{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KIIVMEE3WBEDYWXE7IQL26D5VI","short_pith_number":"pith:KIIVMEE3","schema_version":"1.0","canonical_sha256":"521156109bb0483c5ae4fa20bd787daa388a41cc2292ce4da7768e7510df2320","source":{"kind":"arxiv","id":"2204.13869","version":1},"attestation_state":"computed","paper":{"title":"Por Qu\\'e N\\~ao Utiliser Alla Spr{\\aa}k? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Xu, Kenton Murray","submitted_at":"2022-04-29T04:05:02Z","abstract_excerpt":"The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting. Though this has been demonstrated to work on a variety of tasks, in this paper we show some deficiencies of this approach and propose a one-step mixed training method that trains on both source and target data with \\textit{stochastic gradient surgery}, a novel gradient-level optimization. Unlike the previous studies that focus on one language at a time when target-adapting, "},"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":"2204.13869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-29T04:05:02Z","cross_cats_sorted":[],"title_canon_sha256":"5a60641879a45a2cdffb9a64f26d26f332996678eda76a12fa434756e39dfd82","abstract_canon_sha256":"b9bcf505c1b690c60237cce9d2551d5ede592c3fe17b5d022dd61faf9b1892e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:54.464009Z","signature_b64":"jWSA+JyhRc0mXuSxhZoXpFZOdHAd/W7RM94LlvH3ylOULosyKKCi5np6dEyym31eJ1ZgXj9JGD1TRwENMmHCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"521156109bb0483c5ae4fa20bd787daa388a41cc2292ce4da7768e7510df2320","last_reissued_at":"2026-07-05T04:18:54.463663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:54.463663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Por Qu\\'e N\\~ao Utiliser Alla Spr{\\aa}k? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Xu, Kenton Murray","submitted_at":"2022-04-29T04:05:02Z","abstract_excerpt":"The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting. Though this has been demonstrated to work on a variety of tasks, in this paper we show some deficiencies of this approach and propose a one-step mixed training method that trains on both source and target data with \\textit{stochastic gradient surgery}, a novel gradient-level optimization. Unlike the previous studies that focus on one language at a time when target-adapting, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13869","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/2204.13869/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":"2204.13869","created_at":"2026-07-05T04:18:54.463719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.13869v1","created_at":"2026-07-05T04:18:54.463719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13869","created_at":"2026-07-05T04:18:54.463719+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIIVMEE3WBED","created_at":"2026-07-05T04:18:54.463719+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIIVMEE3WBEDYWXE","created_at":"2026-07-05T04:18:54.463719+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIIVMEE3","created_at":"2026-07-05T04:18:54.463719+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/KIIVMEE3WBEDYWXE7IQL26D5VI","json":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI.json","graph_json":"https://pith.science/api/pith-number/KIIVMEE3WBEDYWXE7IQL26D5VI/graph.json","events_json":"https://pith.science/api/pith-number/KIIVMEE3WBEDYWXE7IQL26D5VI/events.json","paper":"https://pith.science/paper/KIIVMEE3"},"agent_actions":{"view_html":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI","download_json":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI.json","view_paper":"https://pith.science/paper/KIIVMEE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.13869&json=true","fetch_graph":"https://pith.science/api/pith-number/KIIVMEE3WBEDYWXE7IQL26D5VI/graph.json","fetch_events":"https://pith.science/api/pith-number/KIIVMEE3WBEDYWXE7IQL26D5VI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI/action/storage_attestation","attest_author":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI/action/author_attestation","sign_citation":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI/action/citation_signature","submit_replication":"https://pith.science/pith/KIIVMEE3WBEDYWXE7IQL26D5VI/action/replication_record"}},"created_at":"2026-07-05T04:18:54.463719+00:00","updated_at":"2026-07-05T04:18:54.463719+00:00"}