{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3CY7D5LL6RJ5D4MOKTM3QX33H2","short_pith_number":"pith:3CY7D5LL","schema_version":"1.0","canonical_sha256":"d8b1f1f56bf453d1f18e54d9b85f7b3ea62c685ed6e7fd9d54ac277fc2a47be7","source":{"kind":"arxiv","id":"2105.02472","version":2},"attestation_state":"computed","paper":{"title":"XeroAlign: Zero-Shot Cross-lingual Transformer Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ignacio Iacobacci, Milan Gritta","submitted_at":"2021-05-06T07:10:00Z","abstract_excerpt":"The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data necessitates a variety of methods aiming to close the gap to high-resource languages. Zero-shot methods in particular, often use translated task data as a training signal to bridge the performance gap between the source and target language(s). We introduce XeroAlign, a simple method for task-specific alignment of cross-lingual pretrained transformers such as XLM-R. XeroAlign uses translated task data to encourage the model to generate sim"},"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":"2105.02472","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-06T07:10:00Z","cross_cats_sorted":[],"title_canon_sha256":"78f381f9b7e3578bf1756e9208a2c9e3fb39234d89ce3dfcddb329aec868b4dd","abstract_canon_sha256":"c4d932c8bb43e6100ded17bc37d1e0e8b000cd24dfb49c961aaac932dba99c28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:14.149449Z","signature_b64":"uvXPoYgQRImLMi1ehdYKum5FTTcq14KpkwDOBxKrmNugBAbHWuK/VZ3Fpu2DD1Ak75dWmtWElxrQoeTiCLePAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8b1f1f56bf453d1f18e54d9b85f7b3ea62c685ed6e7fd9d54ac277fc2a47be7","last_reissued_at":"2026-07-05T03:25:14.148935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:14.148935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XeroAlign: Zero-Shot Cross-lingual Transformer Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ignacio Iacobacci, Milan Gritta","submitted_at":"2021-05-06T07:10:00Z","abstract_excerpt":"The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data necessitates a variety of methods aiming to close the gap to high-resource languages. Zero-shot methods in particular, often use translated task data as a training signal to bridge the performance gap between the source and target language(s). We introduce XeroAlign, a simple method for task-specific alignment of cross-lingual pretrained transformers such as XLM-R. XeroAlign uses translated task data to encourage the model to generate sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.02472","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/2105.02472/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":"2105.02472","created_at":"2026-07-05T03:25:14.148998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.02472v2","created_at":"2026-07-05T03:25:14.148998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.02472","created_at":"2026-07-05T03:25:14.148998+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CY7D5LL6RJ5","created_at":"2026-07-05T03:25:14.148998+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CY7D5LL6RJ5D4MO","created_at":"2026-07-05T03:25:14.148998+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CY7D5LL","created_at":"2026-07-05T03:25:14.148998+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/3CY7D5LL6RJ5D4MOKTM3QX33H2","json":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2.json","graph_json":"https://pith.science/api/pith-number/3CY7D5LL6RJ5D4MOKTM3QX33H2/graph.json","events_json":"https://pith.science/api/pith-number/3CY7D5LL6RJ5D4MOKTM3QX33H2/events.json","paper":"https://pith.science/paper/3CY7D5LL"},"agent_actions":{"view_html":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2","download_json":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2.json","view_paper":"https://pith.science/paper/3CY7D5LL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.02472&json=true","fetch_graph":"https://pith.science/api/pith-number/3CY7D5LL6RJ5D4MOKTM3QX33H2/graph.json","fetch_events":"https://pith.science/api/pith-number/3CY7D5LL6RJ5D4MOKTM3QX33H2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2/action/storage_attestation","attest_author":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2/action/author_attestation","sign_citation":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2/action/citation_signature","submit_replication":"https://pith.science/pith/3CY7D5LL6RJ5D4MOKTM3QX33H2/action/replication_record"}},"created_at":"2026-07-05T03:25:14.148998+00:00","updated_at":"2026-07-05T03:25:14.148998+00:00"}