Fix [END] tag format in inference.py and update .gitignore to skip logs for HF compliance 9d97259 GGOisW commited on Apr 8
fix(grader): use 0.01 and 0.99 bounds to definitively prevent edge rounding to 1.0 by OpenEnv validators 8d47366 GGOisW commited on Apr 8
Make everything rigorously bulletproof: squash every sub-reward component 440f1a8 GGOisW commited on Apr 8
Aggressive fix: Clamp everything globally to strictly avoid 0.0 or 1.0 task scores 3891231 GGOisW commited on Apr 8
Final fix: Squash rewards and scores to strictly (0, 1) for Phase 2 validation 8b9ab47 GGOisW commited on Apr 8
fix: bulletproof score clamping - add _safe_score() + NaN/Inf handling + grade endpoint safety net 5ee2b30 GGOisW commited on Apr 8
fix(grader): ensure task grader outputs diverse scores strictly within (0,1) b1633cb GGOisW commited on Apr 8
fix: update docs and metadata to strictly (0,1) score range - no 0.0 or 1.0 references 7d3480f GGOisW commited on Apr 7
fix(grader): ensure scores fall strictly within (0, 1) range to pass Phase 2 pipeline 64713ef GGOisW commited on Apr 7
Fix score ranges: clamping scores strictly within (0, 1) per validator logic 2a508a5 GGOisW commited on Apr 7
Fix eval timeout: added API timeouts and reduced max retries in inference.py ed62201 GGOisW commited on Apr 7
Fix Docker build failures: added .dockerignore and pinned dependencies 9403315 GGOisW commited on Apr 7
fix: add main() function and update server entry point for validator compliance b124f30 GGOisW commited on Apr 4
feat: finalize OpenEnv benchmark with risk management engine and spec compliance 034dbb3 GGOisW commited on Apr 3
feat: complete CryptoRiskEnv hackathon project with 2-1 RRR and validated graders d47e223 GGOisW commited on Mar 31