{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MBGUFW4TCPNRCEH74SGEOKEZ7S","short_pith_number":"pith:MBGUFW4T","schema_version":"1.0","canonical_sha256":"604d42db9313db1110ffe48c472899fc9023173b2f72f6739dc51ac2027ae7d2","source":{"kind":"arxiv","id":"2210.07111","version":1},"attestation_state":"computed","paper":{"title":"A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Jimin Sun, Patrick Fernandes, Xinyi Wang","submitted_at":"2022-10-13T15:47:09Z","abstract_excerpt":"Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue et al., 2022). However, these works mainly focus on reporting accuracy on a limited set of tasks and data settings, placing less emphasis on other important factors when tuning and deploying the models in practice, such as memory usage, inference speed, and fine-tuning data robustness. We attempt to fill this gap by performing a comprehensive empirical comparison of multilingual tokenizer-free and subword-based models"},"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":"2210.07111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-13T15:47:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fe38b027eaa86dba1f217c6aa6d46d1f33152394be9580275a7839450cbe583","abstract_canon_sha256":"944b7a3b4bc356393cc070a210e6b098d75812d06d213ebe1e6b3fee35669482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:24.660455Z","signature_b64":"L/ZFC/obrLB8Ita44TBvL1IvexafCX3Y01Vw751MRVbeJhPCd6G283l9Qih4oiJ7ffGzOJhb0E0fezFALMhbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"604d42db9313db1110ffe48c472899fc9023173b2f72f6739dc51ac2027ae7d2","last_reissued_at":"2026-07-05T05:06:24.660004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:24.660004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Jimin Sun, Patrick Fernandes, Xinyi Wang","submitted_at":"2022-10-13T15:47:09Z","abstract_excerpt":"Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue et al., 2022). However, these works mainly focus on reporting accuracy on a limited set of tasks and data settings, placing less emphasis on other important factors when tuning and deploying the models in practice, such as memory usage, inference speed, and fine-tuning data robustness. We attempt to fill this gap by performing a comprehensive empirical comparison of multilingual tokenizer-free and subword-based models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07111","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/2210.07111/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":"2210.07111","created_at":"2026-07-05T05:06:24.660056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07111v1","created_at":"2026-07-05T05:06:24.660056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07111","created_at":"2026-07-05T05:06:24.660056+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBGUFW4TCPNR","created_at":"2026-07-05T05:06:24.660056+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBGUFW4TCPNRCEH7","created_at":"2026-07-05T05:06:24.660056+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBGUFW4T","created_at":"2026-07-05T05:06:24.660056+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/MBGUFW4TCPNRCEH74SGEOKEZ7S","json":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S.json","graph_json":"https://pith.science/api/pith-number/MBGUFW4TCPNRCEH74SGEOKEZ7S/graph.json","events_json":"https://pith.science/api/pith-number/MBGUFW4TCPNRCEH74SGEOKEZ7S/events.json","paper":"https://pith.science/paper/MBGUFW4T"},"agent_actions":{"view_html":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S","download_json":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S.json","view_paper":"https://pith.science/paper/MBGUFW4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07111&json=true","fetch_graph":"https://pith.science/api/pith-number/MBGUFW4TCPNRCEH74SGEOKEZ7S/graph.json","fetch_events":"https://pith.science/api/pith-number/MBGUFW4TCPNRCEH74SGEOKEZ7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S/action/storage_attestation","attest_author":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S/action/author_attestation","sign_citation":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S/action/citation_signature","submit_replication":"https://pith.science/pith/MBGUFW4TCPNRCEH74SGEOKEZ7S/action/replication_record"}},"created_at":"2026-07-05T05:06:24.660056+00:00","updated_at":"2026-07-05T05:06:24.660056+00:00"}