{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JNPRRBT2KGX6DBTRN7M2DX3IPH","short_pith_number":"pith:JNPRRBT2","schema_version":"1.0","canonical_sha256":"4b5f18867a51afe186716fd9a1df6879e6e1fc1f05329c5847a9215ff232ab4b","source":{"kind":"arxiv","id":"2406.02301","version":2},"attestation_state":"computed","paper":{"title":"mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiyuan Lai, Malvina Nissim","submitted_at":"2024-06-04T13:30:45Z","abstract_excerpt":"Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a multilingual context, the question of how reliable this reasoning capability is in different languages is still open. To address it directly, we study multilingual reasoning consistency across multiple languages, using popular open-source LLMs. First, we compile the first large-scale multilingual math reasoning dataset, mCoT-MATH, covering eleven diverse language"},"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":"2406.02301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T13:30:45Z","cross_cats_sorted":[],"title_canon_sha256":"9bf88b405997245364a22aa6f9eb41da04f9479c66b8df2f1349c109ef0913c5","abstract_canon_sha256":"5a092932b5b90475a6cea1dcbcf225690d8f821fb3dab123d5ef1aba8e46cc66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:04.538454Z","signature_b64":"eo2A8VwUsHdt9rVZmb9Ek2f1ajoydP0OwHazcFFdx3qRIfUhX3lAe6XGq6cWBc0wVkClQnCz23iqlj1jptjFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b5f18867a51afe186716fd9a1df6879e6e1fc1f05329c5847a9215ff232ab4b","last_reissued_at":"2026-07-05T08:42:04.537991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:04.537991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiyuan Lai, Malvina Nissim","submitted_at":"2024-06-04T13:30:45Z","abstract_excerpt":"Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a multilingual context, the question of how reliable this reasoning capability is in different languages is still open. To address it directly, we study multilingual reasoning consistency across multiple languages, using popular open-source LLMs. First, we compile the first large-scale multilingual math reasoning dataset, mCoT-MATH, covering eleven diverse language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02301","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/2406.02301/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":"2406.02301","created_at":"2026-07-05T08:42:04.538048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02301v2","created_at":"2026-07-05T08:42:04.538048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02301","created_at":"2026-07-05T08:42:04.538048+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNPRRBT2KGX6","created_at":"2026-07-05T08:42:04.538048+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNPRRBT2KGX6DBTR","created_at":"2026-07-05T08:42:04.538048+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNPRRBT2","created_at":"2026-07-05T08:42:04.538048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00485","citing_title":"Efficient Multilingual Reasoning Transfer via Progressive Code-Switching","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13286","citing_title":"English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH","json":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH.json","graph_json":"https://pith.science/api/pith-number/JNPRRBT2KGX6DBTRN7M2DX3IPH/graph.json","events_json":"https://pith.science/api/pith-number/JNPRRBT2KGX6DBTRN7M2DX3IPH/events.json","paper":"https://pith.science/paper/JNPRRBT2"},"agent_actions":{"view_html":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH","download_json":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH.json","view_paper":"https://pith.science/paper/JNPRRBT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02301&json=true","fetch_graph":"https://pith.science/api/pith-number/JNPRRBT2KGX6DBTRN7M2DX3IPH/graph.json","fetch_events":"https://pith.science/api/pith-number/JNPRRBT2KGX6DBTRN7M2DX3IPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH/action/storage_attestation","attest_author":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH/action/author_attestation","sign_citation":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH/action/citation_signature","submit_replication":"https://pith.science/pith/JNPRRBT2KGX6DBTRN7M2DX3IPH/action/replication_record"}},"created_at":"2026-07-05T08:42:04.538048+00:00","updated_at":"2026-07-05T08:42:04.538048+00:00"}