Revision History
RLVR · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected the misattributed Limits-of-RLVR citation (the pass@k study is Yue et al., arXiv:2504.13837, not arXiv:2510.27044, whose authors were also misnamed), the Tulu 3 RLVR gains wrongly labeled as 70B results, the claim that OpenThinker3 uses RLVR (it is SFT-only), the misdescriptions of RLPR and RLPT, the spurious-rewards result and mechanism, and the brute-force self-verification behavior misattributed to o3 and o4-mini's launch post (plus 34 minor fixes)
Version 6 · Nov 4, 2026, 07:19 PM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:21 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:29 PM