{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DQTCAILTHCXEQGUMYX5EA3QVZD","short_pith_number":"pith:DQTCAILT","schema_version":"1.0","canonical_sha256":"1c2620217338ae481a8cc5fa406e15c8eb459c0655ac9597e05be3e19dd1ec87","source":{"kind":"arxiv","id":"1910.11856","version":3},"attestation_state":"computed","paper":{"title":"On the Cross-lingual Transferability of Monolingual Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Mikel Artetxe, Sebastian Ruder","submitted_at":"2019-10-25T17:30:20Z","abstract_excerpt":"State-of-the-art unsupervised multilingual models (e.g., multilingual BERT) have been shown to generalize in a zero-shot cross-lingual setting. This generalization ability has been attributed to the use of a shared subword vocabulary and joint training across multiple languages giving rise to deep multilingual abstractions. We evaluate this hypothesis by designing an alternative approach that transfers a monolingual model to new languages at the lexical level. More concretely, we first train a transformer-based masked language model on one language, and transfer it to a new language by learnin"},"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":"1910.11856","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-25T17:30:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dcf61da8ec1c27cb3959017ad629f99830839ad4e2bc3185d8c34a503ead8849","abstract_canon_sha256":"694596dcc84870df95d4aba1d52d1fc1ea8a5023506ec12ad9a9f3568e1b15f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:34.942712Z","signature_b64":"H5X14FGpgTMLKm81k6zehIsV2+PrwaxFBROvf1tOjJ2wMWjbG418BMYvsJZrhAzOTom+D4gqfGbhhGA/qjDZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c2620217338ae481a8cc5fa406e15c8eb459c0655ac9597e05be3e19dd1ec87","last_reissued_at":"2026-07-05T03:43:34.942256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:34.942256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Cross-lingual Transferability of Monolingual Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Mikel Artetxe, Sebastian Ruder","submitted_at":"2019-10-25T17:30:20Z","abstract_excerpt":"State-of-the-art unsupervised multilingual models (e.g., multilingual BERT) have been shown to generalize in a zero-shot cross-lingual setting. This generalization ability has been attributed to the use of a shared subword vocabulary and joint training across multiple languages giving rise to deep multilingual abstractions. We evaluate this hypothesis by designing an alternative approach that transfers a monolingual model to new languages at the lexical level. More concretely, we first train a transformer-based masked language model on one language, and transfer it to a new language by learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.11856","kind":"arxiv","version":3},"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/1910.11856/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":"1910.11856","created_at":"2026-07-05T03:43:34.942310+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.11856v3","created_at":"2026-07-05T03:43:34.942310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.11856","created_at":"2026-07-05T03:43:34.942310+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQTCAILTHCXE","created_at":"2026-07-05T03:43:34.942310+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQTCAILTHCXEQGUM","created_at":"2026-07-05T03:43:34.942310+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQTCAILT","created_at":"2026-07-05T03:43:34.942310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31171","citing_title":"MIMO: Multilingual Information Retrieval via Monolingual Objectives","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":287,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD","json":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD.json","graph_json":"https://pith.science/api/pith-number/DQTCAILTHCXEQGUMYX5EA3QVZD/graph.json","events_json":"https://pith.science/api/pith-number/DQTCAILTHCXEQGUMYX5EA3QVZD/events.json","paper":"https://pith.science/paper/DQTCAILT"},"agent_actions":{"view_html":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD","download_json":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD.json","view_paper":"https://pith.science/paper/DQTCAILT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.11856&json=true","fetch_graph":"https://pith.science/api/pith-number/DQTCAILTHCXEQGUMYX5EA3QVZD/graph.json","fetch_events":"https://pith.science/api/pith-number/DQTCAILTHCXEQGUMYX5EA3QVZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD/action/storage_attestation","attest_author":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD/action/author_attestation","sign_citation":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD/action/citation_signature","submit_replication":"https://pith.science/pith/DQTCAILTHCXEQGUMYX5EA3QVZD/action/replication_record"}},"created_at":"2026-07-05T03:43:34.942310+00:00","updated_at":"2026-07-05T03:43:34.942310+00:00"}