{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EAQNP3R2JCHEIT2SPHIIC2ZEAF","short_pith_number":"pith:EAQNP3R2","schema_version":"1.0","canonical_sha256":"2020d7ee3a488e444f5279d0816b24014831f8cad6620c64665c6b34a87ec0e9","source":{"kind":"arxiv","id":"2211.00106","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Cross-Lingual Transfer with Language-Specific Subnetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Garrette, Ekaterina Shutova, Rochelle Choenni","submitted_at":"2022-10-31T19:23:33Z","abstract_excerpt":"Large multilingual language models typically share their parameters across all languages, which enables cross-lingual task transfer, but learning can also be hindered when training updates from different languages are in conflict. In this paper, we propose novel methods for using language-specific subnetworks, which control cross-lingual parameter sharing, to reduce conflicts and increase positive transfer during fine-tuning. We introduce dynamic subnetworks, which are jointly updated with the model, and we combine our methods with meta-learning, an established, but complementary, technique fo"},"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":"2211.00106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T19:23:33Z","cross_cats_sorted":[],"title_canon_sha256":"a4b84f6e83b73c33596f409e75bb35e01cd9183caa96c8dc107fe06a5436407f","abstract_canon_sha256":"88af6dc83c4a9bfff6c23d600482ae4545ddcba4339275de0a2e3b0fd2153828"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:18.575853Z","signature_b64":"6L+e11xMETKOLXUxYpaj7C6fSfYEGCDBzd2M01kdUDA2CQjiNg7K/m2o05L9Ok6R9IGE+OQig2kezFLAkmoRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2020d7ee3a488e444f5279d0816b24014831f8cad6620c64665c6b34a87ec0e9","last_reissued_at":"2026-07-05T05:12:18.575339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:18.575339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Cross-Lingual Transfer with Language-Specific Subnetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Garrette, Ekaterina Shutova, Rochelle Choenni","submitted_at":"2022-10-31T19:23:33Z","abstract_excerpt":"Large multilingual language models typically share their parameters across all languages, which enables cross-lingual task transfer, but learning can also be hindered when training updates from different languages are in conflict. In this paper, we propose novel methods for using language-specific subnetworks, which control cross-lingual parameter sharing, to reduce conflicts and increase positive transfer during fine-tuning. We introduce dynamic subnetworks, which are jointly updated with the model, and we combine our methods with meta-learning, an established, but complementary, technique fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00106","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/2211.00106/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":"2211.00106","created_at":"2026-07-05T05:12:18.575397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00106v1","created_at":"2026-07-05T05:12:18.575397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00106","created_at":"2026-07-05T05:12:18.575397+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAQNP3R2JCHE","created_at":"2026-07-05T05:12:18.575397+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAQNP3R2JCHEIT2S","created_at":"2026-07-05T05:12:18.575397+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAQNP3R2","created_at":"2026-07-05T05:12:18.575397+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/EAQNP3R2JCHEIT2SPHIIC2ZEAF","json":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF.json","graph_json":"https://pith.science/api/pith-number/EAQNP3R2JCHEIT2SPHIIC2ZEAF/graph.json","events_json":"https://pith.science/api/pith-number/EAQNP3R2JCHEIT2SPHIIC2ZEAF/events.json","paper":"https://pith.science/paper/EAQNP3R2"},"agent_actions":{"view_html":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF","download_json":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF.json","view_paper":"https://pith.science/paper/EAQNP3R2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00106&json=true","fetch_graph":"https://pith.science/api/pith-number/EAQNP3R2JCHEIT2SPHIIC2ZEAF/graph.json","fetch_events":"https://pith.science/api/pith-number/EAQNP3R2JCHEIT2SPHIIC2ZEAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF/action/storage_attestation","attest_author":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF/action/author_attestation","sign_citation":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF/action/citation_signature","submit_replication":"https://pith.science/pith/EAQNP3R2JCHEIT2SPHIIC2ZEAF/action/replication_record"}},"created_at":"2026-07-05T05:12:18.575397+00:00","updated_at":"2026-07-05T05:12:18.575397+00:00"}