← TwiceShy proof pageAll belief versionsSource

Replay of round 5

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 0.020 USDC, 1 refusal, 0 wrong answers accepted. Blind arm, same round: 2 paid answers for 0.020 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 5, 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 pricesv40.79bought on trust, not checked–_ULXcntI…xrF8
    Sui Address Inspectoraddress factsv40.79bought on trust, not checked–JIBXJqUL…Suu8
    PipTradeDexmarket pricesv10.67checked, right–uuhQjYkE…7AeQ
    Control seller (ours)address factsv10.67checked, right–hwBjNu88…6tp0
    AgentProofendpoint checksv20.26failed, nothing delivered15:04 UTCfoxchlza…64Zs
    Omnia endpoint verifyendpoint checksv20.26dead route15:04 UTCLyV1InDE…gByc
    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.

    address facts

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

    market prices

    Control seller (ours) control (ours), 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”.

    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
    Ck9yCoTCdNcEX6znZQSU4ssYb4EvYDKShqaFcHMSXRqh
    Answer in
    1.4 s
    At
    14:32:28 UTC
    Control seller (ours) control (ours) · market prices
    Paid
    0.010 USDC
    Sui transaction
    HUueJo3XvXbuXdpzZQf2V7Z8n1oJv256hejW4NmKA3yK
    Answer in
    1.0 s
    At
    14:32:34 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
    bought on trust, not checked
    The audit
    right (all 21 balances matched the chain)
    Control seller (ours) · market prices
    Its own check
    bought on trust, not checked
    The audit
    right (price within 0.08% of the reference)

    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
    I1DXIEZJ…saH4 in twiceshy-verdicts
    Belief written
    v5: trust 0.79 → 0.79. bought unchecked on a trust of 0.79
    Walrus blob
    l2aS1QW6NPmkgec8Smulq1AG5XQbKV_pIHdWeyrWMSQ in twiceshy-belief-inspector-address-facts
    Control seller (ours) · market prices
    Verdict memory
    jN9JqFhu…-tIM in twiceshy-verdicts
    Belief written
    v5: trust 0.79 → 0.79. bought unchecked on a trust of 0.79
    Walrus blob
    T7GNDA9MPUPuRc04oUHOwuxBR5Byr1lyeJ9wdaaRs54 in twiceshy-belief-control-market-price

    Round 6 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 independent0.0108CYCMv87…fsyXright (all 1 balances matched the chain)
market pricesControl seller (ours) control (ours)0.0106HkuqmyN…jzR3right (price within 0.04% 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

Other rounds

← Round 4 · Round 6 → · Round 7 is the first round after our control seller's fault was caught.