← TwiceShy proof pageAll belief versionsSource

Replay of round 8

One round of the memory arm, step by step: what it read from Walrus Memory, what it decided to buy and why, the payment on Sui, how the answer was graded, and the belief version it wrote back.

Memory arm: 2 paid answers for 0.070 USDC, 2 refusals, 0 wrong answers accepted. Blind arm, same round: 3 paid answers for 0.030 USDC, 2 wrong answers accepted.

  1. 1Read memory

    Before buying anything, the agent recalls its beliefs from Walrus Memory. These are the newest version of each belief written before round 8, which is what a recall returns. The run did not log its recalls; the trace flag that prints them was added for the 2026-11-03 rerun, where the recalled versions matched the newest ones written.

    SellerForVersionTrustLast resultCooldown untilBlob
    Control seller (ours)market pricesv60.53checked, wrong15:00 UTCtVNQdxXd…Bm5w
    Sui Address Inspectoraddress factsv60.53checked, wrong15:00 UTCDeGJsdMQ…76z0
    PipTradeDexmarket pricesv30.79checked, right–VzRJYQg9…n6FU
    Control seller (ours)address factsv20.39checked, wrong15:00 UTCPQYgnkeA…CokA
    AgentProofendpoint checksv20.26failed, nothing delivered15:04 UTCfoxchlza…64Zs
    Omnia endpoint verifyendpoint checksv20.26dead route15:04 UTCLyV1InDE…gByc
    PipTradeDexswap quotesv10.50bought on trust, not checked–4WhJKawU…Fg_Y
    Control seller (ours)swap quotesv20.50bought on trust, not checked–oO2zUouH…YYDQ

    Next: Decide ↓

  2. 2Decide

    The trust policy is plain code over those beliefs: below the 0.6 floor a seller gets only canaries; in a cooldown it gets nothing; above the floor, the cheapest good seller wins, with spot checks that thin out as trust grows. If a checked answer fails, it tries the next seller once in the same round. Swap quotes it cannot check itself, so it buys them only from a seller its market-price belief trusts.

    address facts

    Refused to buy. Reason it gave: “no seller is trusted and none is due a canary”.

    market prices

    PipTradeDex independent, as a purchase on trust. Reason it gave: “cheapest good answer at trust 0.79”.

    endpoint checks

    Refused to buy. Reason it gave: “no seller is trusted and none is due a canary”.

    swap quotes

    PipTradeDex independent, as a purchase on trust. Reason it gave: “cheapest good answer at trust 0.79”.

    Next: Pay ↓

  3. 3Pay

    Each purchase is an x402 payment in USDC on Sui mainnet. Gas price is 0: these are gasless transfers.

    PipTradeDex independent · market prices
    Paid
    0.020 USDC
    Sui transaction
    G1A91tUvBZEAihdWyK6CpgK1c1qnZd3vQd6uwhv8B3ed
    Answer in
    9.4 s
    At
    14:56:23 UTC
    PipTradeDex independent · swap quotes
    Paid
    0.050 USDC
    Sui transaction
    CxWz73LgnNWF9byxJzh4LApDcuZ6fjBhXyuwr1j1DRP1
    Answer in
    1.1 s
    At
    14:56:28 UTC

    Next: Grade ↓

  4. 4Grade

    Its own check compares the answer with chain truth read through Tatum: balances for address facts, the deepest native USDC/SUI pool for market prices. Answers bought on trust are not checked by the agent. The audit is the experiment's scoring, which checks every answer; the agent never sees it.

    PipTradeDex · market prices
    Its own check
    bought on trust, not checked
    The audit
    right (price within 0.05% of the reference)
    PipTradeDex · swap quotes
    Its own check
    bought on trust, not checked
    The audit
    right (implied price within 0.00%)

    Next: Remember ↓

  5. 5Remember

    Each purchase becomes a verdict and a new version of that seller's belief, both written to Walrus Memory. The next round starts by reading these.

    PipTradeDex · market prices
    Verdict memory
    zIw4bN8U…wltM in twiceshy-verdicts
    Belief written
    v4: trust 0.79 → 0.79. bought unchecked on a trust of 0.79
    Walrus blob
    xvn71KjO5FkxQh_ACn60as6ZBEMEmvhZWCX1mv_JS0k in twiceshy-belief-piptradedex-market-price
    PipTradeDex · swap quotes
    Verdict memory
    OItF7PO9…veSI in twiceshy-verdicts
    Belief written
    v2: trust 0.50 → 0.50. bought unchecked on a trust of 0.50
    Walrus blob
    28lQzw04R4WV4z3D2S2ZwBAtaIOZKZQHCq9GW-TzF1M in twiceshy-belief-piptradedex-swap-quote

    Round 9 reads these back →

The blind arm in the same round

Same market, same round, no memory and no checks: it takes the cheapest listing every time.

ForSellerUSDCTransactionAudit
address factsSui Address Inspector independent0.010FyyXM7Le…qtETright (all 2 balances matched the chain)
market pricesControl seller (ours) control (ours)0.010G59iuJHp…XVL1accepted a wrong answer (price is 6.9% from the reference)
endpoint checksAgentProof independent0.000–failed, nothing delivered: signed payment offered, seller returned HTTP 500, nothing settled
endpoint checksOmnia endpoint verify independent0.000–dead route: HTTP 404 before any payment
swap quotesControl seller (ours) control (ours)0.0106GhzDYgu…Dc9Jaccepted a wrong answer (implied price 6.6% off)

Other rounds

← Round 7 · Round 9 → · Round 7 is the first round after our control seller's fault was caught.