{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MTY6RO7QNHQVQDF4WVAZBBZLJO","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":"8bb9ed3a5ab49749f76fbb721804f4f8e2372883377508f66e60337a7d2684a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T12:26:02Z","title_canon_sha256":"03343db0a3048018b4b7f41b08a710d2031cce3def75ca59e3b30a0b3255c2d4"},"schema_version":"1.0","source":{"id":"2112.06598","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06598","created_at":"2026-07-05T04:56:13Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06598v2","created_at":"2026-07-05T04:56:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06598","created_at":"2026-07-05T04:56:13Z"},{"alias_kind":"pith_short_12","alias_value":"MTY6RO7QNHQV","created_at":"2026-07-05T04:56:13Z"},{"alias_kind":"pith_short_16","alias_value":"MTY6RO7QNHQVQDF4","created_at":"2026-07-05T04:56:13Z"},{"alias_kind":"pith_short_8","alias_value":"MTY6RO7Q","created_at":"2026-07-05T04:56:13Z"}],"graph_snapshots":[{"event_id":"sha256:c42927d6455d03c7a737bdf407eb65519b1279d677b3fe2ca84ee55d03ee1909","target":"graph","created_at":"2026-07-05T04:56:13Z","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/2112.06598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pretrained language models (LMs) have become the central building block of many NLP applications. Training these models requires ever more computational resources and most of the existing models are trained on English text only. It is exceedingly expensive to train these models in other languages. To alleviate this problem, we introduce a novel method -- called WECHSEL -- to efficiently and effectively transfer pretrained LMs to new languages. WECHSEL can be applied to any model which uses subword-based tokenization and learns an embedding for each subword. The tokenizer of the source mo","authors_text":"Benjamin Minixhofer, Fabian Paischer, Navid Rekabsaz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T12:26:02Z","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06598","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":"sha256:3889030ef4e52e17049ced9e115d0f93d44b917a6dc0e16e87c93094fcd89564","target":"record","created_at":"2026-07-05T04:56:13Z","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":"8bb9ed3a5ab49749f76fbb721804f4f8e2372883377508f66e60337a7d2684a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T12:26:02Z","title_canon_sha256":"03343db0a3048018b4b7f41b08a710d2031cce3def75ca59e3b30a0b3255c2d4"},"schema_version":"1.0","source":{"id":"2112.06598","kind":"arxiv","version":2}},"canonical_sha256":"64f1e8bbf069e1580cbcb54190872b4b801d595275975e6a99d7b86b276a5615","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64f1e8bbf069e1580cbcb54190872b4b801d595275975e6a99d7b86b276a5615","first_computed_at":"2026-07-05T04:56:13.694737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:56:13.694737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aW8YFWgYRFnE8CYPUBJPJEbP0t2oLJi3O8aTGBrtZtnRL5563s9ipCIQL8SeO2Z/UliXTy+CnVRv3QRcUxmEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:56:13.695130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06598","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3889030ef4e52e17049ced9e115d0f93d44b917a6dc0e16e87c93094fcd89564","sha256:c42927d6455d03c7a737bdf407eb65519b1279d677b3fe2ca84ee55d03ee1909"],"state_sha256":"bbe64cf4c1036bd7069841669bb0eb63f809fa1900bcd5471e62fd79938862c0"}