{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BJGB3XRN45IRO2V36Z3DZUENX3","short_pith_number":"pith:BJGB3XRN","canonical_record":{"source":{"id":"2406.16508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T10:27:07Z","cross_cats_sorted":[],"title_canon_sha256":"3200608ed0d49c8e146769109a849917b6fd1794dad0d28c384f352c56313655","abstract_canon_sha256":"1923d3c093f78996be19c57cf32701e20754d6ae990c2bdab97cc8fa8b3ef7af"},"schema_version":"1.0"},"canonical_sha256":"0a4c1dde2de751176abbf6763cd08dbefd3310da85198874b19d4ff8eb8132f2","source":{"kind":"arxiv","id":"2406.16508","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16508","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16508v2","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16508","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"BJGB3XRN45IR","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"pith_short_16","alias_value":"BJGB3XRN45IRO2V3","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"pith_short_8","alias_value":"BJGB3XRN","created_at":"2026-07-05T11:10:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BJGB3XRN45IRO2V36Z3DZUENX3","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T10:27:07Z","cross_cats_sorted":[],"title_canon_sha256":"3200608ed0d49c8e146769109a849917b6fd1794dad0d28c384f352c56313655","abstract_canon_sha256":"1923d3c093f78996be19c57cf32701e20754d6ae990c2bdab97cc8fa8b3ef7af"},"schema_version":"1.0"},"canonical_sha256":"0a4c1dde2de751176abbf6763cd08dbefd3310da85198874b19d4ff8eb8132f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:46.283196Z","signature_b64":"MYRZWmgmFwhLD/RPRj5FTbBxS30PjWc1aylpf4OAhH2MdVr5DZU804DtKXNeVOZG4+0QdiYwTN5nwWR4tYbrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a4c1dde2de751176abbf6763cd08dbefd3310da85198874b19d4ff8eb8132f2","last_reissued_at":"2026-07-05T11:10:46.282672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:46.282672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16508","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":"2026-07-05T11:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+XbwmvQV0hCF8NM/2JQlkfNn6ByPLZ8/SLEriyeUObpLwMJ01sqCvt+IlXoGsRaiVq2QmJO8rnR3RpHff3/ZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:09:14.437536Z"},"content_sha256":"521a7bc68a0ee6b43274ec573713529d53d11f697c8ff10f556575410d520e51","schema_version":"1.0","event_id":"sha256:521a7bc68a0ee6b43274ec573713529d53d11f697c8ff10f556575410d520e51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BJGB3XRN45IRO2V36Z3DZUENX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Vocabulary Size Improves Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ryokan Ri, Sho Takase, Shun Kiyono, Takuya Kato","submitted_at":"2024-06-24T10:27:07Z","abstract_excerpt":"This paper empirically investigates the relationship between subword vocabulary size and the performance of large language models (LLMs) to provide insights on how to define the vocabulary size. Experimental results show that larger vocabulary sizes lead to better performance in LLMs. Moreover, we consider a continual training scenario where a pre-trained language model is trained on a different target language. We introduce a simple method to use a new vocabulary instead of the pre-defined one. We show that using the new vocabulary outperforms the model with the vocabulary used in pre-trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16508","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/2406.16508/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":"2026-07-05T11:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Weol+g2NgpZu+BJWX63VIEIiI7R/VlhIWISVs5xJiz2A7ZBUNn4ze/UDzPjFxWcRxj9iQBkA6Ynb9Q0ugBXJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:09:14.438916Z"},"content_sha256":"75f4998071a5f5a67fda4b0039fa661880199e00faa412ef038361c41395d935","schema_version":"1.0","event_id":"sha256:75f4998071a5f5a67fda4b0039fa661880199e00faa412ef038361c41395d935"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJGB3XRN45IRO2V36Z3DZUENX3/bundle.json","state_url":"https://pith.science/pith/BJGB3XRN45IRO2V36Z3DZUENX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJGB3XRN45IRO2V36Z3DZUENX3/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":"2026-08-18T02:09:14Z","links":{"resolver":"https://pith.science/pith/BJGB3XRN45IRO2V36Z3DZUENX3","bundle":"https://pith.science/pith/BJGB3XRN45IRO2V36Z3DZUENX3/bundle.json","state":"https://pith.science/pith/BJGB3XRN45IRO2V36Z3DZUENX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJGB3XRN45IRO2V36Z3DZUENX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BJGB3XRN45IRO2V36Z3DZUENX3","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":"1923d3c093f78996be19c57cf32701e20754d6ae990c2bdab97cc8fa8b3ef7af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T10:27:07Z","title_canon_sha256":"3200608ed0d49c8e146769109a849917b6fd1794dad0d28c384f352c56313655"},"schema_version":"1.0","source":{"id":"2406.16508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16508","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16508v2","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16508","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"BJGB3XRN45IR","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"pith_short_16","alias_value":"BJGB3XRN45IRO2V3","created_at":"2026-07-05T11:10:46Z"},{"alias_kind":"pith_short_8","alias_value":"BJGB3XRN","created_at":"2026-07-05T11:10:46Z"}],"graph_snapshots":[{"event_id":"sha256:75f4998071a5f5a67fda4b0039fa661880199e00faa412ef038361c41395d935","target":"graph","created_at":"2026-07-05T11:10:46Z","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/2406.16508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper empirically investigates the relationship between subword vocabulary size and the performance of large language models (LLMs) to provide insights on how to define the vocabulary size. Experimental results show that larger vocabulary sizes lead to better performance in LLMs. Moreover, we consider a continual training scenario where a pre-trained language model is trained on a different target language. We introduce a simple method to use a new vocabulary instead of the pre-defined one. We show that using the new vocabulary outperforms the model with the vocabulary used in pre-trainin","authors_text":"Ryokan Ri, Sho Takase, Shun Kiyono, Takuya Kato","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T10:27:07Z","title":"Large Vocabulary Size Improves Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16508","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":"sha256:521a7bc68a0ee6b43274ec573713529d53d11f697c8ff10f556575410d520e51","target":"record","created_at":"2026-07-05T11:10:46Z","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":"1923d3c093f78996be19c57cf32701e20754d6ae990c2bdab97cc8fa8b3ef7af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T10:27:07Z","title_canon_sha256":"3200608ed0d49c8e146769109a849917b6fd1794dad0d28c384f352c56313655"},"schema_version":"1.0","source":{"id":"2406.16508","kind":"arxiv","version":2}},"canonical_sha256":"0a4c1dde2de751176abbf6763cd08dbefd3310da85198874b19d4ff8eb8132f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a4c1dde2de751176abbf6763cd08dbefd3310da85198874b19d4ff8eb8132f2","first_computed_at":"2026-07-05T11:10:46.282672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:46.282672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MYRZWmgmFwhLD/RPRj5FTbBxS30PjWc1aylpf4OAhH2MdVr5DZU804DtKXNeVOZG4+0QdiYwTN5nwWR4tYbrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:46.283196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:521a7bc68a0ee6b43274ec573713529d53d11f697c8ff10f556575410d520e51","sha256:75f4998071a5f5a67fda4b0039fa661880199e00faa412ef038361c41395d935"],"state_sha256":"cb65aadf94ea9487e15d4e77383a9c6978b3d66f8af4b75377676b511df7339e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s6sUWDkmUS8672aWo2VEAqvt0BvdbYTg9JK5RJTGf5o81bRvhUbUxKbBDPEd40RB02hZfVrGq9UGiG8S7P4WAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:09:14.447043Z","bundle_sha256":"580432c62da2feadc8ade5930b09366d03d71eabc11c4db4fbd2b7aa5431a455"}}