Results for “evidence-matrix”
9 skillsMore results
Agent Sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
0
Exp Eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
77
Paper Plan
从 claim graph 编译论文大纲:编译 evidence map → 叙事结构 → 章节计划 + figure plan + citation plan,Review LLM review 必选
77
Result To Claim
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
1k
Detecting Data And Model Poisoning
Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.
24.6k · bundle
Agent Sort
Builds an evidence-backed ECC install plan for a repository by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes.
0
Ladder Of Inference Reflection
Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.
0
Agent Sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
1