{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4MO44H43MFGMWYJMTOIQUFPLSR","short_pith_number":"pith:4MO44H43","schema_version":"1.0","canonical_sha256":"e31dce1f9b614ccb612c9b910a15eb94471dda76c2876ae8011738fd04ba6f9f","source":{"kind":"arxiv","id":"2012.15613","version":2},"attestation_state":"computed","paper":{"title":"How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer, Phillip Rust, Sebastian Ruder","submitted_at":"2020-12-31T14:11:00Z","abstract_excerpt":"In this work, we provide a systematic and comprehensive empirical comparison of pretrained multilingual language models versus their monolingual counterparts with regard to their monolingual task performance. We study a set of nine typologically diverse languages with readily available pretrained monolingual models on a set of five diverse monolingual downstream tasks. We first aim to establish, via fair and controlled comparisons, if a gap between the multilingual and the corresponding monolingual representation of that language exists, and subsequently investigate the reason for any performa"},"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":"2012.15613","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T14:11:00Z","cross_cats_sorted":[],"title_canon_sha256":"a5cff99452be857de6ebf49e6032efdc3099699ce25efd7fb1bbe4fcefb4bcaf","abstract_canon_sha256":"9a78a1fc13dc0e85bfbf4a5184cbf2d10f44165c0f4d08e3232916d282f5a869"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:35.523591Z","signature_b64":"/yPF7S9KlkMgcyzthRzpUgcyEqY/BAyZ2oiLXaDIz2QahoNgRrQQ7Of5A1dISrFKQMdmTCjg/zCsJxx0csxHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e31dce1f9b614ccb612c9b910a15eb94471dda76c2876ae8011738fd04ba6f9f","last_reissued_at":"2026-07-05T02:45:35.522920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:35.522920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer, Phillip Rust, Sebastian Ruder","submitted_at":"2020-12-31T14:11:00Z","abstract_excerpt":"In this work, we provide a systematic and comprehensive empirical comparison of pretrained multilingual language models versus their monolingual counterparts with regard to their monolingual task performance. We study a set of nine typologically diverse languages with readily available pretrained monolingual models on a set of five diverse monolingual downstream tasks. We first aim to establish, via fair and controlled comparisons, if a gap between the multilingual and the corresponding monolingual representation of that language exists, and subsequently investigate the reason for any performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15613","kind":"arxiv","version":2},"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/2012.15613/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":"2012.15613","created_at":"2026-07-05T02:45:35.523032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15613v2","created_at":"2026-07-05T02:45:35.523032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15613","created_at":"2026-07-05T02:45:35.523032+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MO44H43MFGM","created_at":"2026-07-05T02:45:35.523032+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MO44H43MFGMWYJM","created_at":"2026-07-05T02:45:35.523032+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MO44H43","created_at":"2026-07-05T02:45:35.523032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20993","citing_title":"Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24718","citing_title":"The Tokenizer Tax Across 25 European Languages: Domain Invariance, Cross-Lingual Few-Shot Effects, and the Ukrainian Penalty","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14168","citing_title":"SAGE Celer 2.6 Technical Card","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR","json":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR.json","graph_json":"https://pith.science/api/pith-number/4MO44H43MFGMWYJMTOIQUFPLSR/graph.json","events_json":"https://pith.science/api/pith-number/4MO44H43MFGMWYJMTOIQUFPLSR/events.json","paper":"https://pith.science/paper/4MO44H43"},"agent_actions":{"view_html":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR","download_json":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR.json","view_paper":"https://pith.science/paper/4MO44H43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15613&json=true","fetch_graph":"https://pith.science/api/pith-number/4MO44H43MFGMWYJMTOIQUFPLSR/graph.json","fetch_events":"https://pith.science/api/pith-number/4MO44H43MFGMWYJMTOIQUFPLSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR/action/storage_attestation","attest_author":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR/action/author_attestation","sign_citation":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR/action/citation_signature","submit_replication":"https://pith.science/pith/4MO44H43MFGMWYJMTOIQUFPLSR/action/replication_record"}},"created_at":"2026-07-05T02:45:35.523032+00:00","updated_at":"2026-07-05T02:45:35.523032+00:00"}