{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4JDNSB675I44T437354BVDXKU2","short_pith_number":"pith:4JDNSB67","schema_version":"1.0","canonical_sha256":"e246d907dfea39c9f37fdf781a8eeaa69699e7e8732abc75202f251f0a86a872","source":{"kind":"arxiv","id":"2304.00906","version":1},"attestation_state":"computed","paper":{"title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Saattrup Nielsen","submitted_at":"2023-04-03T11:51:46Z","abstract_excerpt":"This paper introduces a Scandinavian benchmarking platform, ScandEval, which can benchmark any pretrained model on four different tasks in the Scandinavian languages. The datasets used in two of the tasks, linguistic acceptability and question answering, are new. We develop and release a Python package and command-line interface, scandeval, which can benchmark any model that has been uploaded to the Hugging Face Hub, with reproducible results. Using this package, we benchmark more than 100 Scandinavian or multilingual models and present the results of these in an interactive online leaderboard"},"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":"2304.00906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T11:51:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f5be8a404f484f588f4e99ea8bae18230cb82dc40b56cc520fdb191174fcdde","abstract_canon_sha256":"c76bbff46d904ce483573252fee319a22b33c9fc87c184cee2a7b5d711a82094"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:24.326260Z","signature_b64":"jT505AQsK5cbrH++fNiRbbtKdlHrNewKWgWtVFumoHBV0H2CGaMxn3eSGqEawZk41llpinTMxd9Pf5AA2KeTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e246d907dfea39c9f37fdf781a8eeaa69699e7e8732abc75202f251f0a86a872","last_reissued_at":"2026-07-05T05:57:24.325719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:24.325719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Saattrup Nielsen","submitted_at":"2023-04-03T11:51:46Z","abstract_excerpt":"This paper introduces a Scandinavian benchmarking platform, ScandEval, which can benchmark any pretrained model on four different tasks in the Scandinavian languages. The datasets used in two of the tasks, linguistic acceptability and question answering, are new. We develop and release a Python package and command-line interface, scandeval, which can benchmark any model that has been uploaded to the Hugging Face Hub, with reproducible results. Using this package, we benchmark more than 100 Scandinavian or multilingual models and present the results of these in an interactive online leaderboard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00906","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/2304.00906/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":"2304.00906","created_at":"2026-07-05T05:57:24.325788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00906v1","created_at":"2026-07-05T05:57:24.325788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00906","created_at":"2026-07-05T05:57:24.325788+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JDNSB675I44","created_at":"2026-07-05T05:57:24.325788+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JDNSB675I44T437","created_at":"2026-07-05T05:57:24.325788+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JDNSB67","created_at":"2026-07-05T05:57:24.325788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06888","citing_title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2","json":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2.json","graph_json":"https://pith.science/api/pith-number/4JDNSB675I44T437354BVDXKU2/graph.json","events_json":"https://pith.science/api/pith-number/4JDNSB675I44T437354BVDXKU2/events.json","paper":"https://pith.science/paper/4JDNSB67"},"agent_actions":{"view_html":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2","download_json":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2.json","view_paper":"https://pith.science/paper/4JDNSB67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00906&json=true","fetch_graph":"https://pith.science/api/pith-number/4JDNSB675I44T437354BVDXKU2/graph.json","fetch_events":"https://pith.science/api/pith-number/4JDNSB675I44T437354BVDXKU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2/action/storage_attestation","attest_author":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2/action/author_attestation","sign_citation":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2/action/citation_signature","submit_replication":"https://pith.science/pith/4JDNSB675I44T437354BVDXKU2/action/replication_record"}},"created_at":"2026-07-05T05:57:24.325788+00:00","updated_at":"2026-07-05T05:57:24.325788+00:00"}