{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ME257J3JWQOCBT52ZNGZAGRJNL","short_pith_number":"pith:ME257J3J","canonical_record":{"source":{"id":"2407.05841","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T11:38:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b06e63561c46e426d7dac84b564285ef8a06ada6d0e58dbd2c8e490614fde25a","abstract_canon_sha256":"cbfb0d9f92edc7b839cfa6136d53bf23ea3fcc0a17a3b68748a7050ecb3b4622"},"schema_version":"1.0"},"canonical_sha256":"6135dfa769b41c20cfbacb4d901a296aceffbb0cdd15af8b7398853844eec574","source":{"kind":"arxiv","id":"2407.05841","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05841","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05841v2","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05841","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"pith_short_12","alias_value":"ME257J3JWQOC","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"pith_short_16","alias_value":"ME257J3JWQOCBT52","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"pith_short_8","alias_value":"ME257J3J","created_at":"2026-07-05T09:23:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ME257J3JWQOCBT52ZNGZAGRJNL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.05841","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T11:38:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b06e63561c46e426d7dac84b564285ef8a06ada6d0e58dbd2c8e490614fde25a","abstract_canon_sha256":"cbfb0d9f92edc7b839cfa6136d53bf23ea3fcc0a17a3b68748a7050ecb3b4622"},"schema_version":"1.0"},"canonical_sha256":"6135dfa769b41c20cfbacb4d901a296aceffbb0cdd15af8b7398853844eec574","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:54.200245Z","signature_b64":"XKVBL6DOwwnOtHWXVJ+XLjhtFudtG/ieCkBAXiByM0xbMtK7hCZ/RyopCAlxA4a4bidmp7n1isUL/QzPAfKsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6135dfa769b41c20cfbacb4d901a296aceffbb0cdd15af8b7398853844eec574","last_reissued_at":"2026-07-05T09:23:54.199773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:54.199773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.05841","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":"2026-07-05T09:23:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rsBu1sIXq0okJnKSDeUqq5fElRhOpWXX6Hyv6pc5cPPUXm4YxZ6OesYC1WHx0yIeK9uBjzb7USfaU+O8KZVQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:34:37.422449Z"},"content_sha256":"aac415878ca1e55f7b732ad3750c052dfb5716c99adb6a10975e52d53b004e0b","schema_version":"1.0","event_id":"sha256:aac415878ca1e55f7b732ad3750c052dfb5716c99adb6a10975e52d53b004e0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ME257J3JWQOCBT52ZNGZAGRJNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Nanda Kishore, Anoop Kunchukuttan, Mitesh M. Khapra, Nandini Mundra, Raj Dabre, Ratish Puduppully","submitted_at":"2024-07-08T11:38:49Z","abstract_excerpt":"Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. This problem is commonly tackled by continually pre-training and fine-tuning these models for said languages. A significant issue in this process is the limited vocabulary coverage in the original model's tokenizer, leading to inadequate representation of new languages and necessitating an expansion of the tokenizer. The initialization of the embeddings corresponding to new vocabulary items presents a further challenge. Current strategies require cross-lingual embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05841","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/2407.05841/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":"2026-07-05T09:23:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SY3jfaOwMMJs9gje48KW00VtGYCYJ/CyGqm5ZM0ZNGk2orlvjT1QxBto8iEtQZt+OVOzMsNmAMVMBF/WNgmHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:34:37.423433Z"},"content_sha256":"22b61ebcb9f75da12fac1e3c8391c58b6e1ff418eaa4bf1e31fd232950334dd0","schema_version":"1.0","event_id":"sha256:22b61ebcb9f75da12fac1e3c8391c58b6e1ff418eaa4bf1e31fd232950334dd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ME257J3JWQOCBT52ZNGZAGRJNL/bundle.json","state_url":"https://pith.science/pith/ME257J3JWQOCBT52ZNGZAGRJNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ME257J3JWQOCBT52ZNGZAGRJNL/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":"2026-08-15T05:34:37Z","links":{"resolver":"https://pith.science/pith/ME257J3JWQOCBT52ZNGZAGRJNL","bundle":"https://pith.science/pith/ME257J3JWQOCBT52ZNGZAGRJNL/bundle.json","state":"https://pith.science/pith/ME257J3JWQOCBT52ZNGZAGRJNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ME257J3JWQOCBT52ZNGZAGRJNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ME257J3JWQOCBT52ZNGZAGRJNL","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":"cbfb0d9f92edc7b839cfa6136d53bf23ea3fcc0a17a3b68748a7050ecb3b4622","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T11:38:49Z","title_canon_sha256":"b06e63561c46e426d7dac84b564285ef8a06ada6d0e58dbd2c8e490614fde25a"},"schema_version":"1.0","source":{"id":"2407.05841","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05841","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05841v2","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05841","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"pith_short_12","alias_value":"ME257J3JWQOC","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"pith_short_16","alias_value":"ME257J3JWQOCBT52","created_at":"2026-07-05T09:23:54Z"},{"alias_kind":"pith_short_8","alias_value":"ME257J3J","created_at":"2026-07-05T09:23:54Z"}],"graph_snapshots":[{"event_id":"sha256:22b61ebcb9f75da12fac1e3c8391c58b6e1ff418eaa4bf1e31fd232950334dd0","target":"graph","created_at":"2026-07-05T09:23:54Z","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/2407.05841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. This problem is commonly tackled by continually pre-training and fine-tuning these models for said languages. A significant issue in this process is the limited vocabulary coverage in the original model's tokenizer, leading to inadequate representation of new languages and necessitating an expansion of the tokenizer. The initialization of the embeddings corresponding to new vocabulary items presents a further challenge. Current strategies require cross-lingual embe","authors_text":"Aditya Nanda Kishore, Anoop Kunchukuttan, Mitesh M. Khapra, Nandini Mundra, Raj Dabre, Ratish Puduppully","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T11:38:49Z","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05841","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:aac415878ca1e55f7b732ad3750c052dfb5716c99adb6a10975e52d53b004e0b","target":"record","created_at":"2026-07-05T09:23:54Z","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":"cbfb0d9f92edc7b839cfa6136d53bf23ea3fcc0a17a3b68748a7050ecb3b4622","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T11:38:49Z","title_canon_sha256":"b06e63561c46e426d7dac84b564285ef8a06ada6d0e58dbd2c8e490614fde25a"},"schema_version":"1.0","source":{"id":"2407.05841","kind":"arxiv","version":2}},"canonical_sha256":"6135dfa769b41c20cfbacb4d901a296aceffbb0cdd15af8b7398853844eec574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6135dfa769b41c20cfbacb4d901a296aceffbb0cdd15af8b7398853844eec574","first_computed_at":"2026-07-05T09:23:54.199773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:54.199773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XKVBL6DOwwnOtHWXVJ+XLjhtFudtG/ieCkBAXiByM0xbMtK7hCZ/RyopCAlxA4a4bidmp7n1isUL/QzPAfKsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:54.200245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05841","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aac415878ca1e55f7b732ad3750c052dfb5716c99adb6a10975e52d53b004e0b","sha256:22b61ebcb9f75da12fac1e3c8391c58b6e1ff418eaa4bf1e31fd232950334dd0"],"state_sha256":"dbefc94d415a8607b300434c16c607ed724d31756dd140d92b452bd6a3593210"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TX/zJ7lvSyr1TxjXep/S8Y9BxLuygNS9+P0FF1/7YmipY3UNhHUQt4GdJ9Kh5xdLC0yDPswa7yb4haJiqsBaAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T05:34:37.430198Z","bundle_sha256":"df081943d906485b66ce24e0fcb8208763224b32618be8436eeea08824c4cb19"}}