{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RNAUN5GQOUUCZ6LWBNSZVVS7WZ","short_pith_number":"pith:RNAUN5GQ","schema_version":"1.0","canonical_sha256":"8b4146f4d075282cf9760b659ad65fb66bdbbcea0d7e2ebe01f9a54e5a1c30c9","source":{"kind":"arxiv","id":"2312.01314","version":2},"attestation_state":"computed","paper":{"title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Even W. Lauvrak, Jon Atle Gulla, Jon Espen Ingvaldsen, Lemei Zhang, Peng Liu, Simen Eide, Terje Farup, Zhirong Yang","submitted_at":"2023-12-03T08:09:45Z","abstract_excerpt":"Norwegian, spoken by only 5 million population, is under-representative within the most impressive breakthroughs in NLP tasks. To the best of our knowledge, there has not yet been a comprehensive evaluation of the existing language models (LMs) on Norwegian generation tasks during the article writing process. To fill this gap, we 1) compiled the existing Norwegian dataset and pre-trained 4 Norwegian Open Language Models varied from parameter scales and architectures, collectively called NorGLM; 2) introduced a comprehensive benchmark, NLEBench, for evaluating natural language generation capabi"},"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":"2312.01314","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-03T08:09:45Z","cross_cats_sorted":[],"title_canon_sha256":"63b0dd5c8437ef9334b022960d85523b4244f786bf6633775e7351514cadc228","abstract_canon_sha256":"540c710d5a4e39dd3cf8ebac211fd96d8291037919c4315dda586e1b58a3a341"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:48.518616Z","signature_b64":"zhgXEaUe/us1gfA2r9uV0xcpTdzjOpdD0SQA3wVtZg7cDlPLAIL9OIMf6r7tqyDV69q0pGdGUidRf2pieR7BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b4146f4d075282cf9760b659ad65fb66bdbbcea0d7e2ebe01f9a54e5a1c30c9","last_reissued_at":"2026-07-05T09:13:48.518096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:48.518096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Even W. Lauvrak, Jon Atle Gulla, Jon Espen Ingvaldsen, Lemei Zhang, Peng Liu, Simen Eide, Terje Farup, Zhirong Yang","submitted_at":"2023-12-03T08:09:45Z","abstract_excerpt":"Norwegian, spoken by only 5 million population, is under-representative within the most impressive breakthroughs in NLP tasks. To the best of our knowledge, there has not yet been a comprehensive evaluation of the existing language models (LMs) on Norwegian generation tasks during the article writing process. To fill this gap, we 1) compiled the existing Norwegian dataset and pre-trained 4 Norwegian Open Language Models varied from parameter scales and architectures, collectively called NorGLM; 2) introduced a comprehensive benchmark, NLEBench, for evaluating natural language generation capabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01314","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/2312.01314/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":"2312.01314","created_at":"2026-07-05T09:13:48.518194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01314v2","created_at":"2026-07-05T09:13:48.518194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01314","created_at":"2026-07-05T09:13:48.518194+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNAUN5GQOUUC","created_at":"2026-07-05T09:13:48.518194+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNAUN5GQOUUCZ6LW","created_at":"2026-07-05T09:13:48.518194+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNAUN5GQ","created_at":"2026-07-05T09:13:48.518194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06652","citing_title":"When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ","json":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ.json","graph_json":"https://pith.science/api/pith-number/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/graph.json","events_json":"https://pith.science/api/pith-number/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/events.json","paper":"https://pith.science/paper/RNAUN5GQ"},"agent_actions":{"view_html":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ","download_json":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ.json","view_paper":"https://pith.science/paper/RNAUN5GQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01314&json=true","fetch_graph":"https://pith.science/api/pith-number/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/action/storage_attestation","attest_author":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/action/author_attestation","sign_citation":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/action/citation_signature","submit_replication":"https://pith.science/pith/RNAUN5GQOUUCZ6LWBNSZVVS7WZ/action/replication_record"}},"created_at":"2026-07-05T09:13:48.518194+00:00","updated_at":"2026-07-05T09:13:48.518194+00:00"}