{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5J2ZX75S75N57ELCEK2ZOOOXAH","short_pith_number":"pith:5J2ZX75S","canonical_record":{"source":{"id":"2506.07541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:28:16Z","cross_cats_sorted":[],"title_canon_sha256":"c92bc11232c49aff5583a071705dd45110f7cc63166894ec54924f6fbff5bb56","abstract_canon_sha256":"16441cfab3a64f5bae67c5605640b7bd64d2b8fd9b8b9b00cfed11a97f4d8641"},"schema_version":"1.0"},"canonical_sha256":"ea759bffb2ff5bdf916222b59739d701e9ab3b0015bb98903da49ffaaa5cf054","source":{"kind":"arxiv","id":"2506.07541","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5J2ZX75S75N57ELCEK2ZOOOXAH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T08:28:16Z","cross_cats_sorted":[],"title_canon_sha256":"c92bc11232c49aff5583a071705dd45110f7cc63166894ec54924f6fbff5bb56","abstract_canon_sha256":"16441cfab3a64f5bae67c5605640b7bd64d2b8fd9b8b9b00cfed11a97f4d8641"},"schema_version":"1.0"},"canonical_sha256":"ea759bffb2ff5bdf916222b59739d701e9ab3b0015bb98903da49ffaaa5cf054","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:29.104709Z","signature_b64":"YU1mvyFtC7E8totfdyUI8MNpWepPFORytcU7X+H7O4gsFkbAVB/7RLa6L5guRtspw6A5BeCRI8dE5o+dLTzACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea759bffb2ff5bdf916222b59739d701e9ab3b0015bb98903da49ffaaa5cf054","last_reissued_at":"2026-07-05T11:18:29.104147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:29.104147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07541","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yW14Fg0WEBG94BuEfrYK85udQ9b+MZS/bVjvyDGUBQOFOuTNQz5L6gQ/T+eLol5HtiZ5yRourmOj21m/eoRCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:29:22.578761Z"},"content_sha256":"3e2538c447f4182f5818985949de22d2b70022bd4172023bab96f760f84f33a6","schema_version":"1.0","event_id":"sha256:3e2538c447f4182f5818985949de22d2b70022bd4172023bab96f760f84f33a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5J2ZX75S75N57ELCEK2ZOOOXAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bit-level BPE: Below the byte boundary","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Naoaki Okazaki, Sangwhan Moon, Tatsuya Hiraoka","submitted_at":"2025-06-09T08:28:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07541","kind":"arxiv","version":1},"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/2506.07541/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":"2026-07-05T11:18:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+NzW1wXNkXx8wpWDbkkp2OGwP82Scp2+zFrEz/M17azwWrfrzuD2ox4sS/zxlUrjT1GY3jsaUve29Tlw+/zvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:29:22.579292Z"},"content_sha256":"5a74f7d43b67c90c4ced226504a4dc71c05c326d3b8e70611139207f82f2ba81","schema_version":"1.0","event_id":"sha256:5a74f7d43b67c90c4ced226504a4dc71c05c326d3b8e70611139207f82f2ba81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5J2ZX75S75N57ELCEK2ZOOOXAH/bundle.json","state_url":"https://pith.science/pith/5J2ZX75S75N57ELCEK2ZOOOXAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5J2ZX75S75N57ELCEK2ZOOOXAH/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":"2026-08-07T23:29:22Z","links":{"resolver":"https://pith.science/pith/5J2ZX75S75N57ELCEK2ZOOOXAH","bundle":"https://pith.science/pith/5J2ZX75S75N57ELCEK2ZOOOXAH/bundle.json","state":"https://pith.science/pith/5J2ZX75S75N57ELCEK2ZOOOXAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5J2ZX75S75N57ELCEK2ZOOOXAH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JXJ0nYSeJOQ3lD9SikqIahWqewJSNqUWWejUt2HzxaVBVPbYa5QaFjGZK8m9qhz1AaaCN1/fUn7TETeu4jj2DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:29:22.584432Z","bundle_sha256":"1ac0837ea907a1b35d06499db3b2e5da73675552645f70d00151f84cdbf250bc"}}