{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6EUDR2SBNE5HYLONUE5PVXNSSS","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":"f203fdb7ce4441f48728f2b50d689f928ccdf416671883767dc9c87e890c4c5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T14:47:13Z","title_canon_sha256":"4eafce8a20d0f4898ffd29920e59f870a2ef0fbee5d660a5baa408ba5c6cc146"},"schema_version":"1.0","source":{"id":"2506.10766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10766","created_at":"2026-07-05T11:20:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10766v1","created_at":"2026-07-05T11:20:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10766","created_at":"2026-07-05T11:20:30Z"},{"alias_kind":"pith_short_12","alias_value":"6EUDR2SBNE5H","created_at":"2026-07-05T11:20:30Z"},{"alias_kind":"pith_short_16","alias_value":"6EUDR2SBNE5HYLON","created_at":"2026-07-05T11:20:30Z"},{"alias_kind":"pith_short_8","alias_value":"6EUDR2SB","created_at":"2026-07-05T11:20:30Z"}],"graph_snapshots":[{"event_id":"sha256:45c8330f46708989f301ed066e92c319eec81918a09284759117e93fa0df4cba","target":"graph","created_at":"2026-07-05T11:20:30Z","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/2506.10766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining massively multilingual Large Language Models (LLMs) for many languages at once is challenging due to limited model capacity, scarce high-quality data, and compute constraints. Moreover, the lack of language coverage of the tokenizer makes it harder to address the gap for new languages purely at the post-training stage. In this work, we study what relatively cheap interventions early on in training improve \"language plasticity\", or adaptation capabilities of the model post-training to new languages. We focus on tokenizer design and propose using a universal tokenizer that is trained","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Alejandro R. Salamanca, Andres Felipe Cruz-Salinas, Diana Abagyan, Hangyu Lin, Kris Cao, Marzieh Fadaee, Sara Hooker","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T14:47:13Z","title":"One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10766","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:c636984562fb5eecd42af86398cb9a57417ca42186280a1252080e5725f67c62","target":"record","created_at":"2026-07-05T11:20:30Z","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":"f203fdb7ce4441f48728f2b50d689f928ccdf416671883767dc9c87e890c4c5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T14:47:13Z","title_canon_sha256":"4eafce8a20d0f4898ffd29920e59f870a2ef0fbee5d660a5baa408ba5c6cc146"},"schema_version":"1.0","source":{"id":"2506.10766","kind":"arxiv","version":1}},"canonical_sha256":"f12838ea41693a7c2dcda13afaddb2949257a51729a1a8649af8a3d1f944bd0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f12838ea41693a7c2dcda13afaddb2949257a51729a1a8649af8a3d1f944bd0c","first_computed_at":"2026-07-05T11:20:30.264422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:30.264422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w6ktQEfJCvcj+ROgORZ3L9sKHUgaUiTO9Z2Mq9WxNBoZV4cnvbvPkzGUfnknrDIZZTsqvWalTfczGWnfcCftCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:30.264931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c636984562fb5eecd42af86398cb9a57417ca42186280a1252080e5725f67c62","sha256:45c8330f46708989f301ed066e92c319eec81918a09284759117e93fa0df4cba"],"state_sha256":"876c5a13c3e4ac9770c9eb01318690b73877b011204611c4fcfe2a5e266af808"}