{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:54CDTT2DU62QGWZIRPVRQOCIPV","short_pith_number":"pith:54CDTT2D","schema_version":"1.0","canonical_sha256":"ef0439cf43a7b5035b288beb1838487d5a12f3e48d97757a4981e38c7b970913","source":{"kind":"arxiv","id":"2409.16235","version":1},"attestation_state":"computed","paper":{"title":"EuroLLM: Multilingual Language Models for Europe","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Amin Farajian, Andr\\'e F. T. Martins, Barry Haddow, Duarte M. Alves, Jo\\~ao Alves, Jos\\'e G. C. de Souza, Jos\\'e Pombal, Manuel Faysse, Mateusz Klimaszewski, Nuno M. Guerreiro, Patrick Fernandes, Pedro Henrique Martins, Pierre Colombo, Ricardo Rei","submitted_at":"2024-09-24T16:51:36Z","abstract_excerpt":"The quality of open-weight LLMs has seen significant improvement, yet they remain predominantly focused on English. In this paper, we introduce the EuroLLM project, aimed at developing a suite of open-weight multilingual LLMs capable of understanding and generating text in all official European Union languages, as well as several additional relevant languages. We outline the progress made to date, detailing our data collection and filtering process, the development of scaling laws, the creation of our multilingual tokenizer, and the data mix and modeling configurations. Additionally, we releas"},"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":"2409.16235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T16:51:36Z","cross_cats_sorted":[],"title_canon_sha256":"591d73bbeebd0e6df5acd6d7866596efdae0451c65b09cbcabb3dbda988ac224","abstract_canon_sha256":"26626c9db5b09faa2d15489f6d8c35a4c97bf0de235f2e876b18c26c0ce59d73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:07.073589Z","signature_b64":"FqwNoBfu9tTxV6zhhe3vrVMADmCSufIj0CRqojTz5vYoPnSRHqPHRNUBGONeb1t8GdILAUi4RYMHvaPhAjQTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef0439cf43a7b5035b288beb1838487d5a12f3e48d97757a4981e38c7b970913","last_reissued_at":"2026-07-05T09:11:07.073117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:07.073117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EuroLLM: Multilingual Language Models for Europe","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Amin Farajian, Andr\\'e F. T. Martins, Barry Haddow, Duarte M. Alves, Jo\\~ao Alves, Jos\\'e G. C. de Souza, Jos\\'e Pombal, Manuel Faysse, Mateusz Klimaszewski, Nuno M. Guerreiro, Patrick Fernandes, Pedro Henrique Martins, Pierre Colombo, Ricardo Rei","submitted_at":"2024-09-24T16:51:36Z","abstract_excerpt":"The quality of open-weight LLMs has seen significant improvement, yet they remain predominantly focused on English. In this paper, we introduce the EuroLLM project, aimed at developing a suite of open-weight multilingual LLMs capable of understanding and generating text in all official European Union languages, as well as several additional relevant languages. We outline the progress made to date, detailing our data collection and filtering process, the development of scaling laws, the creation of our multilingual tokenizer, and the data mix and modeling configurations. Additionally, we releas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16235","kind":"arxiv","version":1},"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/2409.16235/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":"2409.16235","created_at":"2026-07-05T09:11:07.073169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16235v1","created_at":"2026-07-05T09:11:07.073169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16235","created_at":"2026-07-05T09:11:07.073169+00:00"},{"alias_kind":"pith_short_12","alias_value":"54CDTT2DU62Q","created_at":"2026-07-05T09:11:07.073169+00:00"},{"alias_kind":"pith_short_16","alias_value":"54CDTT2DU62QGWZI","created_at":"2026-07-05T09:11:07.073169+00:00"},{"alias_kind":"pith_short_8","alias_value":"54CDTT2D","created_at":"2026-07-05T09:11:07.073169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19100","citing_title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19100","citing_title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03773","citing_title":"KletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19100","citing_title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25846","citing_title":"On the Limits of Model Merging for Multilinguality in Pre-Training","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12227","citing_title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV","json":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV.json","graph_json":"https://pith.science/api/pith-number/54CDTT2DU62QGWZIRPVRQOCIPV/graph.json","events_json":"https://pith.science/api/pith-number/54CDTT2DU62QGWZIRPVRQOCIPV/events.json","paper":"https://pith.science/paper/54CDTT2D"},"agent_actions":{"view_html":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV","download_json":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV.json","view_paper":"https://pith.science/paper/54CDTT2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16235&json=true","fetch_graph":"https://pith.science/api/pith-number/54CDTT2DU62QGWZIRPVRQOCIPV/graph.json","fetch_events":"https://pith.science/api/pith-number/54CDTT2DU62QGWZIRPVRQOCIPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/action/storage_attestation","attest_author":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/action/author_attestation","sign_citation":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/action/citation_signature","submit_replication":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/action/replication_record"}},"created_at":"2026-07-05T09:11:07.073169+00:00","updated_at":"2026-07-05T09:11:07.073169+00:00"}