{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XE5T2XSNFE3ZJRIGJPK3MZUM6N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c051aaf219ad27075e4034f140a5990c68571d35d5431574053d4f1170aa10a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T13:03:45Z","title_canon_sha256":"6a790bdc75e55d64c42d8656196138bfa1e166b7bdf4647d2a755fd52494dbcc"},"schema_version":"1.0","source":{"id":"2407.09879","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09879","created_at":"2026-07-05T11:23:49Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09879v4","created_at":"2026-07-05T11:23:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09879","created_at":"2026-07-05T11:23:49Z"},{"alias_kind":"pith_short_12","alias_value":"XE5T2XSNFE3Z","created_at":"2026-07-05T11:23:49Z"},{"alias_kind":"pith_short_16","alias_value":"XE5T2XSNFE3ZJRIG","created_at":"2026-07-05T11:23:49Z"},{"alias_kind":"pith_short_8","alias_value":"XE5T2XSN","created_at":"2026-07-05T11:23:49Z"}],"graph_snapshots":[{"event_id":"sha256:68d2ebe142b3a10c0a2a79256d4577a3ebf2a53494575abead198f21212d2ab6","target":"graph","created_at":"2026-07-05T11:23:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.09879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively augmenting English instruction-response pairs with multilingual translations. Additionally, we propose LANGIT, a novel N-shot guided fine-tuning strategy, which further enhances model performance by inc","authors_text":"Ahmed Awadallah, Arindam Mitra, Barun Patra, Hardik Hansrajbhai Chauhan, Kriti Aggarwal, Kumar Tanmay, Luciano Del Corro, Monojit Choudhary, Sanchit Ahuja, Sunayana Sitaram, Tejas Indulal Dhamecha, Vishrav Chaudhary","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T13:03:45Z","title":"sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09879","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fb95c74caf232bfece3a473743631a826de46ace136844cda69feba18e642a66","target":"record","created_at":"2026-07-05T11:23:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c051aaf219ad27075e4034f140a5990c68571d35d5431574053d4f1170aa10a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T13:03:45Z","title_canon_sha256":"6a790bdc75e55d64c42d8656196138bfa1e166b7bdf4647d2a755fd52494dbcc"},"schema_version":"1.0","source":{"id":"2407.09879","kind":"arxiv","version":4}},"canonical_sha256":"b93b3d5e4d293794c5064bd5b6668cf36077b2dd56d068180522b036097d332d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b93b3d5e4d293794c5064bd5b6668cf36077b2dd56d068180522b036097d332d","first_computed_at":"2026-07-05T11:23:49.469809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:49.469809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SW3pHvS9yL1daP6NsDgZvV84hxssTOKL6Btrd//WSXadRlgCQkvMOfx5TXSDsJxtH0T1MFNh4/irNgaYi5xOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:49.470237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09879","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb95c74caf232bfece3a473743631a826de46ace136844cda69feba18e642a66","sha256:68d2ebe142b3a10c0a2a79256d4577a3ebf2a53494575abead198f21212d2ab6"],"state_sha256":"53a82789e36acdd8085f831bd8e7ba1d0cff29f1e35b5661d198727e488b9540"}