{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XFJKBHGM4M46QZUGU7Q72ANTZT","short_pith_number":"pith:XFJKBHGM","schema_version":"1.0","canonical_sha256":"b952a09ccce339e86686a7e1fd01b3ccd911a2a46fad0d4443809e2bfadae473","source":{"kind":"arxiv","id":"2506.01592","version":1},"attestation_state":"computed","paper":{"title":"Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Elshabrawy, Alham Fikri Aji, Annant Jain, Faadil Abdullah Shaikh, Jesus-German Ortiz-Barajas, Jonibek Mansurov, Lihan Feng, Mohamed Fazli Mohamed Imam, Rendi Chevi, Thanh-Nhi Nguyen, Yeeun Kang","submitted_at":"2025-06-02T12:28:03Z","abstract_excerpt":"Large Language Models (LLMs) excel in zero-shot and few-shot tasks, but achieving similar performance with encoder-only models like BERT and RoBERTa has been challenging due to their architecture. However, encoders offer advantages such as lower computational and memory costs. Recent work adapts them for zero-shot generalization using Statement Tuning, which reformulates tasks into finite templates. We extend this approach to multilingual NLP, exploring whether encoders can achieve zero-shot cross-lingual generalization and serve as efficient alternatives to memory-intensive LLMs for low-resou"},"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":"2506.01592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T12:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"94c7e3fd6723a0882367f83c50aba8e9d98ec4853e9a58d0d33f970a01dfd458","abstract_canon_sha256":"81e09c6b7ec9654a19f13a93938dbfc437f48b90a48d55fdf776af47dd56c68c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:16.387240Z","signature_b64":"KCHCDuBqWwu3GzURI4Dux6rfGbmncpEOqsv639jvkmeEuQdEObtVw+Ju6P6aF9siJIPsRun3vDi0WimNTCl8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b952a09ccce339e86686a7e1fd01b3ccd911a2a46fad0d4443809e2bfadae473","last_reissued_at":"2026-07-05T11:14:16.386764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:16.386764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Elshabrawy, Alham Fikri Aji, Annant Jain, Faadil Abdullah Shaikh, Jesus-German Ortiz-Barajas, Jonibek Mansurov, Lihan Feng, Mohamed Fazli Mohamed Imam, Rendi Chevi, Thanh-Nhi Nguyen, Yeeun Kang","submitted_at":"2025-06-02T12:28:03Z","abstract_excerpt":"Large Language Models (LLMs) excel in zero-shot and few-shot tasks, but achieving similar performance with encoder-only models like BERT and RoBERTa has been challenging due to their architecture. However, encoders offer advantages such as lower computational and memory costs. Recent work adapts them for zero-shot generalization using Statement Tuning, which reformulates tasks into finite templates. We extend this approach to multilingual NLP, exploring whether encoders can achieve zero-shot cross-lingual generalization and serve as efficient alternatives to memory-intensive LLMs for low-resou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01592","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/2506.01592/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":"2506.01592","created_at":"2026-07-05T11:14:16.386825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01592v1","created_at":"2026-07-05T11:14:16.386825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01592","created_at":"2026-07-05T11:14:16.386825+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFJKBHGM4M46","created_at":"2026-07-05T11:14:16.386825+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFJKBHGM4M46QZUG","created_at":"2026-07-05T11:14:16.386825+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFJKBHGM","created_at":"2026-07-05T11:14:16.386825+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/XFJKBHGM4M46QZUGU7Q72ANTZT","json":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT.json","graph_json":"https://pith.science/api/pith-number/XFJKBHGM4M46QZUGU7Q72ANTZT/graph.json","events_json":"https://pith.science/api/pith-number/XFJKBHGM4M46QZUGU7Q72ANTZT/events.json","paper":"https://pith.science/paper/XFJKBHGM"},"agent_actions":{"view_html":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT","download_json":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT.json","view_paper":"https://pith.science/paper/XFJKBHGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01592&json=true","fetch_graph":"https://pith.science/api/pith-number/XFJKBHGM4M46QZUGU7Q72ANTZT/graph.json","fetch_events":"https://pith.science/api/pith-number/XFJKBHGM4M46QZUGU7Q72ANTZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT/action/storage_attestation","attest_author":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT/action/author_attestation","sign_citation":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT/action/citation_signature","submit_replication":"https://pith.science/pith/XFJKBHGM4M46QZUGU7Q72ANTZT/action/replication_record"}},"created_at":"2026-07-05T11:14:16.386825+00:00","updated_at":"2026-07-05T11:14:16.386825+00:00"}