{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VVV4XNY6PSMPF372GECHEPRTVG","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":"9be9591f10bdcc8258d369a97c7fc93e3e0025835b3cf3d02a87e83aa528e277","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:47:49Z","title_canon_sha256":"3c7cf61ff0ddbe4e07b86cfc9916ce29d8736f56024aef5004cf595f617372a8"},"schema_version":"1.0","source":{"id":"2502.07057","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07057","created_at":"2026-07-05T11:40:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07057v2","created_at":"2026-07-05T11:40:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07057","created_at":"2026-07-05T11:40:32Z"},{"alias_kind":"pith_short_12","alias_value":"VVV4XNY6PSMP","created_at":"2026-07-05T11:40:32Z"},{"alias_kind":"pith_short_16","alias_value":"VVV4XNY6PSMPF372","created_at":"2026-07-05T11:40:32Z"},{"alias_kind":"pith_short_8","alias_value":"VVV4XNY6","created_at":"2026-07-05T11:40:32Z"}],"graph_snapshots":[{"event_id":"sha256:6e21ce5b5568203b4b2841aa3e9672cba4355e54eba3eb517720253e9982089b","target":"graph","created_at":"2026-07-05T11:40:32Z","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/2502.07057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization is a fundamental preprocessing step in NLP, directly impacting large language models' (LLMs) ability to capture syntactic, morphosyntactic, and semantic structures. This paper introduces a novel framework for systematically evaluating tokenization strategies, addressing challenges in morphologically rich and low-resource languages. Using a Turkish dataset of 6,200 multiple-choice questions from the Massive Multitask Language Understanding (MMLU) benchmark, the framework assesses tokenizers across five key metrics: vocabulary size, token count, processing time, language-specific to","authors_text":"Ahmet Semih G\\\"um\\\"u\\c{s}, Ali Arda Fincan, Banu Diri, M. Ali Bayram, Sava\\c{s} Y{\\i}ld{\\i}r{\\i}m, Sercan Karaka\\c{s}","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:47:49Z","title":"Tokenization Standards for Linguistic Integrity: Turkish as a Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07057","kind":"arxiv","version":2},"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":"sha256:4cc58b066577eaf75b8d3a8226a5599b2e42accbafef22390adda3642f27b8bb","target":"record","created_at":"2026-07-05T11:40:32Z","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":"9be9591f10bdcc8258d369a97c7fc93e3e0025835b3cf3d02a87e83aa528e277","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:47:49Z","title_canon_sha256":"3c7cf61ff0ddbe4e07b86cfc9916ce29d8736f56024aef5004cf595f617372a8"},"schema_version":"1.0","source":{"id":"2502.07057","kind":"arxiv","version":2}},"canonical_sha256":"ad6bcbb71e7c98f2effa3104723e33a9946833a3cbb772773abbc5d5ba48ef02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad6bcbb71e7c98f2effa3104723e33a9946833a3cbb772773abbc5d5ba48ef02","first_computed_at":"2026-07-05T11:40:32.692199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:32.692199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HHTjKmAv864NXZybbftPphwUzm89eXkFN8QKaUODAssAKhVN2LL3r9P4QUCf3qYT/xbdgHpL6qntz4QEwiEoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:32.692752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07057","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cc58b066577eaf75b8d3a8226a5599b2e42accbafef22390adda3642f27b8bb","sha256:6e21ce5b5568203b4b2841aa3e9672cba4355e54eba3eb517720253e9982089b"],"state_sha256":"6c561eda0d95e56023599b58a356cab82ab4f73cf077186c7d1ac970de3f05d1"}