{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LZGDTYACL44HBDXOMOYLXHN6TJ","short_pith_number":"pith:LZGDTYAC","schema_version":"1.0","canonical_sha256":"5e4c39e0025f38708eee63b0bb9dbe9a71dc9997bbd2da1e0c72d8440ec3d6a8","source":{"kind":"arxiv","id":"2005.00633","version":1},"attestation_state":"computed","paper":{"title":"From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Lauscher, Goran Glava\\v{s}, Ivan Vuli\\'c, Vinit Ravishankar","submitted_at":"2020-05-01T22:04:58Z","abstract_excerpt":"Massively multilingual transformers pretrained with language modeling objectives (e.g., mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross-lingual transfer in NLP, offering unmatched transfer performance. Current downstream evaluations, however, verify their efficacy predominantly in transfer settings involving languages with sufficient amounts of pretraining data, and with lexically and typologically close languages. In this work, we analyze their limitations and show that cross-lingual transfer via massively multilingual transformers, much like transfer via cr"},"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":"2005.00633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T22:04:58Z","cross_cats_sorted":[],"title_canon_sha256":"f6f2885ed3ee424ed9ad02fb305334f85b6d8d127d7fd6f500b739229c86062d","abstract_canon_sha256":"475398bd64324ba3017e3319c61c47783382452d3f14e38cfe400fc14e330279"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:44.438080Z","signature_b64":"4BasbyrHEtoByl0kZZu19rJYqDYtamT1ab8FJ8/wCoeMIvYuzi1jA2h54iV3Of+DFzykKXQTlzH8XbzGFfC5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4c39e0025f38708eee63b0bb9dbe9a71dc9997bbd2da1e0c72d8440ec3d6a8","last_reissued_at":"2026-07-05T00:59:44.437657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:44.437657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Lauscher, Goran Glava\\v{s}, Ivan Vuli\\'c, Vinit Ravishankar","submitted_at":"2020-05-01T22:04:58Z","abstract_excerpt":"Massively multilingual transformers pretrained with language modeling objectives (e.g., mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross-lingual transfer in NLP, offering unmatched transfer performance. Current downstream evaluations, however, verify their efficacy predominantly in transfer settings involving languages with sufficient amounts of pretraining data, and with lexically and typologically close languages. In this work, we analyze their limitations and show that cross-lingual transfer via massively multilingual transformers, much like transfer via cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00633","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/2005.00633/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":"2005.00633","created_at":"2026-07-05T00:59:44.437715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00633v1","created_at":"2026-07-05T00:59:44.437715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00633","created_at":"2026-07-05T00:59:44.437715+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZGDTYACL44H","created_at":"2026-07-05T00:59:44.437715+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZGDTYACL44HBDXO","created_at":"2026-07-05T00:59:44.437715+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZGDTYAC","created_at":"2026-07-05T00:59:44.437715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15675","citing_title":"C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ","json":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ.json","graph_json":"https://pith.science/api/pith-number/LZGDTYACL44HBDXOMOYLXHN6TJ/graph.json","events_json":"https://pith.science/api/pith-number/LZGDTYACL44HBDXOMOYLXHN6TJ/events.json","paper":"https://pith.science/paper/LZGDTYAC"},"agent_actions":{"view_html":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ","download_json":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ.json","view_paper":"https://pith.science/paper/LZGDTYAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00633&json=true","fetch_graph":"https://pith.science/api/pith-number/LZGDTYACL44HBDXOMOYLXHN6TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LZGDTYACL44HBDXOMOYLXHN6TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ/action/storage_attestation","attest_author":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ/action/author_attestation","sign_citation":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ/action/citation_signature","submit_replication":"https://pith.science/pith/LZGDTYACL44HBDXOMOYLXHN6TJ/action/replication_record"}},"created_at":"2026-07-05T00:59:44.437715+00:00","updated_at":"2026-07-05T00:59:44.437715+00:00"}