{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ARIOSVOZESNY4SBPRFYVMR7WJ5","short_pith_number":"pith:ARIOSVOZ","canonical_record":{"source":{"id":"2606.14122","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-12T05:03:55Z","cross_cats_sorted":[],"title_canon_sha256":"55e5a8e3771b638a099e550e16433fb6a202d09dd1375e507e8aae0a28c5bab3","abstract_canon_sha256":"852a3c6fe20213480b6273eb2d472df411c9c6d565ef1ebfb985e5d5ec55aadb"},"schema_version":"1.0"},"canonical_sha256":"0450e955d9249b8e482f89715647f64f4f129d9f13ca8ce8163dedbc87e911dc","source":{"kind":"arxiv","id":"2606.14122","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ARIOSVOZESNY4SBPRFYVMR7WJ5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.14122","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-12T05:03:55Z","cross_cats_sorted":[],"title_canon_sha256":"55e5a8e3771b638a099e550e16433fb6a202d09dd1375e507e8aae0a28c5bab3","abstract_canon_sha256":"852a3c6fe20213480b6273eb2d472df411c9c6d565ef1ebfb985e5d5ec55aadb"},"schema_version":"1.0"},"canonical_sha256":"0450e955d9249b8e482f89715647f64f4f129d9f13ca8ce8163dedbc87e911dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:19.595974Z","signature_b64":"DOthgBzFwwOZFOn2r/DwzD1biX3E0myEJ07X6L70/vhdfhiH2JDQTwE/ljHKFXQTWBZ656CCuG6i2ez4tl7GBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0450e955d9249b8e482f89715647f64f4f129d9f13ca8ce8163dedbc87e911dc","last_reissued_at":"2026-06-26T01:15:19.595473Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:19.595473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.14122","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T01:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ghwL20BkAwrNhZJQJ7Rt5NpbvqIIPRsKmzZVqhyyTvWEY/usV/8p2GgCJ1ZD4/054njvwbhNy2AoE23uyfMLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:28:45.437286Z"},"content_sha256":"4af1c8dabb4e54edd380f32c21a96cd32477bfd438b26da6412720d5effdf502","schema_version":"1.0","event_id":"sha256:4af1c8dabb4e54edd380f32c21a96cd32477bfd438b26da6412720d5effdf502"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ARIOSVOZESNY4SBPRFYVMR7WJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daisuke Oba, Naoaki Okazaki, Sangwhan Moon, Tatsuya Hiraoka, Youmi Ma","submitted_at":"2026-06-12T05:03:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14122","kind":"arxiv","version":2},"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/2606.14122/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":"2026-06-26T01:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xMI0lCrEj4WXl2CiwFGTLBH9ICePJm8o7Qj5bVbc/M7o2HYc8e3yfzCCUp88nr9fLMfhZzHATskSQy0CvnrvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:28:45.437680Z"},"content_sha256":"c6d09025cd3d3e2742141964c0b9f949492704653abe8efb2ea891e92db8c4f7","schema_version":"1.0","event_id":"sha256:c6d09025cd3d3e2742141964c0b9f949492704653abe8efb2ea891e92db8c4f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARIOSVOZESNY4SBPRFYVMR7WJ5/bundle.json","state_url":"https://pith.science/pith/ARIOSVOZESNY4SBPRFYVMR7WJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARIOSVOZESNY4SBPRFYVMR7WJ5/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":"2026-06-29T19:28:45Z","links":{"resolver":"https://pith.science/pith/ARIOSVOZESNY4SBPRFYVMR7WJ5","bundle":"https://pith.science/pith/ARIOSVOZESNY4SBPRFYVMR7WJ5/bundle.json","state":"https://pith.science/pith/ARIOSVOZESNY4SBPRFYVMR7WJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARIOSVOZESNY4SBPRFYVMR7WJ5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4VJ8BW/awx+XxcSh6zV1uRvSKD0c9rxbL2b0u5uyz643I2RYI1mcFifxE6fcKgPYOL5unknN8RfqW75Eb/wfAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T19:28:45.439685Z","bundle_sha256":"312e18956b8295c574386e9988f5b587e8e4399d46234a0c9528cd161334098c"}}