← TwiceShy proof pageAll belief versionsSource

Replay of round 1

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.

    Nothing yet: this is the first round, so memory holds no belief and every seller starts untrusted. Each one has to pass a canary first.

    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 canary (a question it can check, to earn trust). Reason it gave: “canary: nobody is trusted yet”.

    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

    Control seller (ours) control (ours), as a canary (a question it can check, to earn trust). Reason it gave: “canary: nobody is trusted yet”.

    PipTradeDex independent, as a canary (a question it can check, to earn trust). Reason it gave: “canary: earning a place”.

    endpoint checks

    AgentProof independent, as a canary (a question it can check, to earn trust). Reason it gave: “canary: nobody is trusted yet”.

    Omnia endpoint verify independent, as a canary (a question it can check, to earn trust). Reason it gave: “canary: earning a place”.

    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
    7eUR3KPcmnutHVe9rRTVqzeaDyxfNXirTxbU2D4Ngab2
    Answer in
    1.2 s
    At
    14:00:23 UTC
    Control seller (ours) control (ours) · address facts
    Paid
    0.010 USDC
    Sui transaction
    AUkvG1568JA22evJhqPNnuzvDXRW3zpNpiwHfJhBM6y9
    Answer in
    0.7 s
    At
    14:00:36 UTC
    Control seller (ours) control (ours) · market prices
    Paid
    0.010 USDC
    Sui transaction
    7eyErsqAfkmm4NFV1sWFcF7ZMqA94BWBCAxMez4WKK2f
    Answer in
    1.0 s
    At
    14:00:40 UTC
    PipTradeDex independent · market prices
    Paid
    0.020 USDC
    Sui transaction
    G2hh8rq9ct7bnSigLykhX9m9Wk83NQKUJq4ktm9TuVb7
    Answer in
    10.2 s
    At
    14:00:53 UTC
    AgentProof independent · endpoint checks
    Paid
    0.000 USDC (nothing settled)
    Answer in
    0.3 s
    At
    14:01:08 UTC
    Omnia endpoint verify independent · endpoint checks
    Paid
    0.000 USDC (nothing settled)
    At
    14:01:10 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 22 balances matched the chain)
    The audit
    right (all 22 balances matched the chain)
    Control seller (ours) · address facts
    Its own check
    checked, right (all 22 balances matched the chain)
    The audit
    right (all 22 balances matched the chain)
    Control seller (ours) · market prices
    Its own check
    checked, right (price within 0.04% of the reference)
    The audit
    right (price within 0.04% of the reference)
    PipTradeDex · market prices
    Its own check
    checked, right (price within 0.11% of the reference)
    The audit
    right (price within 0.11% of the reference)
    AgentProof · endpoint checks
    Its own check
    failed, nothing delivered (signed payment offered, seller returned HTTP 500, nothing settled)
    The audit
    no answer to audit
    Omnia endpoint verify · endpoint checks
    Its own check
    dead route (HTTP 404 before any payment)
    The audit
    no answer to audit

    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
    jqSrSNt1…UX0A in twiceshy-verdicts
    Belief written
    v1: trust 0.67. passed: all 22 balances matched the chain
    Walrus blob
    k_rxRLxzc07Qn_rk0LJ7EYY7lYHZMiTJ7Q8MophbvH0 in twiceshy-belief-inspector-address-facts
    Control seller (ours) · address facts
    Verdict memory
    QujTkv9y…qiTQ in twiceshy-verdicts
    Belief written
    v1: trust 0.67. passed: all 22 balances matched the chain
    Walrus blob
    hwBjNu886glCAYjZbk4Ma8-OH2wJhbvmCAen3RF6tp0 in twiceshy-belief-control-address-facts
    Control seller (ours) · market prices
    Verdict memory
    Zv7N8cfC…9EjE in twiceshy-verdicts
    Belief written
    v1: trust 0.67. passed: price within 0.04% of the reference
    Walrus blob
    ngDywYwVpDTZFWfgZZtzyI-KhbRT00FkL3sA6BtVG-0 in twiceshy-belief-control-market-price
    PipTradeDex · market prices
    Verdict memory
    TKWKUWiK…L5fw in twiceshy-verdicts
    Belief written
    v1: trust 0.67. passed: price within 0.11% of the reference
    Walrus blob
    uuhQjYkEliQyL6UiX08dTQBrRpPLHFcvNhH3nhs7AeQ in twiceshy-belief-piptradedex-market-price
    AgentProof · endpoint checks
    Verdict memory
    U9FoKnpo…SqOE in twiceshy-verdicts
    Belief written
    v1: trust 0.33. failed: signed payment offered, seller returned HTTP 500, nothing settled; retest after 20 min
    Walrus blob
    VWRgmj1_ZVJAYTNyG0sHJIagEZO0WJDekrayHwkbJcY in twiceshy-belief-agentproof-endpoint-check
    Omnia endpoint verify · endpoint checks
    Verdict memory
    2SKshZU3…ctGw in twiceshy-verdicts
    Belief written
    v1: trust 0.33. dead: HTTP 404 before any payment; retest after 20 min
    Walrus blob
    IFawCml9O175SNuNMbyqSOwa671Z7QT_ImHaRINXYY4 in twiceshy-belief-omnia-endpoint-check

    Round 2 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)0.010fP2xtjGa…SJ8tright (all 27 balances matched the chain)
market pricesControl seller (ours) control (ours)0.010CkMM8pk2…mPRBright (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 2 → · Round 7 is the first round after our control seller's fault was caught.