← TwiceShy proof pageAll belief versionsSource

Replay of round 15

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: 4 paid answers for 0.050 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 15, 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, wrong–ThLEEklp…_dCE
    Sui Address Inspectoraddress factsv120.75bought on trust, not checked–CAkEc1xP…6oY8
    PipTradeDexmarket pricesv100.84bought on trust, not checked–RzygKl2Z…HuuA
    Control seller (ours)address factsv30.27checked, wrong–i5K4HiK9…IrKY
    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.

    address facts

    Sui Address Inspector independent, as a purchase on trust. 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 on trust. 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”.

    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
    A6tK8HujbBUUyUkLqaXRyfWv6b28G5xrHQoqV456hp5Q
    Answer in
    0.7 s
    At
    15:52:24 UTC
    Control seller (ours) control (ours) · address facts
    Paid
    0.010 USDC
    Sui transaction
    92ZsxAs2Nedo1wcyGh97CwJ3nisY9xv8gPGEhfNoPh1x
    Answer in
    0.8 s
    At
    15:52:33 UTC
    PipTradeDex independent · market prices
    Paid
    0.020 USDC
    Sui transaction
    Fwx4FdgDsZg5vhrpzVKJXuurDu4WUmLSei72rJ1WdzKG
    Answer in
    11.6 s
    At
    15:52:48 UTC
    Control seller (ours) control (ours) · market prices
    Paid
    0.010 USDC
    Sui transaction
    6t7UsA4V9jHkDqxDAern5ChAR3onQSrBJc6gZoRcctbj
    Answer in
    1.0 s
    At
    15:52:54 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 1 balances matched the chain)
    Control seller (ours) · address facts
    Its own check
    checked, right (all 10 balances matched the chain)
    The audit
    right (all 10 balances matched the chain)
    PipTradeDex · market prices
    Its own check
    bought on trust, not checked
    The audit
    right (price within 0.02% of the reference)
    Control seller (ours) · market prices
    Its own check
    checked, right (price within 0.11% of the reference)
    The audit
    right (price within 0.11% 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
    xf14wY2x…-xP8 in twiceshy-verdicts
    Belief written
    v13: trust 0.75 → 0.75. bought unchecked on a trust of 0.75
    Walrus blob
    K4nx7yoqeEpakDGa5UC4QpPQdMj83XOf-feQrqyS_Oo in twiceshy-belief-inspector-address-facts
    Control seller (ours) · address facts
    Verdict memory
    IEJ3_M4j…irME in twiceshy-verdicts
    Belief written
    v4: trust 0.27 → 0.38. passed: all 10 balances matched the chain
    Walrus blob
    MHXTm03M7agSiDkS4xuaLM-lJht9Gd7FQ4jtfXXAhUM in twiceshy-belief-control-address-facts
    PipTradeDex · market prices
    Verdict memory
    lUUs8Wen…Ey7g in twiceshy-verdicts
    Belief written
    v11: trust 0.84 → 0.84. bought unchecked on a trust of 0.84
    Walrus blob
    GnSFnEx3MIjpLQyMddQi6_xP27Gyi2EpKZgqnrSqoSw in twiceshy-belief-piptradedex-market-price
    Control seller (ours) · market prices
    Verdict memory
    Du2uYvnr…T13Q in twiceshy-verdicts
    Belief written
    v8: trust 0.40 → 0.47. passed: price within 0.11% of the reference
    Walrus blob
    YK6drfSsu-MKqDLzXVljIZV-_q_h48NnIk_xdCMTL_k in twiceshy-belief-control-market-price

    Round 16 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 independent0.0108Pkikej3…fJuSright (all 8 balances matched the chain)
market pricesControl seller (ours) control (ours)0.0103a7p13Np…hRChright (price within 0.17% 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 14 · Round 16 → · Round 7 is the first round after our control seller's fault was caught.