← TwiceShy proof pageAll belief versionsSource

Replay of round 10

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: 3 paid answers for 0.080 USDC, 1 refusal, 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 10, 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 pricesv70.40checked, wrong15:44 UTCThLEEklp…_dCE
    Sui Address Inspectoraddress factsv70.60checked, right–CLLjlRiR…wyk4
    PipTradeDexmarket pricesv50.79bought on trust, not checked–NhVmqEDp…rQzM
    Control seller (ours)address factsv30.27checked, wrong15:44 UTCi5K4HiK9…IrKY
    AgentProofendpoint checksv30.21failed, nothing delivered16:25 UTCNu3kUpVC…BnW8
    Omnia endpoint verifyendpoint checksv30.21dead route16:25 UTCF_dcq_Fb…d6IA
    PipTradeDexswap quotesv20.50bought on trust, not checked–28lQzw04…zF1M
    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 0.60”.

    market prices

    PipTradeDex independent, as a purchase with a spot check. 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 0.82”.

    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
    FPh4zx3JebLNCiSRBG3t8pRBdxf8Xhc4zWZ7q51v5dFU
    Answer in
    0.9 s
    At
    15:12:22 UTC
    PipTradeDex independent · market prices
    Paid
    0.020 USDC
    Sui transaction
    G7kyHDe3GDMv6YeQunTHNT5bfwXXkoW3kKx3x1ZRJ3W1
    Answer in
    9.4 s
    At
    15:12:36 UTC
    PipTradeDex independent · swap quotes
    Paid
    0.050 USDC
    Sui transaction
    FM36TuEecekZpvZb8fzqs4UNWjy5rTUJHXuYZ1nViERG
    Answer in
    1.3 s
    At
    15:12:40 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 9 balances matched the chain)
    The audit
    right (all 9 balances matched the chain)
    PipTradeDex · market prices
    Its own check
    checked, right (price within 0.10% of the reference)
    The audit
    right (price within 0.10% of the reference)
    PipTradeDex · swap quotes
    Its own check
    bought on trust, not checked
    The audit
    right (implied price within 0.02%)

    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
    P8fQTjul…AQz4 in twiceshy-verdicts
    Belief written
    v8: trust 0.60 → 0.65. passed: all 9 balances matched the chain
    Walrus blob
    8SDZIUWRtkg-3O81_F18ZFLdHxKtW8lQyx41uPuGnLU in twiceshy-belief-inspector-address-facts
    PipTradeDex · market prices
    Verdict memory
    odkhFiqX…w6s4 in twiceshy-verdicts
    Belief written
    v6: trust 0.79 → 0.82. passed: price within 0.10% of the reference
    Walrus blob
    ZAHnYyyOjUEHl34K28aDwdl3-UyYL1lQK1yZkMStcR8 in twiceshy-belief-piptradedex-market-price
    PipTradeDex · swap quotes
    Verdict memory
    wxsiE7ap…Wq10 in twiceshy-verdicts
    Belief written
    v3: trust 0.50 → 0.50. bought unchecked on a trust of 0.50
    Walrus blob
    PXnwJh5kmr3CZgiVzYZh1Pgz_VGaNiTMShfAQX6z4kU in twiceshy-belief-piptradedex-swap-quote

    Round 11 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 independent0.0106BsTtPSs…7yuvright (all 9 balances matched the chain)
market pricesControl seller (ours) control (ours)0.0105KTPtpLU…1Hgsaccepted 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)0.010GQkN9A1v…kJe8accepted a wrong answer (implied price 6.6% off)

Other rounds

← Round 9 · Round 11 → · Round 7 is the first round after our control seller's fault was caught.