{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EXVW3E5424WBT7HSE3IPDVHSYG","short_pith_number":"pith:EXVW3E54","canonical_record":{"source":{"id":"2311.08849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T10:40:45Z","cross_cats_sorted":[],"title_canon_sha256":"a2cd78aec1d1d63ef60bb6cef51fa513ebac65b218d54f5c3da497e398970a3f","abstract_canon_sha256":"01d5022287a70f143e43f690995a2db7575cff45b010c24dac0beb3d981deb7d"},"schema_version":"1.0"},"canonical_sha256":"25eb6d93bcd72c19fcf226d0f1d4f2c1ad0ddf7ac5b6675134c8c8d9483de8af","source":{"kind":"arxiv","id":"2311.08849","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08849","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08849v2","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08849","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"EXVW3E5424WB","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"EXVW3E5424WBT7HS","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"EXVW3E54","created_at":"2026-07-05T07:59:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EXVW3E5424WBT7HSE3IPDVHSYG","target":"record","payload":{"canonical_record":{"source":{"id":"2311.08849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T10:40:45Z","cross_cats_sorted":[],"title_canon_sha256":"a2cd78aec1d1d63ef60bb6cef51fa513ebac65b218d54f5c3da497e398970a3f","abstract_canon_sha256":"01d5022287a70f143e43f690995a2db7575cff45b010c24dac0beb3d981deb7d"},"schema_version":"1.0"},"canonical_sha256":"25eb6d93bcd72c19fcf226d0f1d4f2c1ad0ddf7ac5b6675134c8c8d9483de8af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:57.139155Z","signature_b64":"fzsWjmeWLMCBfSqrgFOziJEB41QG/jYHS0vsV/bYCn0JE9Sr52WlwIP0RsCK4EpzEh8VqnBr8koLQ2Krs5+SCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25eb6d93bcd72c19fcf226d0f1d4f2c1ad0ddf7ac5b6675134c8c8d9483de8af","last_reissued_at":"2026-07-05T07:59:57.138586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:57.138586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.08849","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":"2026-07-05T07:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYnqGkZf1Zou6bHz/Fi2GackQLTkyYQs1XDfwd/dfHuFPQWyY9H3GOPi4y9+kW3+QT/FgD7Rf5SIh5t/t+gBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:46:10.602815Z"},"content_sha256":"6acce9fd3c78daca906c7c716aaa98655c4c448a6f50e17dd0160b6344cc015d","schema_version":"1.0","event_id":"sha256:6acce9fd3c78daca906c7c716aaa98655c4c448a6f50e17dd0160b6344cc015d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EXVW3E5424WBT7HSE3IPDVHSYG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Mingyang Wang, Peiqin Lin, Yihong Liu","submitted_at":"2023-11-15T10:40:45Z","abstract_excerpt":"Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining. However, this method usually randomly initializes the embeddings of new subwords and introduces substantially more embedding parameters to the model, thus weakening the efficiency. To address these issues, we propose a novel framework: $\\textbf{O}$ne $\\textbf{F}$or $\\textbf{A}$ll ($\\textbf{OFA}$), which wisely initializes the embeddings of unseen subwords and thus can adapt a PLM to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08849","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/2311.08849/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":"2026-07-05T07:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B+NHndvTnQYLCu/A4rGRG+KWNUGKXGoT6a4i9h+NhBnYXmL9WoXh4HZAL/5yg9LRq7bqfPTXEJe9WsEubw/6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:46:10.603199Z"},"content_sha256":"ed359bbe51e0c3c6e439bbf93917cc0608ea0212c7460be3f8076fddb24ee4c7","schema_version":"1.0","event_id":"sha256:ed359bbe51e0c3c6e439bbf93917cc0608ea0212c7460be3f8076fddb24ee4c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXVW3E5424WBT7HSE3IPDVHSYG/bundle.json","state_url":"https://pith.science/pith/EXVW3E5424WBT7HSE3IPDVHSYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXVW3E5424WBT7HSE3IPDVHSYG/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":"2026-08-21T15:46:10Z","links":{"resolver":"https://pith.science/pith/EXVW3E5424WBT7HSE3IPDVHSYG","bundle":"https://pith.science/pith/EXVW3E5424WBT7HSE3IPDVHSYG/bundle.json","state":"https://pith.science/pith/EXVW3E5424WBT7HSE3IPDVHSYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXVW3E5424WBT7HSE3IPDVHSYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EXVW3E5424WBT7HSE3IPDVHSYG","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":"01d5022287a70f143e43f690995a2db7575cff45b010c24dac0beb3d981deb7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T10:40:45Z","title_canon_sha256":"a2cd78aec1d1d63ef60bb6cef51fa513ebac65b218d54f5c3da497e398970a3f"},"schema_version":"1.0","source":{"id":"2311.08849","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08849","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08849v2","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08849","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"EXVW3E5424WB","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"EXVW3E5424WBT7HS","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"EXVW3E54","created_at":"2026-07-05T07:59:57Z"}],"graph_snapshots":[{"event_id":"sha256:ed359bbe51e0c3c6e439bbf93917cc0608ea0212c7460be3f8076fddb24ee4c7","target":"graph","created_at":"2026-07-05T07:59:57Z","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/2311.08849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining. However, this method usually randomly initializes the embeddings of new subwords and introduces substantially more embedding parameters to the model, thus weakening the efficiency. To address these issues, we propose a novel framework: $\\textbf{O}$ne $\\textbf{F}$or $\\textbf{A}$ll ($\\textbf{OFA}$), which wisely initializes the embeddings of unseen subwords and thus can adapt a PLM to ","authors_text":"Hinrich Sch\\\"utze, Mingyang Wang, Peiqin Lin, Yihong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T10:40:45Z","title":"OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08849","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":"sha256:6acce9fd3c78daca906c7c716aaa98655c4c448a6f50e17dd0160b6344cc015d","target":"record","created_at":"2026-07-05T07:59:57Z","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":"01d5022287a70f143e43f690995a2db7575cff45b010c24dac0beb3d981deb7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T10:40:45Z","title_canon_sha256":"a2cd78aec1d1d63ef60bb6cef51fa513ebac65b218d54f5c3da497e398970a3f"},"schema_version":"1.0","source":{"id":"2311.08849","kind":"arxiv","version":2}},"canonical_sha256":"25eb6d93bcd72c19fcf226d0f1d4f2c1ad0ddf7ac5b6675134c8c8d9483de8af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25eb6d93bcd72c19fcf226d0f1d4f2c1ad0ddf7ac5b6675134c8c8d9483de8af","first_computed_at":"2026-07-05T07:59:57.138586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:57.138586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fzsWjmeWLMCBfSqrgFOziJEB41QG/jYHS0vsV/bYCn0JE9Sr52WlwIP0RsCK4EpzEh8VqnBr8koLQ2Krs5+SCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:57.139155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08849","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6acce9fd3c78daca906c7c716aaa98655c4c448a6f50e17dd0160b6344cc015d","sha256:ed359bbe51e0c3c6e439bbf93917cc0608ea0212c7460be3f8076fddb24ee4c7"],"state_sha256":"22454aa2053d595df5f878763915cf6521219d2a2acd626a242f58d38c16d804"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQX0egiMU7csOg8i1ymA/cCgLLDobdEj8VtQlbIvMmxxJKtD6QmjcVH0HJy7kA2lM+fpfkxR8u5oBV6DyzGWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:46:10.605894Z","bundle_sha256":"d39de64c5380c0af33cc268f2c2457f97177c9f726cde331af6917bd7eb2e54a"}}