{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WDTFOOVOALFSILYMCIRFTLJRUZ","short_pith_number":"pith:WDTFOOVO","schema_version":"1.0","canonical_sha256":"b0e6573aae02cb242f0c122259ad31a6786f71079f88f2c3d37a6584610579e4","source":{"kind":"arxiv","id":"2607.00890","version":1},"attestation_state":"computed","paper":{"title":"MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Andrey Kutuzov, Anna Lokrantz, Birger Moell, David Salinas, Fedor Vitiugin, Filip Ginter, Gema Ram\\'irez-S\\'anchez, Jan Haji\\v{c}, Jenia Jitsev, Jenna Kanerva, Jonas Lindh, J\\\"org Tiedemann, Matthias Lindemann, Maximilian Idahl, Sampo Pyysalo, Shenbin Qian, Stephan Oepen, Tim Isbister, Tomasz Galica, Tudor Nicolae Mateiu, Zihao Li","submitted_at":"2026-07-01T12:55:58Z","abstract_excerpt":"Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic parallel corpus with approximately 4.8 trillion target-language tokens across 36 European languages, produced by translating 100 billion high-quality Nemotron-CC tokens with Tower+ and OPUS-MT/HPLT-MT systems. For many medium- and lower-resource European languages, this is the largest openly available pre-training resource. On a broad multilingual benchmark suite, reference LLMs trained on MultiSynt/MT reach the final score of HPLT 2.0, a nativ"},"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":"2607.00890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T12:55:58Z","cross_cats_sorted":[],"title_canon_sha256":"7fc4a9269c82ce0904289ce201196611215306f4d9aadeb2978486def878d17b","abstract_canon_sha256":"716f98cd5110c31f2950d6cade0f64eaaf2e19aa14103a7f07a88da978d1abd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:22.564201Z","signature_b64":"SdMSuhdv8f841QiEv1G0rfUtposNQADKu5fZvMhTNcJgOPIbsLZTJdEe5R3ebjxhrm98oHAFZnl0eeLBRDx2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0e6573aae02cb242f0c122259ad31a6786f71079f88f2c3d37a6584610579e4","last_reissued_at":"2026-07-02T01:18:22.563779Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:22.563779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Andrey Kutuzov, Anna Lokrantz, Birger Moell, David Salinas, Fedor Vitiugin, Filip Ginter, Gema Ram\\'irez-S\\'anchez, Jan Haji\\v{c}, Jenia Jitsev, Jenna Kanerva, Jonas Lindh, J\\\"org Tiedemann, Matthias Lindemann, Maximilian Idahl, Sampo Pyysalo, Shenbin Qian, Stephan Oepen, Tim Isbister, Tomasz Galica, Tudor Nicolae Mateiu, Zihao Li","submitted_at":"2026-07-01T12:55:58Z","abstract_excerpt":"Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic parallel corpus with approximately 4.8 trillion target-language tokens across 36 European languages, produced by translating 100 billion high-quality Nemotron-CC tokens with Tower+ and OPUS-MT/HPLT-MT systems. For many medium- and lower-resource European languages, this is the largest openly available pre-training resource. On a broad multilingual benchmark suite, reference LLMs trained on MultiSynt/MT reach the final score of HPLT 2.0, a nativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00890","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/2607.00890/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":"2607.00890","created_at":"2026-07-02T01:18:22.563845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00890v1","created_at":"2026-07-02T01:18:22.563845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00890","created_at":"2026-07-02T01:18:22.563845+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDTFOOVOALFS","created_at":"2026-07-02T01:18:22.563845+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDTFOOVOALFSILYM","created_at":"2026-07-02T01:18:22.563845+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDTFOOVO","created_at":"2026-07-02T01:18:22.563845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ","json":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ.json","graph_json":"https://pith.science/api/pith-number/WDTFOOVOALFSILYMCIRFTLJRUZ/graph.json","events_json":"https://pith.science/api/pith-number/WDTFOOVOALFSILYMCIRFTLJRUZ/events.json","paper":"https://pith.science/paper/WDTFOOVO"},"agent_actions":{"view_html":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ","download_json":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ.json","view_paper":"https://pith.science/paper/WDTFOOVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00890&json=true","fetch_graph":"https://pith.science/api/pith-number/WDTFOOVOALFSILYMCIRFTLJRUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WDTFOOVOALFSILYMCIRFTLJRUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/action/storage_attestation","attest_author":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/action/author_attestation","sign_citation":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/action/citation_signature","submit_replication":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/action/replication_record"}},"created_at":"2026-07-02T01:18:22.563845+00:00","updated_at":"2026-07-02T01:18:22.563845+00:00"}