Hour-Aware Adaptive Risk Management for Autonomous Memecoin Trading: Companion Dataset

Companion dataset to Kamat (2026), "Hour-Aware Adaptive Risk Management for Autonomous Memecoin Trading" (SSRN abstract_id 6564803). Reproduces the exact data underlying the paper's headline results: 190 closed paper-trades over a 15-day observation window (29 March – 12 April 2026, UTC), and 4,874 post-rejection price samples collected by the counterfactual tracking system across six anonymised filter categories. Filter labels in the post-rejection sample log are anonymised to filter_1 through filter_6 in descending order of sample volume. Liquidity and 24-hour volume are quantised to the nearest power of two (log2 binning) to preserve heavy-tailed distributional shape while preventing threshold inference. Filter-internal score columns and momentum-derivative price-change columns are removed. Two days of paired scanner observation logs are included as supporting context. SHA-256 checksums for all four CSV files are provided in checksums.txt. Reproducibility cutoffs: - trades.csv: date < 2026-04-12T18:00:00Z → 190 rows (matches paper exactly) - rejection_outcomes.csv: sampleTs < 2026-04-12T15:00:00Z → 4,874 rows (matches paper exactly)