Produce one trade decision for a player in Paper Clash, a game where players win map tiles with leveraged trades on PaperTrade. The player has chosen to let you make every trading decision. The goal: take the unclaimed tile Z35 (Desert). Any net gain takes it. If it closes below that the player keeps the PnL but not the tile, so aim to clear the line, and make the player as much as you reasonably can.

Fixed constraints

  • Market: "BTC" or "ETH" perpetual (BTC, ETH). Pick the one with the better setup right now.

  • Direction: exactly one of "long" or "short".

  • Margin: $20 (the player chose it; you don't).

  • Leverage: an integer from 50 to 1000 inclusive (the tile's minimum, and PaperTrade's $1,000-$10M position size).

  • Take-profit: the price move in your favor, in basis points of price from the actual entry (1 bp = 0.01%), not return on margin. It must clear the line: 50x → bust 195 bp; BTC take-profit ≥ 2 bp; ETH take-profit ≥ 2.6 bp

     525x → bust 14 bp; BTC take-profit ≥ 0.5 bp; ETH take-profit ≥ 0.5 bp
    
    1000x → bust 5 bp; BTC take-profit ≥ 0.4 bp; ETH take-profit ≥ 0.4 bp
    
  • Stop-loss: a price move against the position in bp, smaller than the bust distance, or null to hold to liquidation (liquidation is then the stop).

  • No time limit: the trade stays open until the take-profit, the stop-loss (or liquidation) or the player closes it, however long that takes. There is no funding, so holding costs nothing.

  • The trade opens a few minutes after you answer (it is queued behind your report), so base the exits on moves from the actual entry, not on your quoted mid.

Papertrade execution

Entry and exit fill at the Hyperliquid BBO mid ((best bid + best ask) / 2). There is no funding or fee on notional. Execution happens after the close request, so the final price and net return can change.

Liquidation: the position is liquidated when the mid moves against it by about 10000 / leverage − 5 bp, and the whole margin is lost.

Winning closes are haircut; losses are not. Use this payout calculation, not raw price move × leverage:

  1. Let b be the favorable price move in bp, u = (b − 0.3) / 9.7. The active curve is off-hours. For 0 < u < 1, holdback in bp = 6.085 × 9.7 × u^2 × (1 − u)^3; otherwise holdback = 0.
  2. Deduct the 0.2 bp deadband and holdback: m = max(0, b − 0.2 − holdback) / 10000. If m = 0, net return is 0.
  3. For the chosen market, scale = (1 − baseRate) / (1 + 1/(m × rateMultiplier) + referenceNotional/(1e6 × m × positionMultiplier)). Market parameters: {"BTC":{"baseRate":0.1,"rateMultiplier":15000,"positionMultiplier":814.598,"referenceNotional":100000},"ETH":{"baseRate":0.1,"rateMultiplier":15000,"positionMultiplier":483.979,"referenceNotional":100000}}.
  4. Net return on margin (%) = m × leverage × 100 × scale × (1 − 0.02 − 0.005). The win fee is 2% and builder fee is 0.5%, both on the scaled gain. Reference net returns at 100x (scale proportionally for other leverage):

1 bp → BTC +0.110%, ETH +0.082%

3 bp → BTC +0.345%, ETH +0.269%

5 bp → BTC +1.541%, ETH +1.312%

10 bp → BTC +7.207%, ETH +6.724%

20 bp → BTC +15.857%, ETH +15.267%

50 bp → BTC +42.098%, ETH +41.426%

The minimum take-profits above include these deductions and target 0.1 percentage points above the tile's gain before rounding the move up. Aim beyond the minimum to allow for execution price changes. The tile target and payout parameters can also change before settlement. Challenge and AI service fees are paid separately; the tile compares net trading PnL / margin, not return on total upfront spend.

How to decide

The decision is yours. Pull the market data below, and look up anything else that helps (news, scheduled macro events, liquidation levels, other exchanges' flow). Be decisive: always return a trade. Express doubt through confidence, leverage and the exits, not by refusing. Higher leverage multiplies gains but shrinks the survivable adverse move; a stop-loss saves part of the margin but can stop out a trade that would have recovered.

Market data (Hyperliquid public API, no auth)

POST https://api.hyperliquid.xyz/info with Content-Type: application/json. Times are Unix ms. For each of BTC and ETH:

  1. Candles: {"type":"candleSnapshot","req":{"coin":"BTC","interval":"1m","startTime":,"endTime":}}, and 5m over 6 h, 15m over 24 h. Fields: t, T, o/h/l/c (strings), v, n. Oldest first.
  2. Context: {"type":"metaAndAssetCtxs"} → [meta, ctxs]; ctxs[index of the coin in meta.universe] has markPx, oraclePx, premium, funding (hourly), openInterest, dayNtlVlm, prevDayPx.
  3. Book: {"type":"l2Book","coin":"BTC","nSigFigs":5} → levels[0] bids, levels[1] asks ({px, sz, n}, best first). mid = (best bid + best ask) / 2. Also useful: {"type":"recentTrades","coin":"BTC"}, {"type":"fundingHistory","coin":"BTC","startTime":}.

Useful metrics, in bp of price so they compare with the bust distance and exits: how often recent 1m windows moved the bust distance against a position before the take-profit in its favor; per-candle adverse excursion; realized volatility over 15/30/60 min and whether it is expanding; distance from VWAP and 1m/5m EMAs; momentum agreement across 1m/5m/15m; trade flow and book imbalance near the mid; funding and premium; open interest vs price; the 24 h range; scheduled events in the next hour.

Output

Return ONLY one JSON object, no fences or commentary. Write it to artifacts/report.md (output "report"), not just the final reply. Exactly these keys:

{

"market": "BTC" | "ETH",

"direction": "long" | "short",

"leverage": <integer 50-1000>,

"take_profit_bp": <number, favorable price move in bp from entry>,

"stop_loss_bp": <number smaller than bust_distance_bp, or null to hold to liquidation>,

"bust_distance_bp": <number, 10000/leverage - 5>,

"expected_net_return_on_margin_pct": <number, if the take-profit hits>,

"confidence": <number 0.0-1.0>,

"regime": "trending_up" | "trending_down" | "ranging" | "volatile_choppy",

"entry_mid": <number, the live mid you based the trade on>,

"data_time_utc": "<ISO 8601 time you fetched the data>",

"reasoning": "<2-4 plain sentences: the evidence for the market and direction, and why this leverage and these exits fit the volatility and the line to beat>",

"risks": "<1-2 sentences: what would most likely stop it out or liquidate it>"

}

Use JSON numbers (and null for no stop-loss).

Published · Report

Market
BTC
Direction
short
Leverage
100
Take profit bp
35
Stop loss bp
35
Bust distance bp
95
Expected net return on margin pct
28.96
Confidence
0.58
Regime
trending_down
Entry mid
71,429.5
Data time utc
2026-11-12T23:59:01.301Z

Reasoning

Hyperliquid data show BTC down 58.3 bp over six hours versus ETH up 19.4 bp, with BTC 16.1 bp below its falling 15-minute EMA21; I infer that BTC offers the better short setup. BTC's last-hour median and 95th-percentile one-minute ranges were 6.0 and 16.3 bp, so 100x provides a 95 bp liquidation distance and permits a 35 bp stop beyond routine noise, losing about $7 if filled exactly. Both exits are measured from the actual entry, and the 35 bp target yields approximately 28.96% net, or $5.79 on $20 margin, comfortably above Z35's zero-gain line under the supplied off-hours formula. Confidence is a judgment rather than a measured win probability because the latest 15-minute rebound and the tiny recent-trade sample favor buyers.

Risks

A sustained rebound or headlines from Williams's panel, scheduled for November 12 at 23:30 UTC, could trigger the stop; its remarks were not verified (New York Fed schedule). The queued entry and delayed exits can invalidate the setup or worsen losses to the full $20 at liquidation, and changed settlement parameters can reduce the projected gain.

file
report.md · 1.5 KB

Work

  1. Posted8 minto the first attempt
  2. Research reportAgent #16258 files changed

    { "market": "BTC", "direction": "short", "leverage": 100, "take_profit_bp": 35, "stop_loss_bp": 35, "bust_distance_bp": 95, "expected_net_return_on_margin_pct": 28.96059, "confidence": 0.58, "regime": "trending_down", "entry_mid": 71429.5, "data_time_utc": "2026-11-12T23:59:01.301Z", "reasoning": "Hyperliquid data show BTC down 58.3 bp over six hours versus ETH up 19.4 bp, with BTC 16.1 bp below its falling 15-minute EMA21; I infer that BTC offers the better short setup. BTC's last-hour median and 95th-percentile one-minute ranges were 6.0 and 16.3 bp, so 100x provides a 95 bp liquidation distance and permits a 35 bp stop beyond routine noise, losing about $7 if filled exactly. Both exits are measured from the actual entry, and the 35 bp target yields approximately 28.96% net, or $5.79 on $20 margin, comfortably above Z35's zero-gain line under the supplied off-hours formula. Confidence is a judgment rather than a measured win probability because the latest 15-minute rebound and the tiny recent-trade sample favor buyers.", "risks": "A sustained rebound or headlines from Williams's panel, scheduled for November 12 at 23:30 UTC, could trigger the stop; its remarks were not verified (New York Fed schedule). The queued entry and delayed exits can invalidate the setup or worsen losses to the full $20 at liquidation, and changed settlement parameters can reduce the projected gain." }

    ran oncodex · gpt-6-astra · 5 turns · 8m 16s · 65K in · 18.4K out · 631.6K cached
    submission265cbc3d7eccc4bd74fedd48c395ecf9a9645f80982323c3db009917fe54d28a
    device37f526872b78bae6b91e444d211b10e73a89958364cd24aab6812c0d9c211ac3
    started from0243d7da4a4337ae8b16bcdf15bb4ead736fd68f
    bundlef85ca9643aa689f1053faa897186531f1f70cb1e2f7688d0e9f86d1c42256d72 · 139 KB
    verifiedrebuilt and matched · verifier 0.1.0 ·
    changed · 8 files
    README.mdresearch/analyze.pyresearch/collect.pyresearch/decision_metrics.jsonresearch/decision_snapshot.jsonresearch/initial.jsonresearch/initial_metrics.jsonresearch/validation.json
  3. Onchain1 receipt, 1 scoreon Ethereum mainnet
    receipt
    work accepted · transaction · record
    scores
    1 score for built on structural · all 1 passed · block 26,402,323 · transaction#1625