{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:56:00Z","timestamp":1782910560445,"version":"3.54.5"},"publisher-location":"Stroudsburg, PA, USA","reference-count":0,"publisher":"Association for Computational Linguistics","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.18653\/v1\/2026.findings-acl.467","type":"proceedings-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:25:50Z","timestamp":1782908750000},"page":"9584-9605","source":"Crossref","is-referenced-by-count":0,"title":["MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting"],"prefix":"10.18653","author":[{"given":"Kangda","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1643","event":{"name":"Findings of the Association for Computational Linguistics: ACL 2026","location":"San Diego, California, United States","start":{"date-parts":[[2026,7]]},"end":{"date-parts":[[2026,7]]}},"container-title":["Findings of the Association for Computational Linguistics: ACL 2026"],"original-title":[],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:40:00Z","timestamp":1782909600000},"score":1,"resource":{"primary":{"URL":"https:\/\/aclanthology.org\/2026.findings-acl.467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.18653\/v1\/2026.findings-acl.467","relation":{},"subject":[],"published":{"date-parts":[[2026]]}}}