{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KPBJQAYAHZLD52IBCJ4E4DCNIC","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":"724f5e4fa58cd3cf9e8424e7a1a91bfdec40d174c38d336fbeda528c18b1cff0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T14:47:52Z","title_canon_sha256":"cd63e7c0380df0ccac85b4c11474ab92f91e13fb604b272b92540086dec1e0be"},"schema_version":"1.0","source":{"id":"2605.22567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22567","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22567v1","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22567","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"KPBJQAYAHZLD","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"KPBJQAYAHZLD52IB","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"KPBJQAYA","created_at":"2026-05-22T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:fb7f1e4a7bc6d9f2dbeff3e6bbb27160fb541433243ebdb4f6ecf25ba954ed74","target":"graph","created_at":"2026-05-22T01:04:57Z","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/2605.22567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off: prioritizing input-language consistency severely hampers reasoning quality, while prioritizing reasoning often leads to unintended language drift toward English. We address this challenge with LANG, a novel framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks. Our method incorporates two key mechanisms to preve","authors_text":"Bei Li, Jian Yang, Jingang Wang, Jingbo Zhu, Peiguang Li, Rongxiang Weng, Tong Xiao, Xin Chen, Xunliang Cai, Yilin Wang, Yongyu Mu, Yuchun Fan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T14:47:52Z","title":"LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22567","kind":"arxiv","version":1},"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":"sha256:6412ff2c3790d205539d03adf48afbc7e73d10c2fb04ffda8f7d442db80ee69d","target":"record","created_at":"2026-05-22T01:04:57Z","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":"724f5e4fa58cd3cf9e8424e7a1a91bfdec40d174c38d336fbeda528c18b1cff0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T14:47:52Z","title_canon_sha256":"cd63e7c0380df0ccac85b4c11474ab92f91e13fb604b272b92540086dec1e0be"},"schema_version":"1.0","source":{"id":"2605.22567","kind":"arxiv","version":1}},"canonical_sha256":"53c29803003e563ee90112784e0c4d40a710e25a2d8e41e93da135269aa0576e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53c29803003e563ee90112784e0c4d40a710e25a2d8e41e93da135269aa0576e","first_computed_at":"2026-05-22T01:04:57.892018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:57.892018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fahzzqHY+jHr051W9t5i2GXTNaLveuvEU7jwcv7MmDa3iNhqcQOqsfsUm3PdqFMwL0pbsdvvLqT+q00/NZRfAQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:57.892923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6412ff2c3790d205539d03adf48afbc7e73d10c2fb04ffda8f7d442db80ee69d","sha256:fb7f1e4a7bc6d9f2dbeff3e6bbb27160fb541433243ebdb4f6ecf25ba954ed74"],"state_sha256":"d9c74e1b653e035c5733aa5203dc1dd06dfce6e3cbe3b268d0ffa2b47d2d9eb4"}