{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ARIOSVOZESNY4SBPRFYVMR7WJ5","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":"852a3c6fe20213480b6273eb2d472df411c9c6d565ef1ebfb985e5d5ec55aadb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-12T05:03:55Z","title_canon_sha256":"55e5a8e3771b638a099e550e16433fb6a202d09dd1375e507e8aae0a28c5bab3"},"schema_version":"1.0","source":{"id":"2606.14122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.14122","created_at":"2026-06-26T01:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.14122v2","created_at":"2026-06-26T01:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14122","created_at":"2026-06-26T01:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"ARIOSVOZESNY","created_at":"2026-06-26T01:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"ARIOSVOZESNY4SBP","created_at":"2026-06-26T01:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"ARIOSVOZ","created_at":"2026-06-26T01:15:19Z"}],"graph_snapshots":[{"event_id":"sha256:c6d09025cd3d3e2742141964c0b9f949492704653abe8efb2ea891e92db8c4f7","target":"graph","created_at":"2026-06-26T01:15:19Z","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/2606.14122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Byte-level tokenization enables language models to handle any Unicode input, but models can generate invalid UTF-8 sequences when encountering rare or unseen characters. We investigate the relationship between training scale and UTF-8 generation reliability with a 355M parameter model trained on 80B tokens from a balanced multilingual corpus of English, Japanese, Korean, and Chinese. We introduce multiple evaluation protocols that isolate UTF-8 structural validity from language modeling. UTF-8 validity convergence lags perplexity by a roughly a factor of two: perplexity stabilizes after 2.1B t","authors_text":"Daisuke Oba, Naoaki Okazaki, Sangwhan Moon, Tatsuya Hiraoka, Youmi Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-12T05:03:55Z","title":"Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14122","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":"sha256:4af1c8dabb4e54edd380f32c21a96cd32477bfd438b26da6412720d5effdf502","target":"record","created_at":"2026-06-26T01:15:19Z","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":"852a3c6fe20213480b6273eb2d472df411c9c6d565ef1ebfb985e5d5ec55aadb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-12T05:03:55Z","title_canon_sha256":"55e5a8e3771b638a099e550e16433fb6a202d09dd1375e507e8aae0a28c5bab3"},"schema_version":"1.0","source":{"id":"2606.14122","kind":"arxiv","version":2}},"canonical_sha256":"0450e955d9249b8e482f89715647f64f4f129d9f13ca8ce8163dedbc87e911dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0450e955d9249b8e482f89715647f64f4f129d9f13ca8ce8163dedbc87e911dc","first_computed_at":"2026-06-26T01:15:19.595473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:19.595473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOthgBzFwwOZFOn2r/DwzD1biX3E0myEJ07X6L70/vhdfhiH2JDQTwE/ljHKFXQTWBZ656CCuG6i2ez4tl7GBA==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:19.595974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.14122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4af1c8dabb4e54edd380f32c21a96cd32477bfd438b26da6412720d5effdf502","sha256:c6d09025cd3d3e2742141964c0b9f949492704653abe8efb2ea891e92db8c4f7"],"state_sha256":"826cb31a57a893a089cde4b57263317446b20e4c718ca0ce643b2b29c4818f69"}