{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H4CSMV56LDZWXAW4JLXIZTMEO3","short_pith_number":"pith:H4CSMV56","schema_version":"1.0","canonical_sha256":"3f052657be58f36b82dc4aee8ccd8476ffdaad3fefc99869f3becc9ca05dd999","source":{"kind":"arxiv","id":"2403.20266","version":2},"attestation_state":"computed","paper":{"title":"Latxa: An Open Language Model and Evaluation Suite for Basque","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aitor Ormazabal, Aitor Soroa, Eneko Agirre, German Rigau, Itziar Aldabe, Julen Etxaniz, Mikel Artetxe, Naiara Perez, Oscar Sainz","submitted_at":"2024-03-29T16:16:48Z","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"},"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":"2403.20266","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T16:16:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aeff9ba48251f2460c7eb0787a9e6fe44bfc538c3ad7656d2d3b61ca3b659d44","abstract_canon_sha256":"00ea2ef9687980bd02031eb9b2333061538521343fdd1e7c6172c85fbf79568d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:21.222076Z","signature_b64":"LI1yBm1SxQZ3LjxDbiLfyp1G3UM4JFZ6H5YRlCX6yo3h1ksw4gihy4R2EnREly0I5qTry0rOTHCslRgl19EeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f052657be58f36b82dc4aee8ccd8476ffdaad3fefc99869f3becc9ca05dd999","last_reissued_at":"2026-07-05T09:09:21.221450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:21.221450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latxa: An Open Language Model and Evaluation Suite for Basque","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aitor Ormazabal, Aitor Soroa, Eneko Agirre, German Rigau, Itziar Aldabe, Julen Etxaniz, Mikel Artetxe, Naiara Perez, Oscar Sainz","submitted_at":"2024-03-29T16:16:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20266","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/2403.20266/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":"2403.20266","created_at":"2026-07-05T09:09:21.221518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.20266v2","created_at":"2026-07-05T09:09:21.221518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20266","created_at":"2026-07-05T09:09:21.221518+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4CSMV56LDZW","created_at":"2026-07-05T09:09:21.221518+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4CSMV56LDZWXAW4","created_at":"2026-07-05T09:09:21.221518+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4CSMV56","created_at":"2026-07-05T09:09:21.221518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03902","citing_title":"The Harmonic Structure of Information Contours","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3","json":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3.json","graph_json":"https://pith.science/api/pith-number/H4CSMV56LDZWXAW4JLXIZTMEO3/graph.json","events_json":"https://pith.science/api/pith-number/H4CSMV56LDZWXAW4JLXIZTMEO3/events.json","paper":"https://pith.science/paper/H4CSMV56"},"agent_actions":{"view_html":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3","download_json":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3.json","view_paper":"https://pith.science/paper/H4CSMV56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.20266&json=true","fetch_graph":"https://pith.science/api/pith-number/H4CSMV56LDZWXAW4JLXIZTMEO3/graph.json","fetch_events":"https://pith.science/api/pith-number/H4CSMV56LDZWXAW4JLXIZTMEO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3/action/storage_attestation","attest_author":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3/action/author_attestation","sign_citation":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3/action/citation_signature","submit_replication":"https://pith.science/pith/H4CSMV56LDZWXAW4JLXIZTMEO3/action/replication_record"}},"created_at":"2026-07-05T09:09:21.221518+00:00","updated_at":"2026-07-05T09:09:21.221518+00:00"}