{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KM4FGGRJVRED5ZFPLRS5RKHD4A","short_pith_number":"pith:KM4FGGRJ","schema_version":"1.0","canonical_sha256":"5338531a29ac483ee4af5c65d8a8e3e0180dab33ef7b7e15ec70dc1a36ce807c","source":{"kind":"arxiv","id":"2104.06546","version":1},"attestation_state":"computed","paper":{"title":"Large-Scale Contextualised Language Modelling for Norwegian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrey Kutuzov, Erik Velldal, Jeremy Barnes, Lilja {\\O}vrelid, Stephan Oepen","submitted_at":"2021-04-13T23:18:04Z","abstract_excerpt":"We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, mode"},"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":"2104.06546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-13T23:18:04Z","cross_cats_sorted":[],"title_canon_sha256":"cf29ec9ad24175120e26cf5b281e073b8ed74dc546eb3d8d69571f3b0f7df06e","abstract_canon_sha256":"f0584635073ff1e775283c7f20445c19ec52871588c2098d65bfea5514a9273d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:06.831475Z","signature_b64":"JcclHGTCdyIRdVxIJUoD0EZubtwtYRa8NDHmjPB3Zd0itBXfkhZ+1E0wEa3h7PRGEQ75a68scUzfISgiegYECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5338531a29ac483ee4af5c65d8a8e3e0180dab33ef7b7e15ec70dc1a36ce807c","last_reissued_at":"2026-07-05T02:32:06.831040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:06.831040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Contextualised Language Modelling for Norwegian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrey Kutuzov, Erik Velldal, Jeremy Barnes, Lilja {\\O}vrelid, Stephan Oepen","submitted_at":"2021-04-13T23:18:04Z","abstract_excerpt":"We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06546","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/2104.06546/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":"2104.06546","created_at":"2026-07-05T02:32:06.831097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06546v1","created_at":"2026-07-05T02:32:06.831097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06546","created_at":"2026-07-05T02:32:06.831097+00:00"},{"alias_kind":"pith_short_12","alias_value":"KM4FGGRJVRED","created_at":"2026-07-05T02:32:06.831097+00:00"},{"alias_kind":"pith_short_16","alias_value":"KM4FGGRJVRED5ZFP","created_at":"2026-07-05T02:32:06.831097+00:00"},{"alias_kind":"pith_short_8","alias_value":"KM4FGGRJ","created_at":"2026-07-05T02:32:06.831097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15734","citing_title":"Development of Pre-Trained Transformer-based Models for the Nepali Language","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A","json":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A.json","graph_json":"https://pith.science/api/pith-number/KM4FGGRJVRED5ZFPLRS5RKHD4A/graph.json","events_json":"https://pith.science/api/pith-number/KM4FGGRJVRED5ZFPLRS5RKHD4A/events.json","paper":"https://pith.science/paper/KM4FGGRJ"},"agent_actions":{"view_html":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A","download_json":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A.json","view_paper":"https://pith.science/paper/KM4FGGRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06546&json=true","fetch_graph":"https://pith.science/api/pith-number/KM4FGGRJVRED5ZFPLRS5RKHD4A/graph.json","fetch_events":"https://pith.science/api/pith-number/KM4FGGRJVRED5ZFPLRS5RKHD4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A/action/storage_attestation","attest_author":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A/action/author_attestation","sign_citation":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A/action/citation_signature","submit_replication":"https://pith.science/pith/KM4FGGRJVRED5ZFPLRS5RKHD4A/action/replication_record"}},"created_at":"2026-07-05T02:32:06.831097+00:00","updated_at":"2026-07-05T02:32:06.831097+00:00"}