← TwiceShy proof pageAll belief versionsSource

Replay of round 16

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: 5 paid answers for 0.100 USDC, 1 refusal, 0 wrong answers accepted. Blind arm, same round: 3 paid answers for 0.030 USDC, 0 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 16, 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 pricesv80.47checked, right–YK6drfSs…TL_k
    Sui Address Inspectoraddress factsv130.75bought on trust, not checked–K4nx7yoq…S_Oo
    PipTradeDexmarket pricesv110.84bought on trust, not checked–GnSFnEx3…qoSw
    Control seller (ours)address factsv40.38checked, right–MHXTm03M…AhUM
    AgentProofendpoint checksv30.21failed, nothing delivered16:25 UTCNu3kUpVC…BnW8
    Omnia endpoint verifyendpoint checksv30.21dead route16:25 UTCF_dcq_Fb…d6IA
    PipTradeDexswap quotesv50.50bought on trust, not checked–PWlLQbGF…IOnM
    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

    Sui Address Inspector independent, as a purchase with a spot check. Reason it gave: “cheapest good answer at trust 0.75”.

    Control seller (ours) control (ours), as a canary (a question it can check, to earn trust). Reason it gave: “canary: earning a place”.

    market prices

    PipTradeDex independent, as a purchase with a spot check. Reason it gave: “cheapest good answer at trust 0.84”.

    Control seller (ours) control (ours), as a canary (a question it can check, to earn trust). Reason it gave: “canary: earning a place”.

    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 0.85”.

    Next: Pay ↓

  3. 3Pay

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

    Sui Address Inspector independent · address facts
    Paid
    0.010 USDC
    Sui transaction
    9YN7nWU9rtQpNGbzgsvar1ekVbnPXMH3o6uNXoSEF6ty
    Answer in
    1.8 s
    At
    16:00:22 UTC
    Control seller (ours) control (ours) · address facts
    Paid
    0.010 USDC
    Sui transaction
    AGxzWBbYUbSUNEezzC1imKzwDvvhMQfiYsJhRg7LfDPg
    Answer in
    1.2 s
    At
    16:00:33 UTC
    PipTradeDex independent · market prices
    Paid
    0.020 USDC
    Sui transaction
    EYxhvp2Dz3FwYRngZ2CXWCZwuycLQmiFXRW8Jr38KdRr
    Answer in
    9.7 s
    At
    16:00:47 UTC
    Control seller (ours) control (ours) · market prices
    Paid
    0.010 USDC
    Sui transaction
    26t6vrw5aYoposqzChKqXAhb9m5z4QoDPBtFYtVRaN3F
    Answer in
    1.0 s
    At
    16:00:52 UTC
    PipTradeDex independent · swap quotes
    Paid
    0.050 USDC
    Sui transaction
    31XMBzWmdapnvcCeycuUZPwy98wn4yACNMDBXPHCd1bc
    Answer in
    1.2 s
    At
    16:00:56 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.

    Sui Address Inspector · address facts
    Its own check
    checked, right (all 1 balances matched the chain)
    The audit
    right (all 1 balances matched the chain)
    Control seller (ours) · address facts
    Its own check
    checked, right (all 21 balances matched the chain)
    The audit
    right (all 21 balances matched the chain)
    PipTradeDex · market prices
    Its own check
    checked, right (price within 0.04% of the reference)
    The audit
    right (price within 0.04% of the reference)
    Control seller (ours) · market prices
    Its own check
    checked, right (price within 0.14% of the reference)
    The audit
    right (price within 0.14% of the reference)
    PipTradeDex · swap quotes
    Its own check
    bought on trust, not checked
    The audit
    right (implied price within 0.13%)

    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.

    Sui Address Inspector · address facts
    Verdict memory
    xHPHdcvp…PuKQ in twiceshy-verdicts
    Belief written
    v14: trust 0.75 → 0.77. passed: all 1 balances matched the chain
    Walrus blob
    WgNcud4x2WmUNbmP7uSu2rHwROlhEruYyQPNPoUrZlc in twiceshy-belief-inspector-address-facts
    Control seller (ours) · address facts
    Verdict memory
    ZfB4Cv23…ytFA in twiceshy-verdicts
    Belief written
    v5: trust 0.38 → 0.47. passed: all 21 balances matched the chain
    Walrus blob
    42oiuPK2iemcb0RtyaztjKMta0jxXu0468rEImSaIk4 in twiceshy-belief-control-address-facts
    PipTradeDex · market prices
    Verdict memory
    W07BM1K7…qANc in twiceshy-verdicts
    Belief written
    v12: trust 0.84 → 0.85. passed: price within 0.04% of the reference
    Walrus blob
    5y7El70geigGsQ5jHBEr5WeoIJaeq5JdN0OYLD29QJA in twiceshy-belief-piptradedex-market-price
    Control seller (ours) · market prices
    Verdict memory
    kbOgv6ls…GFJk in twiceshy-verdicts
    Belief written
    v9: trust 0.47 → 0.53. passed: price within 0.14% of the reference
    Walrus blob
    TUc5_XCdnN-6YMDbQIsOTILqabs4OySmhnUNoxvKd_s in twiceshy-belief-control-market-price
    PipTradeDex · swap quotes
    Verdict memory
    r1A4Ckod…eD7s in twiceshy-verdicts
    Belief written
    v6: trust 0.50 → 0.50. bought unchecked on a trust of 0.50
    Walrus blob
    0EJ3DoUFvfrPmE-59aLNdN2Uy8rHQ0UhTZvx0nLVkQo in twiceshy-belief-piptradedex-swap-quote

    Round 17 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 independent0.000–failed, nothing delivered: signed payment offered, seller returned no response, nothing settled
address factsControl seller (ours) control (ours)0.010Be32r7sx…R14eright (all 5 balances matched the chain)
market pricesControl seller (ours) control (ours)0.0109LvajJaC…GN2Xright (price within 0.19% of 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)0.0103WJQr7xC…j4bJright (implied price within 0.11%)

Other rounds

← Round 15 · Round 17 → · Round 7 is the first round after our control seller's fault was caught.