{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:54CDTT2DU62QGWZIRPVRQOCIPV","short_pith_number":"pith:54CDTT2D","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"},"canonical_sha256":"ef0439cf43a7b5035b288beb1838487d5a12f3e48d97757a4981e38c7b970913","source":{"kind":"arxiv","id":"2409.16235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16235","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16235v1","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16235","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"54CDTT2DU62Q","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"54CDTT2DU62QGWZI","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"54CDTT2D","created_at":"2026-07-05T09:11:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:54CDTT2DU62QGWZIRPVRQOCIPV","target":"record","payload":{"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"},"canonical_sha256":"ef0439cf43a7b5035b288beb1838487d5a12f3e48d97757a4981e38c7b970913","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"},"source_kind":"arxiv","source_id":"2409.16235","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kf/xG341AMzAzOcougngTbf5ZjDnFZYrMnT4PW/85SXOu/jVIJI/FWvjZROuDtZ8Kgv2d2vJlgmyLat0jgxTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:14:25.390459Z"},"content_sha256":"09f2e538fc04d106f724c7f7845322afed2c1eb5974fbae66104ff2955f692a1","schema_version":"1.0","event_id":"sha256:09f2e538fc04d106f724c7f7845322afed2c1eb5974fbae66104ff2955f692a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:54CDTT2DU62QGWZIRPVRQOCIPV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:11:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ve3RP6yH443hQNZhD5UDrfTdjrkvmIu6hZi2WgchbvZjZ7vJIRxJzOdu96hmrdu6XnEQ6rV3n9aC11o0HZvTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:14:25.390876Z"},"content_sha256":"ebad7571c689e471f7866f41dbe87a1379915ab28f368788a38d240340b226b7","schema_version":"1.0","event_id":"sha256:ebad7571c689e471f7866f41dbe87a1379915ab28f368788a38d240340b226b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/bundle.json","state_url":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54CDTT2DU62QGWZIRPVRQOCIPV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:14:25Z","links":{"resolver":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV","bundle":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/bundle.json","state":"https://pith.science/pith/54CDTT2DU62QGWZIRPVRQOCIPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54CDTT2DU62QGWZIRPVRQOCIPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:54CDTT2DU62QGWZIRPVRQOCIPV","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":"26626c9db5b09faa2d15489f6d8c35a4c97bf0de235f2e876b18c26c0ce59d73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T16:51:36Z","title_canon_sha256":"591d73bbeebd0e6df5acd6d7866596efdae0451c65b09cbcabb3dbda988ac224"},"schema_version":"1.0","source":{"id":"2409.16235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16235","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16235v1","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16235","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"pith_short_12","alias_value":"54CDTT2DU62Q","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"pith_short_16","alias_value":"54CDTT2DU62QGWZI","created_at":"2026-07-05T09:11:07Z"},{"alias_kind":"pith_short_8","alias_value":"54CDTT2D","created_at":"2026-07-05T09:11:07Z"}],"graph_snapshots":[{"event_id":"sha256:ebad7571c689e471f7866f41dbe87a1379915ab28f368788a38d240340b226b7","target":"graph","created_at":"2026-07-05T09:11:07Z","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/2409.16235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T16:51:36Z","title":"EuroLLM: Multilingual Language Models for Europe"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16235","kind":"arxiv","version":1},"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":"sha256:09f2e538fc04d106f724c7f7845322afed2c1eb5974fbae66104ff2955f692a1","target":"record","created_at":"2026-07-05T09:11:07Z","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":"26626c9db5b09faa2d15489f6d8c35a4c97bf0de235f2e876b18c26c0ce59d73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T16:51:36Z","title_canon_sha256":"591d73bbeebd0e6df5acd6d7866596efdae0451c65b09cbcabb3dbda988ac224"},"schema_version":"1.0","source":{"id":"2409.16235","kind":"arxiv","version":1}},"canonical_sha256":"ef0439cf43a7b5035b288beb1838487d5a12f3e48d97757a4981e38c7b970913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef0439cf43a7b5035b288beb1838487d5a12f3e48d97757a4981e38c7b970913","first_computed_at":"2026-07-05T09:11:07.073117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:07.073117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqwNoBfu9tTxV6zhhe3vrVMADmCSufIj0CRqojTz5vYoPnSRHqPHRNUBGONeb1t8GdILAUi4RYMHvaPhAjQTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:07.073589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09f2e538fc04d106f724c7f7845322afed2c1eb5974fbae66104ff2955f692a1","sha256:ebad7571c689e471f7866f41dbe87a1379915ab28f368788a38d240340b226b7"],"state_sha256":"e19f2ead33b0384ec42b2e25464411047755c7829ad50913a61b1b85dc4c878a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lo2tzURFcMAJ3RMP4GzfellBzraGJTCDFkaZBl02W495Wo+ZRpjUXFC1lo+JWekeKo0cfioT+7IcnBDGhly4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:14:25.393992Z","bundle_sha256":"a1f7f2a28e4f8b2fa80c7fc274c71b48e79cb7d96babf8a007e2630a404c0333"}}