{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6YPOQIXI33YPBHTXDDYOHWOEV6","short_pith_number":"pith:6YPOQIXI","schema_version":"1.0","canonical_sha256":"f61ee822e8def0f09e7718f0e3d9c4afb3f55e3148e5fe05cf70b377b592ee95","source":{"kind":"arxiv","id":"2410.03730","version":3},"attestation_state":"computed","paper":{"title":"Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Arno Weber, Alex Jude, Andreas Herten, Anirban Bhowmick, Benny J\\\"org Stein, Carolin Penke, Charvi Jain, Chelsea John, Daniel Steinigen, Fabian K\\\"uch, Fabio Barth, Georg Rehm, Hammam Abdelwahab, Ines Wendler, Jan Ebert, Jasper Schulze Buschhoff, Joachim k\\\"ohler, Johannes Leveling, Karl-Heinz Sylla, Katrin Klug, Klaudia Thellmann, Lalith Manjunath, Lena Jurkschat, Lennard Helmer, Lucas Weber, Malte Ostendorff, Max L\\\"ubbering, Mehdi Ali, Michael Fromm, Nicolas Flores-Herr, Nicolo' Brandizzi, Oleg Filatov, Paramita Mirza, Pavel Denisov, Pedro Ortiz Suarez, Qasid Saleem, Rafet Sifa, Ren\\'e J\\\"akel, Richard Rutmann, Samuel Weinbach, Stefan Kesselheim","submitted_at":"2024-09-30T16:05:38Z","abstract_excerpt":"We present two multilingual LLMs, Teuken 7B-base and Teuken 7B-instruct, designed to embrace Europe's linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English data and utilizing a custom multilingual tokenizer, our models address the limitations of existing LLMs that predominantly focus on English or a few high-resource languages. We detail the models' development principles, i.e., data composition, tokenizer optimization, and training methodologies. The models demonstrate strong performance across multilingual b"},"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":"2410.03730","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T16:05:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"17d05f3f4136ab7b9822591bc38d55886911643444ef84b9680166752cc92cc8","abstract_canon_sha256":"a7011831140772b142d4de89bc8580964770b1819cc25f9525231d45ee59e748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:50.202938Z","signature_b64":"+j+30gsJBtT2vAtToI6YY7+j4T+Dlu6Wi5bgNb2aD1UeCoh5qSsokn35ine14LUsLD7KoBkoV78YjFu386hMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f61ee822e8def0f09e7718f0e3d9c4afb3f55e3148e5fe05cf70b377b592ee95","last_reissued_at":"2026-07-05T11:56:50.202247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:50.202247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Arno Weber, Alex Jude, Andreas Herten, Anirban Bhowmick, Benny J\\\"org Stein, Carolin Penke, Charvi Jain, Chelsea John, Daniel Steinigen, Fabian K\\\"uch, Fabio Barth, Georg Rehm, Hammam Abdelwahab, Ines Wendler, Jan Ebert, Jasper Schulze Buschhoff, Joachim k\\\"ohler, Johannes Leveling, Karl-Heinz Sylla, Katrin Klug, Klaudia Thellmann, Lalith Manjunath, Lena Jurkschat, Lennard Helmer, Lucas Weber, Malte Ostendorff, Max L\\\"ubbering, Mehdi Ali, Michael Fromm, Nicolas Flores-Herr, Nicolo' Brandizzi, Oleg Filatov, Paramita Mirza, Pavel Denisov, Pedro Ortiz Suarez, Qasid Saleem, Rafet Sifa, Ren\\'e J\\\"akel, Richard Rutmann, Samuel Weinbach, Stefan Kesselheim","submitted_at":"2024-09-30T16:05:38Z","abstract_excerpt":"We present two multilingual LLMs, Teuken 7B-base and Teuken 7B-instruct, designed to embrace Europe's linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English data and utilizing a custom multilingual tokenizer, our models address the limitations of existing LLMs that predominantly focus on English or a few high-resource languages. We detail the models' development principles, i.e., data composition, tokenizer optimization, and training methodologies. The models demonstrate strong performance across multilingual b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03730","kind":"arxiv","version":3},"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/2410.03730/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":"2410.03730","created_at":"2026-07-05T11:56:50.202325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03730v3","created_at":"2026-07-05T11:56:50.202325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03730","created_at":"2026-07-05T11:56:50.202325+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YPOQIXI33YP","created_at":"2026-07-05T11:56:50.202325+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YPOQIXI33YPBHTX","created_at":"2026-07-05T11:56:50.202325+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YPOQIXI","created_at":"2026-07-05T11:56:50.202325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.10013","citing_title":"Training LLMs on HPC Systems: Best Practices from the OpenGPT-X Project","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08182","citing_title":"TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05662","citing_title":"XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6","json":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6.json","graph_json":"https://pith.science/api/pith-number/6YPOQIXI33YPBHTXDDYOHWOEV6/graph.json","events_json":"https://pith.science/api/pith-number/6YPOQIXI33YPBHTXDDYOHWOEV6/events.json","paper":"https://pith.science/paper/6YPOQIXI"},"agent_actions":{"view_html":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6","download_json":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6.json","view_paper":"https://pith.science/paper/6YPOQIXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03730&json=true","fetch_graph":"https://pith.science/api/pith-number/6YPOQIXI33YPBHTXDDYOHWOEV6/graph.json","fetch_events":"https://pith.science/api/pith-number/6YPOQIXI33YPBHTXDDYOHWOEV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6/action/storage_attestation","attest_author":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6/action/author_attestation","sign_citation":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6/action/citation_signature","submit_replication":"https://pith.science/pith/6YPOQIXI33YPBHTXDDYOHWOEV6/action/replication_record"}},"created_at":"2026-07-05T11:56:50.202325+00:00","updated_at":"2026-07-05T11:56:50.202325+00:00"}