← TwiceShy proof pageAll belief versionsSource

Replay of round 18

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 0.060 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 18, 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 pricesv100.58checked, right–R2-j7arf…HlMU
    Sui Address Inspectoraddress factsv150.77bought on trust, not checked–im4qb-GB…pOjQ
    PipTradeDexmarket pricesv130.85bought on trust, not checked–Q9vx_EIl…nNzg
    Control seller (ours)address factsv60.53checked, right–Wycisxkn…sEUw
    AgentProofendpoint checksv30.21failed, nothing delivered16:25 UTCNu3kUpVC…BnW8
    Omnia endpoint verifyendpoint checksv30.21dead route16:25 UTCF_dcq_Fb…d6IA
    PipTradeDexswap quotesv60.50bought on trust, not checked–0EJ3DoUF…VkQo
    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 on trust. Reason it gave: “cheapest good answer at trust 0.77”.

    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 on trust. Reason it gave: “cheapest good answer at trust 0.85”.

    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

    Control seller (ours) control (ours), as a purchase on trust. Reason it gave: “cheapest good answer at trust 0.63”.

    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
    E9x1xmFmJ2p15gKAodW22PYq7cRHAsc7Bzkj9ZrZWPcK
    Answer in
    0.8 s
    At
    16:16:25 UTC
    Control seller (ours) control (ours) · address facts
    Paid
    0.010 USDC
    Sui transaction
    C4yDr6heRnAGD5uCBYKQuztsAgsEJHu3W34ag2qQBC8s
    Answer in
    0.7 s
    At
    16:16:32 UTC
    PipTradeDex independent · market prices
    Paid
    0.020 USDC
    Sui transaction
    y6BFAuAwxfKAUKeMcwmrouh3oFrQrSAZ9Ubm3Q917uD
    Answer in
    10.8 s
    At
    16:16:46 UTC
    Control seller (ours) control (ours) · market prices
    Paid
    0.010 USDC
    Sui transaction
    o1ueReEDUkseqZ6XkLWgJcMeaLsyGaoVCr9PgMZkE37
    Answer in
    1.0 s
    At
    16:16:51 UTC
    Control seller (ours) control (ours) · swap quotes
    Paid
    0.010 USDC
    Sui transaction
    5swiDrAqdgSXgPmCLiB3pzTd2DUAgSuqW2MotEBiJwxn
    Answer in
    1.0 s
    At
    16:16:55 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 5 balances matched the chain)
    Control seller (ours) · address facts
    Its own check
    checked, right (all 3 balances matched the chain)
    The audit
    right (all 3 balances matched the chain)
    PipTradeDex · market prices
    Its own check
    bought on trust, not checked
    The audit
    right (price within 0.14% of the reference)
    Control seller (ours) · market prices
    Its own check
    checked, right (price within 0.00% of the reference)
    The audit
    right (price within 0.00% of the reference)
    Control seller (ours) · swap quotes
    Its own check
    bought on trust, not checked
    The audit
    right (implied price within 0.01%)

    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
    A6vLa9dx…2KvA in twiceshy-verdicts
    Belief written
    v16: trust 0.77 → 0.77. bought unchecked on a trust of 0.77
    Walrus blob
    -Qq42tjjwGw40oatXs_ojTVoGCqPwiluOrBKMKcuTVA in twiceshy-belief-inspector-address-facts
    Control seller (ours) · address facts
    Verdict memory
    haDXQvFw…uWnw in twiceshy-verdicts
    Belief written
    v7: trust 0.53 → 0.59. passed: all 3 balances matched the chain
    Walrus blob
    SHTRD7gwd4o0EsL_2TvKDFHVZBdWOmxHirSyB7748us in twiceshy-belief-control-address-facts
    PipTradeDex · market prices
    Verdict memory
    ZXYUDpQ_…XNHw in twiceshy-verdicts
    Belief written
    v14: trust 0.85 → 0.85. bought unchecked on a trust of 0.85
    Walrus blob
    JjuU2oOuUXmOQaBR_Qbnh2EgS-NJN87NctJ3CW60dzM in twiceshy-belief-piptradedex-market-price
    Control seller (ours) · market prices
    Verdict memory
    iCxc4FVU…2MVg in twiceshy-verdicts
    Belief written
    v11: trust 0.58 → 0.63. passed: price within 0.00% of the reference
    Walrus blob
    dEZ4TG6tjN1dQj8p5OdNDHRXBdynuYq-gAFcQbl9c0c in twiceshy-belief-control-market-price
    Control seller (ours) · swap quotes
    Verdict memory
    9YHqw3hM…FlSs in twiceshy-verdicts
    Belief written
    v3: trust 0.50 → 0.50. bought unchecked on a trust of 0.50
    Walrus blob
    uvJNkfiaRT1hrS1BAOURALjtDVn7QRDAIrC5PCGvyUg in twiceshy-belief-control-swap-quote

    Round 19 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 independent0.010ABtFiZ9Z…8WRDright (all 1 balances matched the chain)
market pricesControl seller (ours) control (ours)0.010ERGpPtBT…SAw1right (price within 0.00% 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)0.010HNJuuPUU…H92Zright (implied price within 0.03%)

Other rounds

← Round 17 · Round 19 → · Round 7 is the first round after our control seller's fault was caught.