{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PM442M4ELKUIJYTKA74QWFWJAN","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":"449500cb4b7a344e8fcd92ef597c58982418318a3e02d7be76152986fc451cd0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T13:34:23Z","title_canon_sha256":"3822cbc61125372b7170d49c1ed989adaebaa274db0eb32c617698714f7b3fee"},"schema_version":"1.0","source":{"id":"2412.06484","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06484","created_at":"2026-07-05T10:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06484v2","created_at":"2026-07-05T10:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06484","created_at":"2026-07-05T10:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"PM442M4ELKUI","created_at":"2026-07-05T10:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"PM442M4ELKUIJYTK","created_at":"2026-07-05T10:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"PM442M4E","created_at":"2026-07-05T10:08:25Z"}],"graph_snapshots":[{"event_id":"sha256:6d47e922167dc12175d25fdec1d934f896e9f5bc112414a45998b363e6cc4826","target":"graph","created_at":"2026-07-05T10:08:25Z","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/2412.06484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models requires vast amounts of data, posing a challenge for less widely spoken languages like Norwegian and even more so for truly low-resource languages like Northern S\\'ami. To address this issue, we present a novel three-stage continual training approach that substantially improves the downstream performance together with the inference efficiency for the target languages. Based on our findings, we train, evaluate, and openly release a new generative language model for Norwegian Bokm\\r{a}l, Nynorsk, and Northern S\\'ami with 11.4 billion parameters: NorMistral-11B.","authors_text":"Andrey Kutuzov, David Samuel, Erik Velldal, Lilja {\\O}vrelid, Lucas Georges Gabriel Charpentier, Stephan Oepen, Vladislav Mikhailov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T13:34:23Z","title":"Small Languages, Big Models: A Study of Continual Training on Languages of Norway"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06484","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":"sha256:0f4651ed678ad96e939b08321e2ab943677cfeb1dc1027efbabfb394502cfd54","target":"record","created_at":"2026-07-05T10:08:25Z","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":"449500cb4b7a344e8fcd92ef597c58982418318a3e02d7be76152986fc451cd0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T13:34:23Z","title_canon_sha256":"3822cbc61125372b7170d49c1ed989adaebaa274db0eb32c617698714f7b3fee"},"schema_version":"1.0","source":{"id":"2412.06484","kind":"arxiv","version":2}},"canonical_sha256":"7b39cd33845aa884e26a07f90b16c9037af59244d523e576636f2c2888450544","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b39cd33845aa884e26a07f90b16c9037af59244d523e576636f2c2888450544","first_computed_at":"2026-07-05T10:08:25.829224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:25.829224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RJelK4O3f69iBLhrEAG6WapaVS09QZrNkiYUIwqPS6ztAurHGLMAFvM6JGDQ2AgBq/6FUpEXKnS9mvWgfG/OAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:25.829710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06484","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f4651ed678ad96e939b08321e2ab943677cfeb1dc1027efbabfb394502cfd54","sha256:6d47e922167dc12175d25fdec1d934f896e9f5bc112414a45998b363e6cc4826"],"state_sha256":"b6f0abdcd41faa30d932a059886b3e89633309474d6e1bb0bf9687f76ac7ed90"}