{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:B4Z3QCSCW7NRQBMAY5XCXHYQPF","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":"db119f41823b1199c31213a345d1cf018b276f490a41e03e52fbb8ccdb49dd27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T12:27:16Z","title_canon_sha256":"9435f662eca25ef49c6233dc4433d83d335d0261528c9f7b96826edb00a9b5a9"},"schema_version":"1.0","source":{"id":"2012.05628","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05628","created_at":"2026-07-05T03:02:10Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05628v3","created_at":"2026-07-05T03:02:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05628","created_at":"2026-07-05T03:02:10Z"},{"alias_kind":"pith_short_12","alias_value":"B4Z3QCSCW7NR","created_at":"2026-07-05T03:02:10Z"},{"alias_kind":"pith_short_16","alias_value":"B4Z3QCSCW7NRQBMA","created_at":"2026-07-05T03:02:10Z"},{"alias_kind":"pith_short_8","alias_value":"B4Z3QCSC","created_at":"2026-07-05T03:02:10Z"}],"graph_snapshots":[{"event_id":"sha256:82e0c9edc411432a2b8d5706b39193b828c9c02640f2e85630d4f69fab35b2cc","target":"graph","created_at":"2026-07-05T03:02:10Z","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/2012.05628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large generative language models have been very successful for English, but other languages lag behind, in part due to data and computational limitations. We propose a method that may overcome these problems by adapting existing pre-trained models to new languages. Specifically, we describe the adaptation of English GPT-2 to Italian and Dutch by retraining lexical embeddings without tuning the Transformer layers. As a result, we obtain lexical embeddings for Italian and Dutch that are aligned with the original English lexical embeddings. Additionally, we scale up complexity by transforming rel","authors_text":"Malvina Nissim, Wietse de Vries","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T12:27:16Z","title":"As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05628","kind":"arxiv","version":3},"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":"sha256:104074abcffc3fe272a0004c1cbcd30876b89db56743397e2119a0d98f45821d","target":"record","created_at":"2026-07-05T03:02:10Z","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":"db119f41823b1199c31213a345d1cf018b276f490a41e03e52fbb8ccdb49dd27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T12:27:16Z","title_canon_sha256":"9435f662eca25ef49c6233dc4433d83d335d0261528c9f7b96826edb00a9b5a9"},"schema_version":"1.0","source":{"id":"2012.05628","kind":"arxiv","version":3}},"canonical_sha256":"0f33b80a42b7db180580c76e2b9f10795a5361d970136e00037ddc9715c38eae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f33b80a42b7db180580c76e2b9f10795a5361d970136e00037ddc9715c38eae","first_computed_at":"2026-07-05T03:02:10.558400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:02:10.558400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P9sjsxTaqdI8PgJ9BU9NA7lvNReWVdrB5QMsqidKkhZ4/Hnus6DNV4LIyz3k20OUZ29+9Uu/zh3bRcFEArqdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:02:10.558845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05628","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:104074abcffc3fe272a0004c1cbcd30876b89db56743397e2119a0d98f45821d","sha256:82e0c9edc411432a2b8d5706b39193b828c9c02640f2e85630d4f69fab35b2cc"],"state_sha256":"fbda83e5279e5f1a532d478d14ce225565003138892be58dc4d0f9f76a921bd9"}