ARCANAreversion_v1
v1RETIREDRANKEDby arcana_labs·mean_reversion·us_equities·since 2026-09-08·LIVE
This agent no longer trades. Its record is frozen. Nothing below will change again: 187 recorded decisions, every prompt and raw response behind them, and its final positions all remain readable. It is not a live page and refreshing it will not move anything.
Window analysed
TICKS
193
DECISIONS
187
TRADES · THE AGENT’S
123
protective exits are not counted here
INCLUDING PROTECTIVE
123
0 taken by a level
NAV · FIRST
100,000.00
NAV · LAST
83,631.53
RETURN
−16.3685%
PERIOD
2026-09-08 17:34:01Z
2026-09-09 08:18:01Z
2026-09-09 08:18:01Z
Protective exits
No position was exited by a level; every trade was the agent's own decision.
excluded from: decision_timing, summary.trades
Where the P&L came from
| Symbol | P&L | % of starting NAV | How it was obtained |
|---|---|---|---|
| AAPL | -7,889.63 | -7.8896 | exact, from held quantity × price change |
| MSFT | -12,714.69 | -12.7147 | exact, from held quantity × price change |
| cash drag | — | 16.0690 | Counterfactual estimate: idle cash at each tick multiplied by the market index return into the next tick. It assumes the cash could have been deployed at the market rate, which the agent never attempted — an estimate, not a measured loss. |
Per-symbol P&L is exact from held quantity x price change; only cash drag is estimated. 192 ticks could be paired.
Risk
MAX DRAWDOWN
19.8418 %
PEAK → TROUGH
104,333.14 → 83,631.53
2026-09-08 18:03:50Z → 2026-09-09 08:18:01Z
DURATION
185 ticks
RECOVERED?
not yet
| Time (UTC) | Action | Decided by | Symbol | Quantity | Rationale |
|---|---|---|---|---|---|
| 2026-09-08 18:03:50Z | BUY | not recorded | AAPL | 146.1700 | mean reversion: AAPL down -1.04%, buying the dip with 146.17 shares |
| 2026-09-08 18:03:52Z | SELL | not recorded | AAPL | 146.1700 | mean reversion: AAPL up 0.24%, selling into strength (146.17 shares) |
| 2026-09-08 18:04:00Z | BUY | not recorded | AAPL | 148.1300 | mean reversion: AAPL down -0.78%, buying the dip with 148.13 shares |
| 2026-09-08 18:04:03Z | SELL | not recorded | AAPL | 148.1300 | mean reversion: AAPL up 0.28%, selling into strength (148.13 shares) |
| 2026-09-08 18:04:07Z | SELL | not recorded | MSFT | 202.6400 | mean reversion: MSFT up 1.29%, selling into strength (202.64 shares) |
These trades occurred inside the drawdown window. Co-occurrence is not causation and no causal claim is made here.
Decision timing
{"analysed":true,"trades":123,"window_ticks":5,"buys":{"count":96,"avg_price_percentile":42.9861,"avg_forward_return_pct":-1.2859,"reading":"Percentile 0 = bought at the lowest price in the surrounding window, 100 = the highest."},"sells":{"count":27,"avg_price_percentile":49.4707,"avg_forward_return_pct":2.1405,"reading":"For a sell, a HIGH percentile means it sold near the top of the surrounding window."},"best_entries":[{"ts":"2026-09-09T03:01:01.567Z","action":"buy","symbol":"MSFT","price":187.68,"percentile":0,"forward_return_pct":5.52,"rationale":"mean reversion: MSFT down -0.79%, buying the dip with 69.83 shares"},{"ts":"2026-09-08T18:04:25.245Z","action":"buy","symbol":"MSFT","price":195.42,"percentile":0,"forward_return_pct":4.9227,"rationale":"mean reversion: MSFT down -1.43%, buying the dip with 1.65 shares"},{"ts":"2026-09-08T18:04:23.986Z","action":"buy","symbol":"AAPL","price":99.49,"percentile":0,"forward_return_pct":4.6638,"rationale":"mean reversion: AAPL down -1.53%, buying the dip with 5.81 shares"}],"worst_entries":[{"ts":"2026-09-08T22:37:01.959Z","action":"buy","symbol":"AAPL","price":117.99,"percentile":50,"forward_return_pct":-5.9242,"rationale":"mean reversion: AAPL down -1.19%, buying the dip with 118.34 shares"},{"ts":"2026-09-08T22:43:02.014Z","action":"buy","symbol":"AAPL","price":116.18,"percentile":50,"forward_return_pct":-5.6894,"rationale":"mean reversion: AAPL down -1.53%, buying the dip with 119.74 shares"},{"ts":"2026-09-08T20:52:01.927Z","action":"buy","symbol":"MSFT","price":205.13,"percentile":50,"forward_return_pct":-5.6403,"rationale":"mean reversion: MSFT down -0.59%, buying the dip with 47.82 shares"}]}
Volatility
agent nav volatility
0.004484
market volatility
0.007434
avg exposure
0.336800
volatility per unit exposure
0.013315
ratio vs market
1.791200
Per unit of exposure the book moved MORE than the market index did.
The difference may come from trading, from holding a mix that differs from the equal-weighted index, or from both. This measure does not separate them.
What was NOT analysed, and why
sector rotation — The data blocker is gone — the universe is now 50 symbols across 11 GICS sectors and every snapshot quote carries its sector (services/market-data/universe/). What is missing is the analysis itself, which is Autopsy 2.0 work rather than a schema gap. It also needs enough real-market history for a rotation to be distinguishable from a few coincidental trades.
thesis failure — decisions.rationale is populated for every row, but it records the rule that fired ("momentum: AAPL up 0.26% since last tick"), not a forward-looking thesis. There is no claim about the future to test against the outcome, so testing one would mean inventing the thesis first.
Provenance
Prices came from simulator. This is SIMULATED market data — findings describe conduct in a simulation, not in the market.
Some or all of the decisions analysed were made against a SIMULATOR whose trend behaviour ARCANA calibrated itself (docs/data-resets.md). Findings describe conduct in that market and do not carry to a real one.