{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JJ5IG3H3E7SMGPSUEK3P7XVD5Z","short_pith_number":"pith:JJ5IG3H3","schema_version":"1.0","canonical_sha256":"4a7a836cfb27e4c33e5422b6ffdea3ee7a2767077ba3f7658fe97e2272adace7","source":{"kind":"arxiv","id":"2402.00786","version":5},"attestation_state":"computed","paper":{"title":"CroissantLLM: A Truly Bilingual French-English Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F.T. Martins, Antoni Bigata Casademunt, Ant\\'onio Loison, Caio Corro, C\\'eline Hudelot, Duarte M. Alves, Fran\\c{c}ois Yvon, Gautier Viaud, Jo\\~ao Alves, Manuel Faysse, Nicolas Boizard, Nuno M. Guerreiro, Patrick Fernandes, Pedro H. Martins, Pierre Colombo, Ricardo Rei","submitted_at":"2024-02-01T17:17:55Z","abstract_excerpt":"We introduce CroissantLLM, a 1.3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully open-sourced bilingual model that runs swiftly on consumer-grade local hardware. To that end, we pioneer the approach of training an intrinsically bilingual model with a 1:1 English-to-French pretraining data ratio, a custom tokenizer, and bilingual finetuning datasets. We release the training dataset, notably containing a French split with manually curated, high-quality, and varied data sources. To assess performance "},"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":"2402.00786","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T17:17:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"36e869cf50f865997516cb699570d2475613380c1996cbb32ed1d0dca9747345","abstract_canon_sha256":"9b138b9963390f27522295e09a3b01215646425b1252ba428a29e318ac8e914f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:36.168253Z","signature_b64":"ii0+hY9MH3Ko8/VC5OzKBsjQpWP72ZVDRE9A80/qSUhHP6TUcdxfoLumP6q4aEFB/m2KR/4geAnS+qILu9JtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7a836cfb27e4c33e5422b6ffdea3ee7a2767077ba3f7658fe97e2272adace7","last_reissued_at":"2026-07-05T10:46:36.167764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:36.167764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CroissantLLM: A Truly Bilingual French-English Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F.T. Martins, Antoni Bigata Casademunt, Ant\\'onio Loison, Caio Corro, C\\'eline Hudelot, Duarte M. Alves, Fran\\c{c}ois Yvon, Gautier Viaud, Jo\\~ao Alves, Manuel Faysse, Nicolas Boizard, Nuno M. Guerreiro, Patrick Fernandes, Pedro H. Martins, Pierre Colombo, Ricardo Rei","submitted_at":"2024-02-01T17:17:55Z","abstract_excerpt":"We introduce CroissantLLM, a 1.3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully open-sourced bilingual model that runs swiftly on consumer-grade local hardware. To that end, we pioneer the approach of training an intrinsically bilingual model with a 1:1 English-to-French pretraining data ratio, a custom tokenizer, and bilingual finetuning datasets. We release the training dataset, notably containing a French split with manually curated, high-quality, and varied data sources. To assess performance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00786","kind":"arxiv","version":5},"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/2402.00786/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":"2402.00786","created_at":"2026-07-05T10:46:36.167826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00786v5","created_at":"2026-07-05T10:46:36.167826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00786","created_at":"2026-07-05T10:46:36.167826+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ5IG3H3E7SM","created_at":"2026-07-05T10:46:36.167826+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ5IG3H3E7SMGPSU","created_at":"2026-07-05T10:46:36.167826+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ5IG3H3","created_at":"2026-07-05T10:46:36.167826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01995","citing_title":"CARTE: A Benchmark for Mapping Language Model Knowledge Across France","ref_index":5,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01542","citing_title":"Mesh Based Simulations with Spatial and Temporal awareness","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z","json":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z.json","graph_json":"https://pith.science/api/pith-number/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/graph.json","events_json":"https://pith.science/api/pith-number/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/events.json","paper":"https://pith.science/paper/JJ5IG3H3"},"agent_actions":{"view_html":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z","download_json":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z.json","view_paper":"https://pith.science/paper/JJ5IG3H3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00786&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/action/storage_attestation","attest_author":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/action/author_attestation","sign_citation":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/action/citation_signature","submit_replication":"https://pith.science/pith/JJ5IG3H3E7SMGPSUEK3P7XVD5Z/action/replication_record"}},"created_at":"2026-07-05T10:46:36.167826+00:00","updated_at":"2026-07-05T10:46:36.167826+00:00"}