{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6LU4SFUHA4DE676OGSKUFVR5NI","short_pith_number":"pith:6LU4SFUH","schema_version":"1.0","canonical_sha256":"f2e9c9168707064f7fce349542d63d6a3c1c36e9f654fbae887c71500e128c73","source":{"kind":"arxiv","id":"2507.03003","version":1},"attestation_state":"computed","paper":{"title":"Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongxiang Fan, Nicholas D. Lane, Royson Lee, Wanru Zhao, Xinchi Qiu, Yan Gao, Yihong Chen","submitted_at":"2025-07-02T05:23:20Z","abstract_excerpt":"Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and languages. However, the fine-tuning of multilingual LLMs, especially for low-resource languages, faces significant challenges arising from data-sharing restrictions (the physical border) and inherent linguistic differences (the linguistic border). These barriers hinder users of various languages, particularly those in low-resource regions, from fully benefiting from the advantages of LLMs. To address these challenges"},"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":"2507.03003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T05:23:20Z","cross_cats_sorted":[],"title_canon_sha256":"3f7a97f8ea02649cdc953e434e949c52cdfea958de4cab3b54f6348e1aec3ed4","abstract_canon_sha256":"149cf2519a5d7a8f774891f81891812a0a645ae646c5bd93767ab036c8dad585"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:50.565606Z","signature_b64":"g5r3OwUb1g53fGeOuR4dKnfB1KSnOapT6QBgHTNMJ0J20amvdbDoMro/NORpANEUNMRY2Ip3gKH7x6orEj4SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2e9c9168707064f7fce349542d63d6a3c1c36e9f654fbae887c71500e128c73","last_reissued_at":"2026-07-05T11:31:50.565122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:50.565122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongxiang Fan, Nicholas D. Lane, Royson Lee, Wanru Zhao, Xinchi Qiu, Yan Gao, Yihong Chen","submitted_at":"2025-07-02T05:23:20Z","abstract_excerpt":"Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and languages. However, the fine-tuning of multilingual LLMs, especially for low-resource languages, faces significant challenges arising from data-sharing restrictions (the physical border) and inherent linguistic differences (the linguistic border). These barriers hinder users of various languages, particularly those in low-resource regions, from fully benefiting from the advantages of LLMs. To address these challenges"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03003","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/2507.03003/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":"2507.03003","created_at":"2026-07-05T11:31:50.565172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03003v1","created_at":"2026-07-05T11:31:50.565172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03003","created_at":"2026-07-05T11:31:50.565172+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LU4SFUHA4DE","created_at":"2026-07-05T11:31:50.565172+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LU4SFUHA4DE676O","created_at":"2026-07-05T11:31:50.565172+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LU4SFUH","created_at":"2026-07-05T11:31:50.565172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06202","citing_title":"Cross-Lingual Transfer and Parameter-Efficient Adaptation in the Turkic Language Family: A Theoretical Framework for Low-Resource Language Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI","json":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI.json","graph_json":"https://pith.science/api/pith-number/6LU4SFUHA4DE676OGSKUFVR5NI/graph.json","events_json":"https://pith.science/api/pith-number/6LU4SFUHA4DE676OGSKUFVR5NI/events.json","paper":"https://pith.science/paper/6LU4SFUH"},"agent_actions":{"view_html":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI","download_json":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI.json","view_paper":"https://pith.science/paper/6LU4SFUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03003&json=true","fetch_graph":"https://pith.science/api/pith-number/6LU4SFUHA4DE676OGSKUFVR5NI/graph.json","fetch_events":"https://pith.science/api/pith-number/6LU4SFUHA4DE676OGSKUFVR5NI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI/action/storage_attestation","attest_author":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI/action/author_attestation","sign_citation":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI/action/citation_signature","submit_replication":"https://pith.science/pith/6LU4SFUHA4DE676OGSKUFVR5NI/action/replication_record"}},"created_at":"2026-07-05T11:31:50.565172+00:00","updated_at":"2026-07-05T11:31:50.565172+00:00"}