- Experiment request: H100 math sycophancy transfer to ConspiracyBench (d835158909dbadef130a67ecf04da73435b8e328)
- #442 return: thinking-off H100 run, outputs in completed_experiments/hillclimb/math-sycophancy-transfer (3d7e7e5816ae888e0bb434a1136c79b0e5ee5b24)
- Move the run package to completed_experiments/hillclimb/math-sycophancy-transfer/ (baa3529c4bff41cd89e295bcdeadbc1b429a03f1)
- Merge main into PR #442 (dfd9b8c39d1ed58dd5e57aa9112b33878639f29d)
Co-authored-by: Tomer Zipori <tomerz14@users.noreply.huggingface.co>
Co-authored-by: Екатерина К. <asdfasdfqrqwer@users.noreply.huggingface.co>
[experiment] Eval: Qwen3.5 4B with thinking off (2026-10-28) (#445)
- Eval: Qwen3.5 4B with thinking off (2026-10-28) (2637bee9022919831a68d8ae625999f679aa7186)
- Merge main into PR #445 (e8bf31293034b63cc709461d1ab14963546622cd)
Co-authored-by: Екатерина К. <asdfasdfqrqwer@users.noreply.huggingface.co>
[experiment] [request for compute] Experiment request: evidence-focused instruction evaluation (#441)
- Baseline eval: five ~4B thinking models on ConspiracyBench, graded by pplx-decider (6b6f55790034653f48f5bff82961d0dce49116a0)
- Move every eval output into outputs/, separate from the write-up and page source (c4a606dbe2189c97b65334c9aa20d117b683d8ce)
- Results page: pass@5 baselines table up front; rates stored at full precision (81394ee35f3bb164e29dd078e5e6cfbc1f241466)
- Results page: lower-is-better endorsement scores as the standard (ever/always endorses @5, endorsement rate) (e03035638939583f916eb400d6433d753faf19d3)
[experiment] Judge reliability: diagnosis, label review, rubric experiments, explorer (#409)
- [experiment] Judge reliability: diagnosis, label review, rubric experiments, explorer (748e53d9bc2899481ac638b02f7aeb23f835379d)
- Merge remote-tracking branch 'origin/pr/409' into reliability-v1.2-rerun (ba7b507c21bfc246a0340933d54f984617d3e2a9)
- decision_judges_v1: tag option and rerun entrypoint for repeat runs (7094ee6e4803b6a4e66bb8b66fe77da8300a158b)
- Judge reliability: rerun of the four decision judges on reference v1.2 (c67545f1c0629921d0f69ad0653bd7bb860e25ad)
- Judge reliability rerun: source of the combined judge-trust page (f92d1cb0fbf8cf5bbfe1302021e7f2b7763a6e7d)
- Judge reliability rerun: report only headline scores against the final labels (3703f7d70a6e7a50b5c790867486d85e7eae3405)
