excerpt":"Foundation models tokenize Ukrainian legal text with vastly different efficiency, yet no systematic comparison exists for this domain. We benchmark seven models from five providers on 273 validated court decisions from Ukraine's state registry (EDRSR), measuring tokenizer fertility and zero-shot performance on three tasks. Three findings emerge. (1) Tokenizer fertility varies 1.6x: Qwen3 models consume 60% more tokens than Llama-family models on identical input, directly reducing API cost. (2) NVIDIA Nemotron Super 3 (120B) achieves the highest composite score (83.1), outperforming Mistral Lar","authors_text":"Volodymyr Ovcharov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T14:35:05Z","title":"Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14890","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:cec511290246ae17b24bfc3c5f2053952e7ad7d3f448299e2d08925481349fb0","target":"record","created_at":"2026-05-17T23:38:55Z","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":"4ed822335daca52b2d6286467f2af4aaf13b773486789d5b54d3e64733db86dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T14:35:05Z","title_canon_sha256":"746f07cef7336087ecc1ba4809157a72f36434d9aebf27be5dbb9d2deebc2223"},"schema_version":"1.0","source":{"id":"2605.14890","kind":"arxiv","version":1}},"canonical_sha256":"9e090c6c7ed223cf4833fd8f6ca47577311085174b595b201f9f67e340124b2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e090c6c7ed223cf4833fd8f6ca47577311085174b595b201f9f67e340124b2d","first_computed_at":"2026-05-17T23:38:55.952549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:55.952549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wu8bisIvSANcOsYy/iBa99XEZTAG9YGQxH/DzX2M6yHUhOF0VrjYiGUfXhcFdCqnEhoQ2u3B2zZzIN5d/km5DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:55.953226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cec511290246ae17b24bfc3c5f2053952e7ad7d3f448299e2d08925481349fb0","sha256:c3c3b74d1fa6e3a67e50414dbf61b3652886c85988c85d06832de1ffc0bf3e4e"],"state_sha256":"c08a5792c11b010fbe2b964daab750b1eb953de498b0be99d8a06279b3c899b5"}