{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZXJKOOT7JM2YL2VT6TSN7ZTK7E","short_pith_number":"pith:ZXJKOOT7","schema_version":"1.0","canonical_sha256":"cdd2a73a7f4b3585eab3f4e4dfe66af9302ba8b68b15bf32bec0195019d3cdad","source":{"kind":"arxiv","id":"2305.13026","version":2},"attestation_state":"computed","paper":{"title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Malvina Nissim, Martijn Wieling, Wietse de Vries","submitted_at":"2023-05-22T13:27:37Z","abstract_excerpt":"We introduce the Dutch Model Benchmark: DUMB. The benchmark includes a diverse set of datasets for low-, medium- and high-resource tasks. The total set of nine tasks includes four tasks that were previously not available in Dutch. Instead of relying on a mean score across tasks, we propose Relative Error Reduction (RER), which compares the DUMB performance of language models to a strong baseline which can be referred to in the future even when assessing different sets of language models. Through a comparison of 14 pre-trained language models (mono- and multi-lingual, of varying sizes), we asse"},"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":"2305.13026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T13:27:37Z","cross_cats_sorted":[],"title_canon_sha256":"a0d89041865c4e44da1829deffcd5b12cde5a8e00098b30757059ace98071fed","abstract_canon_sha256":"bd59078ebb9561df42dc88e449d7a11c19930aa2c4a73a5be811a79a94d0f9f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:23.574598Z","signature_b64":"s7fePz5xL8OR/V/J4GF2qqnOeiABUNZ/UdOzrN3gprjjcFNn5hsLzGeU77cP5QlGu6kV8ijsAroU1eO4jojWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdd2a73a7f4b3585eab3f4e4dfe66af9302ba8b68b15bf32bec0195019d3cdad","last_reissued_at":"2026-07-05T07:00:23.574061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:23.574061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Malvina Nissim, Martijn Wieling, Wietse de Vries","submitted_at":"2023-05-22T13:27:37Z","abstract_excerpt":"We introduce the Dutch Model Benchmark: DUMB. The benchmark includes a diverse set of datasets for low-, medium- and high-resource tasks. The total set of nine tasks includes four tasks that were previously not available in Dutch. Instead of relying on a mean score across tasks, we propose Relative Error Reduction (RER), which compares the DUMB performance of language models to a strong baseline which can be referred to in the future even when assessing different sets of language models. Through a comparison of 14 pre-trained language models (mono- and multi-lingual, of varying sizes), we asse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13026","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/2305.13026/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":"2305.13026","created_at":"2026-07-05T07:00:23.574122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13026v2","created_at":"2026-07-05T07:00:23.574122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13026","created_at":"2026-07-05T07:00:23.574122+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXJKOOT7JM2Y","created_at":"2026-07-05T07:00:23.574122+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXJKOOT7JM2YL2VT","created_at":"2026-07-05T07:00:23.574122+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXJKOOT7","created_at":"2026-07-05T07:00:23.574122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21508","citing_title":"skLEP: A Slovak General Language Understanding Benchmark","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E","json":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E.json","graph_json":"https://pith.science/api/pith-number/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/graph.json","events_json":"https://pith.science/api/pith-number/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/events.json","paper":"https://pith.science/paper/ZXJKOOT7"},"agent_actions":{"view_html":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E","download_json":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E.json","view_paper":"https://pith.science/paper/ZXJKOOT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13026&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/action/storage_attestation","attest_author":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/action/author_attestation","sign_citation":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/action/citation_signature","submit_replication":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/action/replication_record"}},"created_at":"2026-07-05T07:00:23.574122+00:00","updated_at":"2026-07-05T07:00:23.574122+00:00"}