Use when working on dataset materialization, model training, backtesting, scan-edge signals, paper-trading workflows, or experiment artifacts in polymarket-tmax-lab.
Use this skill for the research and trading simulation loop.
AGENTS.md.docs/agent-skills/research-loop.mddocs/codebase/modeling.mddocs/codebase/backtest-execution.mdbuild-dataset MUST use --markets-path configs/market_inventory/full_training_set_snapshots.json.
Running without it rebuilds with only 12 example rows (destroys training data).full_training_set_snapshots.json is a checked-in training inventory. It is not the auto-refreshed canonical historical backlog.configs/market_inventory/historical_temperature_snapshots.json first and then intentionally regenerate full_training_set_snapshots.json from that curated inventory.historical_training_set* / historical_backtest_panel overwrite requires .--allow-canonical-overwrite--output-name values for experiments and rely on the automatic artifacts/recovery/ backup when promoting canonical output.scan-edge MUST include --min-model-prob 0.05 --max-model-prob 0.95.scripts/run_price_check.sh and redirect to an absolute logs/price_check.log path. Do not put raw uv run python scripts/log_gamma_prices.py commands directly in crontab.train-advanced --model-name lgbm_emos --variant <variant>.uv run python scripts/quick_eval.py (champion baseline + OOF variants).observation-report, observation-shadow, observation-daemon, approve-live-candidate.paper-multimodel-report, execution-sensitivity-report, market-bottleneck-report.execution-watchlist-playbook.exact_public intraday -> documented research intraday -> METAR fallback, target-day only.station-dashboard, station-dashboard-daemon.artifacts/signals/v2/execution_watchlist_playbook.json when present and raises Tier A ask-threshold alerts without changing live guardrails.station-cycle, station-daemon.artifacts/benchmarks/v2/benchmark_summary.jsonrecency_neighbor_oof (CRPS 0.7463 honest, MAE 0.591, σ calibrated 2–5°).pmtmax-autoresearch when you are exploring new lgbm_emos candidates around recency_neighbor_oof.uv run pmtmax build-dataset --markets-path configs/market_inventory/full_training_set_snapshots.json --forecast-missing-only --allow-canonical-overwriteuv run pmtmax bootstrap-lab --forecast-missing-onlyuv run pmtmax backfill-forecasts --markets-path configs/market_inventory/historical_temperature_snapshots.json --strict-archive --missing-onlyuv run pmtmax backfill-forecasts --markets-path configs/market_inventory/historical_temperature_snapshots.json --strict-archive --missing-only --single-run-horizon market_open --single-run-horizon previous_evening --single-run-horizon morning_ofdata/parquet/gold/v2/historical_training_set.parquetartifacts/models/v2/artifacts/models/v2/champion.jsonartifacts/signals/v2/scan_edge_latest.jsonartifacts/signals/v2/live_pilot_queue.jsonartifacts/signals/v2/forward_paper_trades.jsonlogs/daily_experiment.logscripts/run_price_check.shlogs/price_check.logconfigs/paper-exploration.yamlconfigs/paper-all-supported-horizon-policy.yamlartifacts/signals/v2/execution_watchlist_playbook.json