{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H4CSMV56LDZWXAW4JLXIZTMEO3","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":"00ea2ef9687980bd02031eb9b2333061538521343fdd1e7c6172c85fbf79568d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T16:16:48Z","title_canon_sha256":"aeff9ba48251f2460c7eb0787a9e6fe44bfc538c3ad7656d2d3b61ca3b659d44"},"schema_version":"1.0","source":{"id":"2403.20266","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.20266","created_at":"2026-07-05T09:09:21Z"},{"alias_kind":"arxiv_version","alias_value":"2403.20266v2","created_at":"2026-07-05T09:09:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20266","created_at":"2026-07-05T09:09:21Z"},{"alias_kind":"pith_short_12","alias_value":"H4CSMV56LDZW","created_at":"2026-07-05T09:09:21Z"},{"alias_kind":"pith_short_16","alias_value":"H4CSMV56LDZWXAW4","created_at":"2026-07-05T09:09:21Z"},{"alias_kind":"pith_short_8","alias_value":"H4CSMV56","created_at":"2026-07-05T09:09:21Z"}],"graph_snapshots":[{"event_id":"sha256:9a7a9ead3f32efb1ec819866d2d7d57b8a291bf9508825f9d9c585e917a42d63","target":"graph","created_at":"2026-07-05T09:09:21Z","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/2403.20266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Latxa, a family of large language models for Basque ranging from 7 to 70 billion parameters. Latxa is based on Llama 2, which we continue pretraining on a new Basque corpus comprising 4.3M documents and 4.2B tokens. Addressing the scarcity of high-quality benchmarks for Basque, we further introduce 4 multiple choice evaluation datasets: EusProficiency, comprising 5,169 questions from official language proficiency exams; EusReading, comprising 352 reading comprehension questions; EusTrivia, comprising 1,715 trivia questions from 5 knowledge areas; and EusExams, comprising 16,774 qu","authors_text":"Aitor Ormazabal, Aitor Soroa, Eneko Agirre, German Rigau, Itziar Aldabe, Julen Etxaniz, Mikel Artetxe, Naiara Perez, Oscar Sainz","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T16:16:48Z","title":"Latxa: An Open Language Model and Evaluation Suite for Basque"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20266","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":"sha256:47a9b99e0ad27d71a79b7d3d8f743b84867f180eb458db77f4c8f09d53a3ea10","target":"record","created_at":"2026-07-05T09:09:21Z","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":"00ea2ef9687980bd02031eb9b2333061538521343fdd1e7c6172c85fbf79568d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T16:16:48Z","title_canon_sha256":"aeff9ba48251f2460c7eb0787a9e6fe44bfc538c3ad7656d2d3b61ca3b659d44"},"schema_version":"1.0","source":{"id":"2403.20266","kind":"arxiv","version":2}},"canonical_sha256":"3f052657be58f36b82dc4aee8ccd8476ffdaad3fefc99869f3becc9ca05dd999","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f052657be58f36b82dc4aee8ccd8476ffdaad3fefc99869f3becc9ca05dd999","first_computed_at":"2026-07-05T09:09:21.221450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:21.221450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LI1yBm1SxQZ3LjxDbiLfyp1G3UM4JFZ6H5YRlCX6yo3h1ksw4gihy4R2EnREly0I5qTry0rOTHCslRgl19EeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:21.222076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.20266","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47a9b99e0ad27d71a79b7d3d8f743b84867f180eb458db77f4c8f09d53a3ea10","sha256:9a7a9ead3f32efb1ec819866d2d7d57b8a291bf9508825f9d9c585e917a42d63"],"state_sha256":"80cc820864a266d08a0dc714c902eb75be4f5281340bc241f8428aca367e629e"}