{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5J2ZX75S75N57ELCEK2ZOOOXAH","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":"16441cfab3a64f5bae67c5605640b7bd64d2b8fd9b8b9b00cfed11a97f4d8641","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:28:16Z","title_canon_sha256":"c92bc11232c49aff5583a071705dd45110f7cc63166894ec54924f6fbff5bb56"},"schema_version":"1.0","source":{"id":"2506.07541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07541","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07541v1","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07541","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"pith_short_12","alias_value":"5J2ZX75S75N5","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"pith_short_16","alias_value":"5J2ZX75S75N57ELC","created_at":"2026-07-05T11:18:29Z"},{"alias_kind":"pith_short_8","alias_value":"5J2ZX75S","created_at":"2026-07-05T11:18:29Z"}],"graph_snapshots":[{"event_id":"sha256:5a74f7d43b67c90c4ced226504a4dc71c05c326d3b8e70611139207f82f2ba81","target":"graph","created_at":"2026-07-05T11:18:29Z","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/2506.07541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Byte-level fallbacks for subword tokenization have become a common practice in large language models. In particular, it has been demonstrated to be incredibly effective as a pragmatic solution for preventing OOV, especially in the context of larger models. However, breaking a character down to individual bytes significantly increases the sequence length for long-tail tokens in languages such as Chinese, Japanese, and Korean (CJK) and other character-diverse contexts such as emoji. The increased sequence length results in longer computation during both training and inference. In this work, we p","authors_text":"Naoaki Okazaki, Sangwhan Moon, Tatsuya Hiraoka","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:28:16Z","title":"Bit-level BPE: Below the byte boundary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07541","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":"sha256:3e2538c447f4182f5818985949de22d2b70022bd4172023bab96f760f84f33a6","target":"record","created_at":"2026-07-05T11:18:29Z","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":"16441cfab3a64f5bae67c5605640b7bd64d2b8fd9b8b9b00cfed11a97f4d8641","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:28:16Z","title_canon_sha256":"c92bc11232c49aff5583a071705dd45110f7cc63166894ec54924f6fbff5bb56"},"schema_version":"1.0","source":{"id":"2506.07541","kind":"arxiv","version":1}},"canonical_sha256":"ea759bffb2ff5bdf916222b59739d701e9ab3b0015bb98903da49ffaaa5cf054","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea759bffb2ff5bdf916222b59739d701e9ab3b0015bb98903da49ffaaa5cf054","first_computed_at":"2026-07-05T11:18:29.104147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:29.104147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YU1mvyFtC7E8totfdyUI8MNpWepPFORytcU7X+H7O4gsFkbAVB/7RLa6L5guRtspw6A5BeCRI8dE5o+dLTzACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:29.104709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e2538c447f4182f5818985949de22d2b70022bd4172023bab96f760f84f33a6","sha256:5a74f7d43b67c90c4ced226504a4dc71c05c326d3b8e70611139207f82f2ba81"],"state_sha256":"119646707fc102c24cb6c0844037b0835e34afb0950fe809f8d07e572e1f0e2f"}