{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CE6I76NT5PV7VG6FSTILI3BOFG","short_pith_number":"pith:CE6I76NT","schema_version":"1.0","canonical_sha256":"113c8ff9b3ebebfa9bc594d0b46c2e29a6174f453c18bac6be6719bebb9200ba","source":{"kind":"arxiv","id":"2410.08964","version":3},"attestation_state":"computed","paper":{"title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Chen Wang, Jiajun Zhang, Junhong Wu, Wen Yang","submitted_at":"2024-10-11T16:32:05Z","abstract_excerpt":"Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited \"first-class\" languages such as English and Chinese, leaving many other languages underrepresented. This imbalance, while limiting broader applications, generates a natural preference ranking between languages, offering an opportunity to bootstrap the multilingual capabilities of LLM in a self-improving manner. Thus, we propose $\\textit{Language Imbalance Driven Rewarding}$, where the inherent imbalance between dominant and non-dominant languag"},"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":"2410.08964","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T16:32:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76a7c69aa7a1596633e4666954158235e264c9b5ee20f9752b47b6cf436ad588","abstract_canon_sha256":"557d73ebd473b086b6543dd728b25ff2d468bc9e9abece1a64bf38d1ccd4358e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:16.246245Z","signature_b64":"VWU9hjzxRjQsdM8Td/zCpf/GVwGr+YnGatfOY7gM/eFugG4oH3WpsiWt7cHuk4LwfHG0jtMXiPM3x+1G96ASAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"113c8ff9b3ebebfa9bc594d0b46c2e29a6174f453c18bac6be6719bebb9200ba","last_reissued_at":"2026-07-05T10:20:16.245721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:16.245721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Chen Wang, Jiajun Zhang, Junhong Wu, Wen Yang","submitted_at":"2024-10-11T16:32:05Z","abstract_excerpt":"Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited \"first-class\" languages such as English and Chinese, leaving many other languages underrepresented. This imbalance, while limiting broader applications, generates a natural preference ranking between languages, offering an opportunity to bootstrap the multilingual capabilities of LLM in a self-improving manner. Thus, we propose $\\textit{Language Imbalance Driven Rewarding}$, where the inherent imbalance between dominant and non-dominant languag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08964","kind":"arxiv","version":3},"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/2410.08964/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":"2410.08964","created_at":"2026-07-05T10:20:16.245778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08964v3","created_at":"2026-07-05T10:20:16.245778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08964","created_at":"2026-07-05T10:20:16.245778+00:00"},{"alias_kind":"pith_short_12","alias_value":"CE6I76NT5PV7","created_at":"2026-07-05T10:20:16.245778+00:00"},{"alias_kind":"pith_short_16","alias_value":"CE6I76NT5PV7VG6F","created_at":"2026-07-05T10:20:16.245778+00:00"},{"alias_kind":"pith_short_8","alias_value":"CE6I76NT","created_at":"2026-07-05T10:20:16.245778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21593","citing_title":"Language as a Latent Variable for Reasoning Optimization","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG","json":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG.json","graph_json":"https://pith.science/api/pith-number/CE6I76NT5PV7VG6FSTILI3BOFG/graph.json","events_json":"https://pith.science/api/pith-number/CE6I76NT5PV7VG6FSTILI3BOFG/events.json","paper":"https://pith.science/paper/CE6I76NT"},"agent_actions":{"view_html":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG","download_json":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG.json","view_paper":"https://pith.science/paper/CE6I76NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08964&json=true","fetch_graph":"https://pith.science/api/pith-number/CE6I76NT5PV7VG6FSTILI3BOFG/graph.json","fetch_events":"https://pith.science/api/pith-number/CE6I76NT5PV7VG6FSTILI3BOFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG/action/storage_attestation","attest_author":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG/action/author_attestation","sign_citation":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG/action/citation_signature","submit_replication":"https://pith.science/pith/CE6I76NT5PV7VG6FSTILI3BOFG/action/replication_record"}},"created_at":"2026-07-05T10:20:16.245778+00:00","updated_at":"2026-07-05T10:20:16.245778+00:00"}