{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QEE2BRI5VQHGQ7BS3XMXNZOZZJ","short_pith_number":"pith:QEE2BRI5","schema_version":"1.0","canonical_sha256":"8109a0c51dac0e687c32ddd976e5d9ca52dbd7c6b9380d05fcf7a568e3525ca1","source":{"kind":"arxiv","id":"2306.07790","version":1},"attestation_state":"computed","paper":{"title":"NoCoLA: The Norwegian Corpus of Linguistic Acceptability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Samuel, Matias Jentoft","submitted_at":"2023-06-13T14:11:19Z","abstract_excerpt":"While there has been a surge of large language models for Norwegian in recent years, we lack any tool to evaluate their understanding of grammaticality. We present two new Norwegian datasets for this task. NoCoLA_class is a supervised binary classification task where the goal is to discriminate between acceptable and non-acceptable sentences. On the other hand, NoCoLA_zero is a purely diagnostic task for evaluating the grammatical judgement of a language model in a completely zero-shot manner, i.e. without any further training. In this paper, we describe both datasets in detail, show how to us"},"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":"2306.07790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T14:11:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ef41d594fb282f3f09a3dc6b4143f3338608ac883357c579865f3350d168ae2","abstract_canon_sha256":"d349cf4a534f35f7d03a594653f02b7fdd9b61c10413470825403f061964bf0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:08.891917Z","signature_b64":"qGxEeENfWFolxP/FKxPSf+tQzRG/z2MR/3/TJlGCO9EdLTzT8QcvIczMAT25AAYP1yVGnsKaZRea8qWxLwLZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8109a0c51dac0e687c32ddd976e5d9ca52dbd7c6b9380d05fcf7a568e3525ca1","last_reissued_at":"2026-07-05T06:20:08.891553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:08.891553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NoCoLA: The Norwegian Corpus of Linguistic Acceptability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Samuel, Matias Jentoft","submitted_at":"2023-06-13T14:11:19Z","abstract_excerpt":"While there has been a surge of large language models for Norwegian in recent years, we lack any tool to evaluate their understanding of grammaticality. We present two new Norwegian datasets for this task. NoCoLA_class is a supervised binary classification task where the goal is to discriminate between acceptable and non-acceptable sentences. On the other hand, NoCoLA_zero is a purely diagnostic task for evaluating the grammatical judgement of a language model in a completely zero-shot manner, i.e. without any further training. In this paper, we describe both datasets in detail, show how to us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07790","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/2306.07790/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":"2306.07790","created_at":"2026-07-05T06:20:08.891616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07790v1","created_at":"2026-07-05T06:20:08.891616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07790","created_at":"2026-07-05T06:20:08.891616+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEE2BRI5VQHG","created_at":"2026-07-05T06:20:08.891616+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEE2BRI5VQHGQ7BS","created_at":"2026-07-05T06:20:08.891616+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEE2BRI5","created_at":"2026-07-05T06:20:08.891616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ","json":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ.json","graph_json":"https://pith.science/api/pith-number/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/graph.json","events_json":"https://pith.science/api/pith-number/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/events.json","paper":"https://pith.science/paper/QEE2BRI5"},"agent_actions":{"view_html":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ","download_json":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ.json","view_paper":"https://pith.science/paper/QEE2BRI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07790&json=true","fetch_graph":"https://pith.science/api/pith-number/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/action/storage_attestation","attest_author":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/action/author_attestation","sign_citation":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/action/citation_signature","submit_replication":"https://pith.science/pith/QEE2BRI5VQHGQ7BS3XMXNZOZZJ/action/replication_record"}},"created_at":"2026-07-05T06:20:08.891616+00:00","updated_at":"2026-07-05T06:20:08.891616+00:00"}