{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JJ5IG3H3E7SMGPSUEK3P7XVD5Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9b138b9963390f27522295e09a3b01215646425b1252ba428a29e318ac8e914f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T17:17:55Z","title_canon_sha256":"36e869cf50f865997516cb699570d2475613380c1996cbb32ed1d0dca9747345"},"schema_version":"1.0","source":{"id":"2402.00786","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00786","created_at":"2026-07-05T10:46:36Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00786v5","created_at":"2026-07-05T10:46:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00786","created_at":"2026-07-05T10:46:36Z"},{"alias_kind":"pith_short_12","alias_value":"JJ5IG3H3E7SM","created_at":"2026-07-05T10:46:36Z"},{"alias_kind":"pith_short_16","alias_value":"JJ5IG3H3E7SMGPSU","created_at":"2026-07-05T10:46:36Z"},{"alias_kind":"pith_short_8","alias_value":"JJ5IG3H3","created_at":"2026-07-05T10:46:36Z"}],"graph_snapshots":[{"event_id":"sha256:a2698875be2b4ac06a2a7e09ff381c0881622b0bca97b41c690a8b82f65a4f65","target":"graph","created_at":"2026-07-05T10:46:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.00786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T17:17:55Z","title":"CroissantLLM: A Truly Bilingual French-English Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00786","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d6da411030fb52cfeb6189e7b47c993e42f67177113112ae6a10d58c5cfc5de0","target":"record","created_at":"2026-07-05T10:46:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9b138b9963390f27522295e09a3b01215646425b1252ba428a29e318ac8e914f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T17:17:55Z","title_canon_sha256":"36e869cf50f865997516cb699570d2475613380c1996cbb32ed1d0dca9747345"},"schema_version":"1.0","source":{"id":"2402.00786","kind":"arxiv","version":5}},"canonical_sha256":"4a7a836cfb27e4c33e5422b6ffdea3ee7a2767077ba3f7658fe97e2272adace7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a7a836cfb27e4c33e5422b6ffdea3ee7a2767077ba3f7658fe97e2272adace7","first_computed_at":"2026-07-05T10:46:36.167764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:36.167764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ii0+hY9MH3Ko8/VC5OzKBsjQpWP72ZVDRE9A80/qSUhHP6TUcdxfoLumP6q4aEFB/m2KR/4geAnS+qILu9JtDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:36.168253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00786","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6da411030fb52cfeb6189e7b47c993e42f67177113112ae6a10d58c5cfc5de0","sha256:a2698875be2b4ac06a2a7e09ff381c0881622b0bca97b41c690a8b82f65a4f65"],"state_sha256":"c8c94ac3c5c95a197da31680240c06fab68b1d933ed75e55030d6a94444eeec7"}