{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z6NETYLQVYCWKGKCPUEIEQZ2HM","short_pith_number":"pith:Z6NETYLQ","schema_version":"1.0","canonical_sha256":"cf9a49e170ae056519427d0882433a3b0b2592daf1f0767835da9635163b9a17","source":{"kind":"arxiv","id":"2210.05619","version":2},"attestation_state":"computed","paper":{"title":"Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Isabel Papadimitriou, Kezia Lopez","submitted_at":"2022-10-11T17:06:38Z","abstract_excerpt":"While multilingual language models can improve NLP performance on low-resource languages by leveraging higher-resource languages, they also reduce average performance on all languages (the 'curse of multilinguality'). Here we show another problem with multilingual models: grammatical structures in higher-resource languages bleed into lower-resource languages, a phenomenon we call grammatical structure bias. We show this bias via a novel method for comparing the fluency of multilingual models to the fluency of monolingual Spanish and Greek models: testing their preference for two carefully-chos"},"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":"2210.05619","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T17:06:38Z","cross_cats_sorted":[],"title_canon_sha256":"90296d882791b95332a50216fc85001ce50da8fe6e41ac8e82582bf521177b0f","abstract_canon_sha256":"02751b3ede457026ab4b3d14cfdb9f11d43afa65d82c690779b0a6a9074021f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:32.944798Z","signature_b64":"MYQL4w8CcgKPvMyrGiNMwpGTdRW6tUTj30qo7z+qgj4RfE94lZLHBNaQpbXcANT2Qzwhfx+8j+tB+8Szc1wCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf9a49e170ae056519427d0882433a3b0b2592daf1f0767835da9635163b9a17","last_reissued_at":"2026-07-05T06:00:32.944250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:32.944250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Isabel Papadimitriou, Kezia Lopez","submitted_at":"2022-10-11T17:06:38Z","abstract_excerpt":"While multilingual language models can improve NLP performance on low-resource languages by leveraging higher-resource languages, they also reduce average performance on all languages (the 'curse of multilinguality'). Here we show another problem with multilingual models: grammatical structures in higher-resource languages bleed into lower-resource languages, a phenomenon we call grammatical structure bias. We show this bias via a novel method for comparing the fluency of multilingual models to the fluency of monolingual Spanish and Greek models: testing their preference for two carefully-chos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05619","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/2210.05619/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":"2210.05619","created_at":"2026-07-05T06:00:32.944310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05619v2","created_at":"2026-07-05T06:00:32.944310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05619","created_at":"2026-07-05T06:00:32.944310+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6NETYLQVYCW","created_at":"2026-07-05T06:00:32.944310+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6NETYLQVYCWKGKC","created_at":"2026-07-05T06:00:32.944310+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6NETYLQ","created_at":"2026-07-05T06:00:32.944310+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/Z6NETYLQVYCWKGKCPUEIEQZ2HM","json":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM.json","graph_json":"https://pith.science/api/pith-number/Z6NETYLQVYCWKGKCPUEIEQZ2HM/graph.json","events_json":"https://pith.science/api/pith-number/Z6NETYLQVYCWKGKCPUEIEQZ2HM/events.json","paper":"https://pith.science/paper/Z6NETYLQ"},"agent_actions":{"view_html":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM","download_json":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM.json","view_paper":"https://pith.science/paper/Z6NETYLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05619&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6NETYLQVYCWKGKCPUEIEQZ2HM/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6NETYLQVYCWKGKCPUEIEQZ2HM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM/action/storage_attestation","attest_author":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM/action/author_attestation","sign_citation":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM/action/citation_signature","submit_replication":"https://pith.science/pith/Z6NETYLQVYCWKGKCPUEIEQZ2HM/action/replication_record"}},"created_at":"2026-07-05T06:00:32.944310+00:00","updated_at":"2026-07-05T06:00:32.944310+00:00"}