{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ROGZYKTO2QEXB6TZ42PQP6IUMU","short_pith_number":"pith:ROGZYKTO","schema_version":"1.0","canonical_sha256":"8b8d9c2a6ed40970fa79e69f07f9146538ede82d3cbeb611e15fab7e5b59080c","source":{"kind":"arxiv","id":"2007.01658","version":1},"attestation_state":"computed","paper":{"title":"Playing with Words at the National Library of Sweden -- Making a Swedish BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Haffenden, Love B\\\"orjeson, Martin Malmsten","submitted_at":"2020-07-03T12:53:39Z","abstract_excerpt":"This paper introduces the Swedish BERT (\"KB-BERT\") developed by the KBLab for data-driven research at the National Library of Sweden (KB). Building on recent efforts to create transformer-based BERT models for languages other than English, we explain how we used KB's collections to create and train a new language-specific BERT model for Swedish. We also present the results of our model in comparison with existing models - chiefly that produced by the Swedish Public Employment Service, Arbetsf\\\"ormedlingen, and Google's multilingual M-BERT - where we demonstrate that KB-BERT outperforms these i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.01658","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-07-03T12:53:39Z","cross_cats_sorted":[],"title_canon_sha256":"8cb82944c01ca625189f020999fdaae4d2cbe9be4cdae5acc3f4eab11d270304","abstract_canon_sha256":"c7c859b360b05fb8e0429960fdb72f2a7a6455ffe9065541230ef92d0100c1bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:03.843863Z","signature_b64":"1z1YDJNweA7tWBegagegkGLDtMwjXJx9Un1hpaTHBGhRaYAWy6dECKrKeJu3dbcqHiZlqMKJ6IgzdBMfVYeKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b8d9c2a6ed40970fa79e69f07f9146538ede82d3cbeb611e15fab7e5b59080c","last_reissued_at":"2026-07-05T01:16:03.843380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:03.843380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Playing with Words at the National Library of Sweden -- Making a Swedish BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Haffenden, Love B\\\"orjeson, Martin Malmsten","submitted_at":"2020-07-03T12:53:39Z","abstract_excerpt":"This paper introduces the Swedish BERT (\"KB-BERT\") developed by the KBLab for data-driven research at the National Library of Sweden (KB). Building on recent efforts to create transformer-based BERT models for languages other than English, we explain how we used KB's collections to create and train a new language-specific BERT model for Swedish. We also present the results of our model in comparison with existing models - chiefly that produced by the Swedish Public Employment Service, Arbetsf\\\"ormedlingen, and Google's multilingual M-BERT - where we demonstrate that KB-BERT outperforms these i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01658","kind":"arxiv","version":1},"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/2007.01658/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.01658","created_at":"2026-07-05T01:16:03.843470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01658v1","created_at":"2026-07-05T01:16:03.843470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01658","created_at":"2026-07-05T01:16:03.843470+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROGZYKTO2QEX","created_at":"2026-07-05T01:16:03.843470+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROGZYKTO2QEXB6TZ","created_at":"2026-07-05T01:16:03.843470+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROGZYKTO","created_at":"2026-07-05T01:16:03.843470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02466","citing_title":"ATLAS: Article Tracking, Linking, and Analysis of Swedish Encyclopedias","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU","json":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU.json","graph_json":"https://pith.science/api/pith-number/ROGZYKTO2QEXB6TZ42PQP6IUMU/graph.json","events_json":"https://pith.science/api/pith-number/ROGZYKTO2QEXB6TZ42PQP6IUMU/events.json","paper":"https://pith.science/paper/ROGZYKTO"},"agent_actions":{"view_html":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU","download_json":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU.json","view_paper":"https://pith.science/paper/ROGZYKTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01658&json=true","fetch_graph":"https://pith.science/api/pith-number/ROGZYKTO2QEXB6TZ42PQP6IUMU/graph.json","fetch_events":"https://pith.science/api/pith-number/ROGZYKTO2QEXB6TZ42PQP6IUMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU/action/storage_attestation","attest_author":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU/action/author_attestation","sign_citation":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU/action/citation_signature","submit_replication":"https://pith.science/pith/ROGZYKTO2QEXB6TZ42PQP6IUMU/action/replication_record"}},"created_at":"2026-07-05T01:16:03.843470+00:00","updated_at":"2026-07-05T01:16:03.843470+00:00"}