{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VE4HBJXFUVXPY3AWALVKWZUFW2","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":"e76704c6cb802e30c429622fe893dbe7d627b320c9bdbbae9b369c03d7df8e36","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T09:15:17Z","title_canon_sha256":"10fa815785d6304ceb13b3c5130208c2a502896cfb1ddc23c3af62b7c8c37200"},"schema_version":"1.0","source":{"id":"2301.10472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10472","created_at":"2026-07-05T07:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10472v2","created_at":"2026-07-05T07:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10472","created_at":"2026-07-05T07:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"VE4HBJXFUVXP","created_at":"2026-07-05T07:00:43Z"},{"alias_kind":"pith_short_16","alias_value":"VE4HBJXFUVXPY3AW","created_at":"2026-07-05T07:00:43Z"},{"alias_kind":"pith_short_8","alias_value":"VE4HBJXF","created_at":"2026-07-05T07:00:43Z"}],"graph_snapshots":[{"event_id":"sha256:1e62d49951cfc5b8c50433b67ab9631064c76be40fb65588f6d711921821f92c","target":"graph","created_at":"2026-07-05T07:00:43Z","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/2301.10472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multilingual language models typically rely on a single vocabulary shared across 100+ languages. As these models have increased in parameter count and depth, vocabulary size has remained largely unchanged. This \\textit{vocabulary bottleneck} limits the representational capabilities of multilingual models like XLM-R. In this paper, we introduce a new approach for scaling to very large multilingual vocabularies by de-emphasizing token sharing between languages with little lexical overlap and assigning vocabulary capacity to achieve sufficient coverage for each individual language. Tokeniza","authors_text":"Davis Liang, Hila Gonen, Luke Zettlemoyer, Madian Khabsa, Marjan Ghazvininejad, Naman Goyal, Rui Hou, Yuning Mao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T09:15:17Z","title":"XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10472","kind":"arxiv","version":2},"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:e9f096d2a63fc0073272b4750ad13223fa0b48dead68826b946491b6419a1f04","target":"record","created_at":"2026-07-05T07:00:43Z","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":"e76704c6cb802e30c429622fe893dbe7d627b320c9bdbbae9b369c03d7df8e36","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T09:15:17Z","title_canon_sha256":"10fa815785d6304ceb13b3c5130208c2a502896cfb1ddc23c3af62b7c8c37200"},"schema_version":"1.0","source":{"id":"2301.10472","kind":"arxiv","version":2}},"canonical_sha256":"a93870a6e5a56efc6c1602eaab6685b6883da77fdd556b2ee57e503dccad1c0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a93870a6e5a56efc6c1602eaab6685b6883da77fdd556b2ee57e503dccad1c0e","first_computed_at":"2026-07-05T07:00:43.762194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:43.762194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"khCLX1MILbgv7mTC177PI9Hi7QqGOMOHMZ/Vk0/QK5HxCjXyB2vUUZi/1I8fItiWVJUD2RSJvuJWajuenfejDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:43.762707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.10472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9f096d2a63fc0073272b4750ad13223fa0b48dead68826b946491b6419a1f04","sha256:1e62d49951cfc5b8c50433b67ab9631064c76be40fb65588f6d711921821f92c"],"state_sha256":"c79abf71a443e7408a5104dd254d310a19a42b0820252f84500e83a72767532e"}