{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZXJKOOT7JM2YL2VT6TSN7ZTK7E","short_pith_number":"pith:ZXJKOOT7","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"},"canonical_sha256":"cdd2a73a7f4b3585eab3f4e4dfe66af9302ba8b68b15bf32bec0195019d3cdad","source":{"kind":"arxiv","id":"2305.13026","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13026","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13026v2","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13026","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZXJKOOT7JM2Y","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZXJKOOT7JM2YL2VT","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZXJKOOT7","created_at":"2026-07-05T07:00:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZXJKOOT7JM2YL2VT6TSN7ZTK7E","target":"record","payload":{"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"},"canonical_sha256":"cdd2a73a7f4b3585eab3f4e4dfe66af9302ba8b68b15bf32bec0195019d3cdad","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"},"source_kind":"arxiv","source_id":"2305.13026","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WlRV2DasPjcN5WHDaeFrzKKgYHzCEzz4VkchVLyNCz6GpNKGO6fMUUFtnbJfFLsE1YhMrGG6Ta+j984d470eCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:57.412872Z"},"content_sha256":"42bf86d269efbba4b3eb365eb80c64e4a892f795c9df9dab140db3d6b7cfbd8e","schema_version":"1.0","event_id":"sha256:42bf86d269efbba4b3eb365eb80c64e4a892f795c9df9dab140db3d6b7cfbd8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZXJKOOT7JM2YL2VT6TSN7ZTK7E","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sI6gIGquh6hrjLS+kCs9iHdtMV1w4vLF8c6z04pC6AVlslAd/FSOC2gsQEN8UW1tll6bbJ/vDapNsWIpIGB5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:57.413365Z"},"content_sha256":"4a57a87fc978109a068b73761319c18533524fa44dc1ea0e3baa10f9d3b40783","schema_version":"1.0","event_id":"sha256:4a57a87fc978109a068b73761319c18533524fa44dc1ea0e3baa10f9d3b40783"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/bundle.json","state_url":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T16:57:57Z","links":{"resolver":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E","bundle":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/bundle.json","state":"https://pith.science/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXJKOOT7JM2YL2VT6TSN7ZTK7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZXJKOOT7JM2YL2VT6TSN7ZTK7E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bd59078ebb9561df42dc88e449d7a11c19930aa2c4a73a5be811a79a94d0f9f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T13:27:37Z","title_canon_sha256":"a0d89041865c4e44da1829deffcd5b12cde5a8e00098b30757059ace98071fed"},"schema_version":"1.0","source":{"id":"2305.13026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13026","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13026v2","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13026","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZXJKOOT7JM2Y","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZXJKOOT7JM2YL2VT","created_at":"2026-07-05T07:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZXJKOOT7","created_at":"2026-07-05T07:00:23Z"}],"graph_snapshots":[{"event_id":"sha256:4a57a87fc978109a068b73761319c18533524fa44dc1ea0e3baa10f9d3b40783","target":"graph","created_at":"2026-07-05T07:00:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.13026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Malvina Nissim, Martijn Wieling, Wietse de Vries","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T13:27:37Z","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13026","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:42bf86d269efbba4b3eb365eb80c64e4a892f795c9df9dab140db3d6b7cfbd8e","target":"record","created_at":"2026-07-05T07:00:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bd59078ebb9561df42dc88e449d7a11c19930aa2c4a73a5be811a79a94d0f9f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T13:27:37Z","title_canon_sha256":"a0d89041865c4e44da1829deffcd5b12cde5a8e00098b30757059ace98071fed"},"schema_version":"1.0","source":{"id":"2305.13026","kind":"arxiv","version":2}},"canonical_sha256":"cdd2a73a7f4b3585eab3f4e4dfe66af9302ba8b68b15bf32bec0195019d3cdad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdd2a73a7f4b3585eab3f4e4dfe66af9302ba8b68b15bf32bec0195019d3cdad","first_computed_at":"2026-07-05T07:00:23.574061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:23.574061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s7fePz5xL8OR/V/J4GF2qqnOeiABUNZ/UdOzrN3gprjjcFNn5hsLzGeU77cP5QlGu6kV8ijsAroU1eO4jojWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:23.574598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42bf86d269efbba4b3eb365eb80c64e4a892f795c9df9dab140db3d6b7cfbd8e","sha256:4a57a87fc978109a068b73761319c18533524fa44dc1ea0e3baa10f9d3b40783"],"state_sha256":"19446035a77edf7db5a6b695db13e044523e69c3f42ef5353154be49147c3322"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"azFMC+i7qreDbxjUiKhTewn19aVYlG5iH5vo7VFPyVKH2imcXtz/SerBbevuCzAVNs/6XwjDkKhhHPtvUIMbBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:57:57.417859Z","bundle_sha256":"f08c91fd88c04178d4f3072eb70f9e0f96c5be5ca0bc6dc14850dbbd588c1f63"}}