{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MFPYBDNOMM7XPGO2HQX3R7EMXZ","short_pith_number":"pith:MFPYBDNO","schema_version":"1.0","canonical_sha256":"615f808dae633f7799da3c2fb8fc8cbe670dd9ce64233fe3ead3513eebeec013","source":{"kind":"arxiv","id":"2406.19759","version":2},"attestation_state":"computed","paper":{"title":"Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Orgest Xhelili, Yihong Liu","submitted_at":"2024-06-28T08:59:24Z","abstract_excerpt":"Multilingual pre-trained models (mPLMs) have shown impressive performance on cross-lingual transfer tasks. However, the transfer performance is often hindered when a low-resource target language is written in a different script than the high-resource source language, even though the two languages may be related or share parts of their vocabularies. Inspired by recent work that uses transliteration to address this problem, our paper proposes a transliteration-based post-pretraining alignment (PPA) method aiming to improve the cross-lingual alignment between languages using diverse scripts. We s"},"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":"2406.19759","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T08:59:24Z","cross_cats_sorted":[],"title_canon_sha256":"34c767e658a0d2f2540bca9becb4e2701288eb9c919e740662c1d6a772341936","abstract_canon_sha256":"e0e77d5546f7ba7b68349a2b5d416c7340237b2ea398b3fe60459c4f4bcbaa19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:44.731501Z","signature_b64":"Lied4mWqxWjS8VlB9ZXAmw9OR3jdQ1rC+I7+SbC9q8T0fqVWgWnqmT2k9EdwfL3jg8AvTRp73SV0bLYIClPACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"615f808dae633f7799da3c2fb8fc8cbe670dd9ce64233fe3ead3513eebeec013","last_reissued_at":"2026-07-05T09:17:44.731013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:44.731013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Orgest Xhelili, Yihong Liu","submitted_at":"2024-06-28T08:59:24Z","abstract_excerpt":"Multilingual pre-trained models (mPLMs) have shown impressive performance on cross-lingual transfer tasks. However, the transfer performance is often hindered when a low-resource target language is written in a different script than the high-resource source language, even though the two languages may be related or share parts of their vocabularies. Inspired by recent work that uses transliteration to address this problem, our paper proposes a transliteration-based post-pretraining alignment (PPA) method aiming to improve the cross-lingual alignment between languages using diverse scripts. We s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19759","kind":"arxiv","version":2},"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/2406.19759/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":"2406.19759","created_at":"2026-07-05T09:17:44.731070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19759v2","created_at":"2026-07-05T09:17:44.731070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19759","created_at":"2026-07-05T09:17:44.731070+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFPYBDNOMM7X","created_at":"2026-07-05T09:17:44.731070+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFPYBDNOMM7XPGO2","created_at":"2026-07-05T09:17:44.731070+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFPYBDNO","created_at":"2026-07-05T09:17:44.731070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19799","citing_title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ","json":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ.json","graph_json":"https://pith.science/api/pith-number/MFPYBDNOMM7XPGO2HQX3R7EMXZ/graph.json","events_json":"https://pith.science/api/pith-number/MFPYBDNOMM7XPGO2HQX3R7EMXZ/events.json","paper":"https://pith.science/paper/MFPYBDNO"},"agent_actions":{"view_html":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ","download_json":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ.json","view_paper":"https://pith.science/paper/MFPYBDNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19759&json=true","fetch_graph":"https://pith.science/api/pith-number/MFPYBDNOMM7XPGO2HQX3R7EMXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MFPYBDNOMM7XPGO2HQX3R7EMXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ/action/storage_attestation","attest_author":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ/action/author_attestation","sign_citation":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ/action/citation_signature","submit_replication":"https://pith.science/pith/MFPYBDNOMM7XPGO2HQX3R7EMXZ/action/replication_record"}},"created_at":"2026-07-05T09:17:44.731070+00:00","updated_at":"2026-07-05T09:17:44.731070+00:00"}