Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning

explore run Use this as the Rigor Improve / Rigor Explore run leaf skill. The installed slug remains explore run for compatibility. Use the shared operating principles in ../ai research reproduction/references/agent operating principles.md ; this skill should guide candidate run planning while preserving model judgment about the active repo. When to apply When the researcher explicitly authorizes exploratory runs. When the task is a small subset validation, short cycle training probe, batch sweep, idle GPU search, or quick transfer learning trial. When the output should rank candidate runs rather than certify trusted success. When not to apply When the user wants trusted training execution or conservative verification. When there is no explicit exploratory authorization. When the task is repository setup, intake, or debugging. Clear boundaries This skill owns exploratory execution planning and summary only. Use ai research explore instead when the task spans both current research coordination and exploratory code changes. It may hand off actual command execution to minimal run and audit or run train . It should keep experiment state isolated from the trusted baseline. It should prefer small subset and short cycle checks before heavier exploratory runs. It should label run results as bounded evidence and explain when a comparison is not directly fair. Ranking Semantics Pre execution candidate selection uses three factors: cost , success rate , and expected gain . Default weights should stay conservative unless the researcher explicitly provides selection weights . Budget pruning still applies after scoring through max variants and max short cycle runs . If runs are executed later, downstream ranking should switch to real execution evidence, not stay purely heuristic. Variant Spec Hints Use variant axes to define the candidate dimension grid. Use subset sizes and short run steps to express exploratory run scale. Use selection weights to rebalance cost , success rate , and expected gain . Use primary metric and metric goal so downstream ranking can order executed candidates consistently. Output expectations explore outputs/CHANGESET.md explore outputs/SCIENTIFIC CHANGELOG.md explore outputs/COMPARABILITY REPORT.md explore outputs/TOP RUNS.md explore outputs/status.json Notes Use references/execution policy.md , ../ai research reproduction/references/explore variant spec.md , ../ai research reproduction/references/deep learning experiment principles.md , scripts/plan variants.py , and scripts/write outputs.py .

explore-run