{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OGH2DXLRNAOEHIY4KBFLBT5E2O","short_pith_number":"pith:OGH2DXLR","schema_version":"1.0","canonical_sha256":"718fa1dd71681c43a31c504ab0cfa4d38d966b8d6618af8b99852666628ac59c","source":{"kind":"arxiv","id":"2511.23231","version":2},"attestation_state":"computed","paper":{"title":"Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Qin, Qiming Li, Ruihan Chen, Xiachong Feng, Xiaocheng Feng, Yixuan Ma, Zekai Ye","submitted_at":"2025-11-28T14:40:27Z","abstract_excerpt":"Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Eng"},"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":"2511.23231","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-28T14:40:27Z","cross_cats_sorted":[],"title_canon_sha256":"089dd44623690c8a38a30b5ed7970f1ce045eb37d2490fd3c1a6870d437dd358","abstract_canon_sha256":"486869d0354b31369e7b3f769cd2d971407ee519341e342aaaf4841267dadbea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:19:56.947765Z","signature_b64":"N8pku/R9irvTcjv00KSZgUgSNxVxbmEcs7dyhEqJMNKyaQeLt+zHNO1puXYiwM5PZgA5phKJ+JOFTNycWngMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718fa1dd71681c43a31c504ab0cfa4d38d966b8d6618af8b99852666628ac59c","last_reissued_at":"2026-07-14T01:19:56.946803Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:19:56.946803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Qin, Qiming Li, Ruihan Chen, Xiachong Feng, Xiaocheng Feng, Yixuan Ma, Zekai Ye","submitted_at":"2025-11-28T14:40:27Z","abstract_excerpt":"Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Eng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.23231","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/2511.23231/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":"2511.23231","created_at":"2026-07-14T01:19:56.947259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.23231v2","created_at":"2026-07-14T01:19:56.947259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.23231","created_at":"2026-07-14T01:19:56.947259+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGH2DXLRNAOE","created_at":"2026-07-14T01:19:56.947259+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGH2DXLRNAOEHIY4","created_at":"2026-07-14T01:19:56.947259+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGH2DXLR","created_at":"2026-07-14T01:19:56.947259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00485","citing_title":"Efficient Multilingual Reasoning Transfer via Progressive Code-Switching","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O","json":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O.json","graph_json":"https://pith.science/api/pith-number/OGH2DXLRNAOEHIY4KBFLBT5E2O/graph.json","events_json":"https://pith.science/api/pith-number/OGH2DXLRNAOEHIY4KBFLBT5E2O/events.json","paper":"https://pith.science/paper/OGH2DXLR"},"agent_actions":{"view_html":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O","download_json":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O.json","view_paper":"https://pith.science/paper/OGH2DXLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.23231&json=true","fetch_graph":"https://pith.science/api/pith-number/OGH2DXLRNAOEHIY4KBFLBT5E2O/graph.json","fetch_events":"https://pith.science/api/pith-number/OGH2DXLRNAOEHIY4KBFLBT5E2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O/action/storage_attestation","attest_author":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O/action/author_attestation","sign_citation":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O/action/citation_signature","submit_replication":"https://pith.science/pith/OGH2DXLRNAOEHIY4KBFLBT5E2O/action/replication_record"}},"created_at":"2026-07-14T01:19:56.947259+00:00","updated_at":"2026-07-14T01:19:56.947259+00:00"}