{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AA2V5E6JBFF6WBMV7JW4DAIJCW","short_pith_number":"pith:AA2V5E6J","schema_version":"1.0","canonical_sha256":"00355e93c9094beb0595fa6dc1810915b951f2d7e71204e336cd2f357785e006","source":{"kind":"arxiv","id":"2305.15011","version":2},"attestation_state":"computed","paper":{"title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Fajri Koto, Haonan Li, Minghao Wu, Timothy Baldwin","submitted_at":"2023-05-24T10:50:31Z","abstract_excerpt":"Instruction tuning has shown great promise in improving the performance of large language models. However, research on multilingual instruction tuning has been limited due to the scarcity of high-quality instruction-response datasets across different languages. To bridge this gap, we present Bactrian-X, a comprehensive multilingual parallel dataset of 3.4 million instruction-response pairs across 52 languages. Leveraging this dataset, we train a set of adapters using low-rank adaptation (LoRA), which are lightweight components that seamlessly integrate with large language models. These adapter"},"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":"2305.15011","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T10:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"2bc7d1755bbb061f7cb3d3113c7b378031d9c222736a409715af45505cc44a38","abstract_canon_sha256":"9842a5790cb48ab1b319fa84c560c48113268f5f3965861a9486d820a111ee42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:56.911141Z","signature_b64":"wagqif4gSwV6LYZZXKJZ6yoM5PHv+1D1xpmtyHqGQZnuOW2exzg0LVc/OX8VX28wJveAFbhfrPSz7O2VUc23AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00355e93c9094beb0595fa6dc1810915b951f2d7e71204e336cd2f357785e006","last_reissued_at":"2026-07-05T06:58:56.910743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:56.910743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Fajri Koto, Haonan Li, Minghao Wu, Timothy Baldwin","submitted_at":"2023-05-24T10:50:31Z","abstract_excerpt":"Instruction tuning has shown great promise in improving the performance of large language models. However, research on multilingual instruction tuning has been limited due to the scarcity of high-quality instruction-response datasets across different languages. To bridge this gap, we present Bactrian-X, a comprehensive multilingual parallel dataset of 3.4 million instruction-response pairs across 52 languages. Leveraging this dataset, we train a set of adapters using low-rank adaptation (LoRA), which are lightweight components that seamlessly integrate with large language models. These adapter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15011","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/2305.15011/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":"2305.15011","created_at":"2026-07-05T06:58:56.910797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15011v2","created_at":"2026-07-05T06:58:56.910797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15011","created_at":"2026-07-05T06:58:56.910797+00:00"},{"alias_kind":"pith_short_12","alias_value":"AA2V5E6JBFF6","created_at":"2026-07-05T06:58:56.910797+00:00"},{"alias_kind":"pith_short_16","alias_value":"AA2V5E6JBFF6WBMV","created_at":"2026-07-05T06:58:56.910797+00:00"},{"alias_kind":"pith_short_8","alias_value":"AA2V5E6J","created_at":"2026-07-05T06:58:56.910797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.16154","citing_title":"AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.12720","citing_title":"FLEXITOKENS: Flexible Tokenization for Evolving Language Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW","json":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW.json","graph_json":"https://pith.science/api/pith-number/AA2V5E6JBFF6WBMV7JW4DAIJCW/graph.json","events_json":"https://pith.science/api/pith-number/AA2V5E6JBFF6WBMV7JW4DAIJCW/events.json","paper":"https://pith.science/paper/AA2V5E6J"},"agent_actions":{"view_html":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW","download_json":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW.json","view_paper":"https://pith.science/paper/AA2V5E6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15011&json=true","fetch_graph":"https://pith.science/api/pith-number/AA2V5E6JBFF6WBMV7JW4DAIJCW/graph.json","fetch_events":"https://pith.science/api/pith-number/AA2V5E6JBFF6WBMV7JW4DAIJCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW/action/storage_attestation","attest_author":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW/action/author_attestation","sign_citation":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW/action/citation_signature","submit_replication":"https://pith.science/pith/AA2V5E6JBFF6WBMV7JW4DAIJCW/action/replication_record"}},"created_at":"2026-07-05T06:58:56.910797+00:00","updated_at":"2026-07-05T06:58:56.910797+00:00"}