mehdiforoozandeh/CANDI

candi-autoresearch

Design and run Karpathy-style autoresearch harnesses in CANDI/EpiDenoise. Use when planning FAFO loops, writing prepare.py/train.py/program.md, scope-fenced agent experiment search, or sandbox/autoresearch/* tags. Not for full sandbox production runs — those…

原文语言：英语

jepa-observability

Analyze CANDI JEPA runs. Triggers on: lejepa/* metrics, encoder_eff_rank, cos_sim_ctx_tgt, sigreg_loss, adaLN_gamma_norm, meta_sens_runtype, SIGReg lambda, pred_hidden bottleneck, UMAP/PCA encoder geometry, encoder collapse, trivial solution, metadata…

原文语言：英语

log-observability

Analyze sandbox.train run logs deterministically and act as autoresearch co-researcher on EpiDenoise sandbox runs. Use when the user asks to inspect, compare, rank, or diagnose sandbox runs, mentions metrics.jsonl / resolved_config.yaml / SLURM job IDs / W&B…

原文语言：英语

sandbox-idea-hub

Maintain the EpiDenoise/CANDI sandbox experiment idea hub. Use when planning, staging, running, documenting, or interpreting sandbox experiments, hypotheses, B/E/I experiment IDs, idea_*.md files, EXPERIMENTS.md, META.md, or sandbox run findings.

原文语言：英语

sandbox-synthesis

Produce cross-run synthesis docs for sandbox experiments. Use whenever rolling up findings across multiple sandbox runs (sweeps, ablations, head-isolation comparisons, longitudinal F* findings), creating or editing files matching…

原文语言：英语