{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TRNWMK6FQEUMUABFPW5WS6YQZJ","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":"87705771b86a4bafd9b490c1c3344c867588b7ac00e942513fbf0b1018d0ea7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T09:53:33Z","title_canon_sha256":"7e57b9ee4f691b50fda8644dcd4e8755e4d9227e7937dce6f27ef33ce29ecb82"},"schema_version":"1.0","source":{"id":"2303.09859","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09859","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09859v3","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09859","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"TRNWMK6FQEUM","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"TRNWMK6FQEUMUABF","created_at":"2026-07-05T06:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"TRNWMK6F","created_at":"2026-07-05T06:07:37Z"}],"graph_snapshots":[{"event_id":"sha256:4affe30d7308d9a36cfcb85618e144ef3fbe5a359e91e127bde8b3f27fc833bf","target":"graph","created_at":"2026-07-05T06:07:37Z","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/2303.09859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While modern masked language models (LMs) are trained on ever larger corpora, we here explore the effects of down-scaling training to a modestly-sized but representative, well-balanced, and publicly available English text source -- the British National Corpus. We show that pre-training on this carefully curated corpus can reach better performance than the original BERT model. We argue that this type of corpora has great potential as a language modeling benchmark. To showcase this potential, we present fair, reproducible and data-efficient comparative studies of LMs, in which we evaluate severa","authors_text":"Andrey Kutuzov, David Samuel, Erik Velldal, Lilja {\\O}vrelid","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T09:53:33Z","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09859","kind":"arxiv","version":3},"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":"sha256:8c61df57a6243dd37b014942d64be9aae86d8d32fc4981d41eb0f69ab9d39756","target":"record","created_at":"2026-07-05T06:07:37Z","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":"87705771b86a4bafd9b490c1c3344c867588b7ac00e942513fbf0b1018d0ea7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T09:53:33Z","title_canon_sha256":"7e57b9ee4f691b50fda8644dcd4e8755e4d9227e7937dce6f27ef33ce29ecb82"},"schema_version":"1.0","source":{"id":"2303.09859","kind":"arxiv","version":3}},"canonical_sha256":"9c5b662bc58128ca00257dbb697b10ca6f91082c10c77c4eccb1a68e726ef646","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c5b662bc58128ca00257dbb697b10ca6f91082c10c77c4eccb1a68e726ef646","first_computed_at":"2026-07-05T06:07:37.872852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:37.872852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WAYuw6kSq4I4ZMcVUkByT8F6w/05bQLBX7Z4xlyjcvJ4Fu5lqa8tI8KAErvAP/CrIqO7nQym8Og7R8q8mJ9nCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:37.873216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09859","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c61df57a6243dd37b014942d64be9aae86d8d32fc4981d41eb0f69ab9d39756","sha256:4affe30d7308d9a36cfcb85618e144ef3fbe5a359e91e127bde8b3f27fc833bf"],"state_sha256":"a0ff0b6420d2f193e7ed1331541d0d89bac8ddfe72c6fd2f103d294c01ed2225"}