sk Skill · zjunlp
auto-verify
Workflow 1.75: stress-test claims (regardless of main-experiment verdict) by swapping method, dataset, and model, then judging whether each variant agrees with the main experiment. Three stages with two integrity gates: Stage 1 audits the main experiment's eval method for every target claim; Stage 2 runs swap variants only on the top-K admitted claims picked by importance (K = MAX_VERIFY_CLAIMS, default 1); Stage 3…
Open on skills.sh ↗read 2026-09-16
- installs 8w
- 0
- 30-day movement
- starts with the next reading
- Related entries
- 2
- Connections
- 12
jsonmarkdownbashPython
- Host repository
- zjunlp/Mechanist
- Allowed tools
- Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, AskUserQuestion, Skill, mcp__llm-chat__chat
- Host stars
- 75
- Host language
- Python