{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WDTFOOVOALFSILYMCIRFTLJRUZ","short_pith_number":"pith:WDTFOOVO","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"},"canonical_sha256":"b0e6573aae02cb242f0c122259ad31a6786f71079f88f2c3d37a6584610579e4","source":{"kind":"arxiv","id":"2607.00890","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00890","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00890v1","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00890","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"WDTFOOVOALFS","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"WDTFOOVOALFSILYM","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"WDTFOOVO","created_at":"2026-07-02T01:18:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WDTFOOVOALFSILYMCIRFTLJRUZ","target":"record","payload":{"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"},"canonical_sha256":"b0e6573aae02cb242f0c122259ad31a6786f71079f88f2c3d37a6584610579e4","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"},"source_kind":"arxiv","source_id":"2607.00890","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":"2026-07-02T01:18:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0841Z4hrNh6QdkERN3FUJE9HRnCkwZ5+qs89wxI9jSWnuZgAh0IFFrEJ1wiU1kPyBmFY757kZ7geS38r82EyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:54:39.157134Z"},"content_sha256":"6b4f97e8133da7d46103fb4853d4b9b3ae01d6cee82318dd13a29c678c8be58f","schema_version":"1.0","event_id":"sha256:6b4f97e8133da7d46103fb4853d4b9b3ae01d6cee82318dd13a29c678c8be58f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WDTFOOVOALFSILYMCIRFTLJRUZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:18:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mu2isw5LvW/spWbKPZ1yOPVmnqpDOZUKaTD9lv0LQB5LMr1oA1d6vrl1T9dmT9TSdg29opY3NS7UlnMUMxX+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:54:39.157526Z"},"content_sha256":"9c3e44696a15d6faad451bcfdad91da9bd2b72de9623594778e74e05e6fb184c","schema_version":"1.0","event_id":"sha256:9c3e44696a15d6faad451bcfdad91da9bd2b72de9623594778e74e05e6fb184c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/bundle.json","state_url":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/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":"2026-07-02T23:54:39Z","links":{"resolver":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ","bundle":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/bundle.json","state":"https://pith.science/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDTFOOVOALFSILYMCIRFTLJRUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WDTFOOVOALFSILYMCIRFTLJRUZ","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":"716f98cd5110c31f2950d6cade0f64eaaf2e19aa14103a7f07a88da978d1abd2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T12:55:58Z","title_canon_sha256":"7fc4a9269c82ce0904289ce201196611215306f4d9aadeb2978486def878d17b"},"schema_version":"1.0","source":{"id":"2607.00890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00890","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00890v1","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00890","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"WDTFOOVOALFS","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"WDTFOOVOALFSILYM","created_at":"2026-07-02T01:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"WDTFOOVO","created_at":"2026-07-02T01:18:22Z"}],"graph_snapshots":[{"event_id":"sha256:9c3e44696a15d6faad451bcfdad91da9bd2b72de9623594778e74e05e6fb184c","target":"graph","created_at":"2026-07-02T01:18:22Z","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/2607.00890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T12:55:58Z","title":"MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00890","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":"sha256:6b4f97e8133da7d46103fb4853d4b9b3ae01d6cee82318dd13a29c678c8be58f","target":"record","created_at":"2026-07-02T01:18:22Z","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":"716f98cd5110c31f2950d6cade0f64eaaf2e19aa14103a7f07a88da978d1abd2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T12:55:58Z","title_canon_sha256":"7fc4a9269c82ce0904289ce201196611215306f4d9aadeb2978486def878d17b"},"schema_version":"1.0","source":{"id":"2607.00890","kind":"arxiv","version":1}},"canonical_sha256":"b0e6573aae02cb242f0c122259ad31a6786f71079f88f2c3d37a6584610579e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0e6573aae02cb242f0c122259ad31a6786f71079f88f2c3d37a6584610579e4","first_computed_at":"2026-07-02T01:18:22.563779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:22.563779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SdMSuhdv8f841QiEv1G0rfUtposNQADKu5fZvMhTNcJgOPIbsLZTJdEe5R3ebjxhrm98oHAFZnl0eeLBRDx2CA==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:22.564201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b4f97e8133da7d46103fb4853d4b9b3ae01d6cee82318dd13a29c678c8be58f","sha256:9c3e44696a15d6faad451bcfdad91da9bd2b72de9623594778e74e05e6fb184c"],"state_sha256":"68656512ac32fb6fdb03ab58f1745ff117c47013d1a80f8cd825f6a56b50b764"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FxQujjN9/cLJa79FQM3KnXpxLPr0DYO6+/We4kP8HXhwCPBKUzwkH6rbtzIwNR9e9wrsGfIn3EmY8hW5AW0XDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T23:54:39.159640Z","bundle_sha256":"b2341bd619775cf2a4c57f9aff2918d2aca951be47d1e5ea3c7582cd0dea0b00"}}