{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TBY3CWQQDLXYDPHVK7FO7FMS2W","short_pith_number":"pith:TBY3CWQQ","schema_version":"1.0","canonical_sha256":"9871b15a101aef81bcf557caef9592d58db477d57aa922fc51b8f2888e6c5cc1","source":{"kind":"arxiv","id":"2408.15040","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Large Language Models for European Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sampo Pyysalo, Wazir Ali","submitted_at":"2024-08-27T13:10:05Z","abstract_excerpt":"Large Language Models (LLMs) have gained significant attention due to their high performance on a wide range of natural language tasks since the release of ChatGPT. The LLMs learn to understand and generate language by training billions of model parameters on vast volumes of text data. Despite being a relatively new field, LLM research is rapidly advancing in various directions. In this paper, we present an overview of LLM families, including LLaMA, PaLM, GPT, and MoE, and the methods developed to create and enhance LLMs for official European Union (EU) languages. We provide a comprehensive su"},"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":"2408.15040","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T13:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"468be1d542d03b59f60462debe8c5f9d62892e36bb2b516eb2f499a8a23d3432","abstract_canon_sha256":"3fa10874bd16aefd981e556d25a550d45c9634f311bec19f0fd9d4bd292ba1a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:08.714928Z","signature_b64":"B837MOzObSOtmXO8j+c3cYkCY58JTEBd6QvPQ5mKbzSLZjIskvt1j45bNbb9EhZevGCbP2hJA/62AYf1c+MSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9871b15a101aef81bcf557caef9592d58db477d57aa922fc51b8f2888e6c5cc1","last_reissued_at":"2026-07-05T09:00:08.714376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:08.714376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Large Language Models for European Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sampo Pyysalo, Wazir Ali","submitted_at":"2024-08-27T13:10:05Z","abstract_excerpt":"Large Language Models (LLMs) have gained significant attention due to their high performance on a wide range of natural language tasks since the release of ChatGPT. The LLMs learn to understand and generate language by training billions of model parameters on vast volumes of text data. Despite being a relatively new field, LLM research is rapidly advancing in various directions. In this paper, we present an overview of LLM families, including LLaMA, PaLM, GPT, and MoE, and the methods developed to create and enhance LLMs for official European Union (EU) languages. We provide a comprehensive su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15040","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/2408.15040/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":"2408.15040","created_at":"2026-07-05T09:00:08.714447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15040v2","created_at":"2026-07-05T09:00:08.714447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15040","created_at":"2026-07-05T09:00:08.714447+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBY3CWQQDLXY","created_at":"2026-07-05T09:00:08.714447+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBY3CWQQDLXYDPHV","created_at":"2026-07-05T09:00:08.714447+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBY3CWQQ","created_at":"2026-07-05T09:00:08.714447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W","json":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W.json","graph_json":"https://pith.science/api/pith-number/TBY3CWQQDLXYDPHVK7FO7FMS2W/graph.json","events_json":"https://pith.science/api/pith-number/TBY3CWQQDLXYDPHVK7FO7FMS2W/events.json","paper":"https://pith.science/paper/TBY3CWQQ"},"agent_actions":{"view_html":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W","download_json":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W.json","view_paper":"https://pith.science/paper/TBY3CWQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15040&json=true","fetch_graph":"https://pith.science/api/pith-number/TBY3CWQQDLXYDPHVK7FO7FMS2W/graph.json","fetch_events":"https://pith.science/api/pith-number/TBY3CWQQDLXYDPHVK7FO7FMS2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W/action/storage_attestation","attest_author":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W/action/author_attestation","sign_citation":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W/action/citation_signature","submit_replication":"https://pith.science/pith/TBY3CWQQDLXYDPHVK7FO7FMS2W/action/replication_record"}},"created_at":"2026-07-05T09:00:08.714447+00:00","updated_at":"2026-07-05T09:00:08.714447+00:00"}