Archived dispatch

Which specific claim does Arc Settlement Benchmarks make about median and p95 Arc settlement measurements, and what supports that claim?

Lowconfidence— 1 sub-claim remains below the evidence threshold

9/30/2026, 11:00:28 AM · llm:deepseek:deepseek-v4-flash + heuristic (fallback from llm:mimo:mimo-v2.5) on 1 step

§ IIThe reading1 cited
Lowconfidence— 1 sub-claim remains below the evidence thresholddeep researchpreview plan 1/3 claimsportfolio 1/1 · evidence 0%

> ⚠ Low confidence — 1 sub-claim remains below the evidence threshold within budget. Treat this as provisional.

Arc Settlement Benchmarks reports that, across thousands of submitBatch calls on Arc testnet, x402 batched settlements finalize in roughly 180 milliseconds, with a measured median of 178ms and a p95 of 240ms . The source supports these figures by attributing the performance to Arc's BFT consensus, which it says delivers sub-second finality so that a Gateway-batched payment confirms in well under a quarter second and is not block-time-bound the way an Ethereum L1 transaction is . No further evidence or methodology is provided in the supplied passage beyond the stated measurements and the BFT-consensus explanation . The SoFi source does not address Arc settlement measurements and provides no support for these claims.

Evidence ledger — quotes verified before rewards

  1. What specific claim does Arc Settlement Benchmarks make about median Arc settlement measurements?

    100%
    “Across thousands of submitBatch calls on Arc testnet, x402 batched settlements finalize in roughly 180 milliseconds (measured median 178ms, p95 240ms).” [S2] Measuring x402 settlement latency on Arc
  2. What specific claim does Arc Settlement Benchmarks make about p95 Arc settlement measurements?

    100%
    “Across thousands of submitBatch calls on Arc testnet, x402 batched settlements finalize in roughly 180 milliseconds (measured median 178ms, p95 240ms).” [S2] Measuring x402 settlement latency on Arc
  3. What evidence or support does Arc Settlement Benchmarks provide for its claims about median and p95 Arc settlement measurements?

    0%

    No reward-qualifying evidence

Cited sources and planned rewards

Helpful?
Spent$0.02
To creators100%
Decisions1 bought · 0 cached · 20 skipped
llm:deepseek:deepseek-v4-flash + heuristic (fallback from llm:mimo:mimo-v2.5) on 1 steplive on Arc testnet
Decision log · 57 steps
§ IThe decision$0.017 settled / $0.03
57%$0.013 under cap
Decompose

Breaking down: "Which specific claim does Arc Settlement Benchmarks make about median and p95 Arc settlement measurements, and what supports that claim?"

Decompose

Identified 3 research target(s) to investigate; these are not established facts

Decompose

Deep mode: up to 4 paid/cached reads plus one bounded gap-expansion pass when needed.

Discover

Discovered 21 verified source(s)

Discover

Recalled 47 past runs on this subject — how these sources performed when they were available.

Discover

ERC-8004 reputation loaded — composite scores on this subject.

Pre-check

Claim-aware portfolio selected 1/1 positive proposal(s): 0 cached + 1 fresh, predicting 0/3 claim(s) above the evidence floor with $0.002000/$0.015000 fetch USDC reserved.

Pre-check

Free-preview pre-check covers 1/3 sub-claims (33%). The agent may buy only claim-targeted sources and will label the answer provisional if paid evidence stays thin.

DecideBUY
Cointelegraph.com News — SoFi tie-up shows stablecoins can provide alternative blockchain settlement rail$0.002 · EV 14%

Strong topical match on settlement, provide, addresses sub-claim 3; worth the 0.002 USDC toll. — selected for the claim-aware evidence portfolio (targets claim 3; $0.002000 fetch USDC, 1 attention slot).

DecideSKIP
Stablecoin Ledger — Why USDC settles instantly onchain$0.003 · EV 7%

Weak match (only settlement); not worth 0.003 USDC.

DecideSKIP
Agent Economy Weekly — Budgets make agents decide, not just automate$0.004 · EV 7%

Weak match (only make); not worth 0.004 USDC.

DecideSKIP
Onchain Micropayments Digest — Nanopayments and the $0.000001 floor$0.005 · EV 7%

Weak match (only settlement); not worth 0.005 USDC.

DecideSKIP
Distributed Systems Notes — Idempotency keys prevent double-spends$0.003 · EV 7%

Weak match (only make); not worth 0.003 USDC.

DecideSKIP
Garden & Soil Monthly — Building a no-dig raised bed$0.002 · EV 0%

Weak match (no key terms); not worth 0.002 USDC.

DecideSKIP
Retro Game Hardware — Recapping a 1990s console$0.002 · EV 0%

Weak match (no key terms); not worth 0.002 USDC.

DecideSKIP
Stripe Blog — Analyzing the evidence that helps businesses win “product not received” disputes$0.002 · EV 7%

Weak match (only evidence); not worth 0.002 USDC.

DecideSKIP
Ethereum Foundation Blog — The triage is the product: running AI agents against Ethereum's protocol code$0.002 · EV 0%

Weak match (no key terms); not worth 0.002 USDC.

DecideSKIP
Latent.Space — Ontologies Are So Back: Why AI Agents Are Reviving the Semantic Web$0.004 · EV 0%

Weak match (no key terms); not worth 0.004 USDC.

DecideSKIP
Simon Willison's Weblog — New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging$0.003 · EV 7%

Weak match (only support); not worth 0.003 USDC.

DecideSKIP
Hugging Face - Blog — BenchMIRT: What are LLM benchmarks actually measuring?$0.003 · EV 7%

Weak match (only benchmarks); not worth 0.003 USDC.

DecideSKIP
Vitalik Buterin's website — Low-risk defi can be for Ethereum what search was for Google$0.004 · EV 7%

Weak match (only settlement); not worth 0.004 USDC.

DecideSKIP
The Coinbase Blog - Medium — In response to the Wall Street Journal$0.003 · EV 0%

Weak match (no key terms); not worth 0.003 USDC.

DecideSKIP
Decrypt — FCA, HTX in Settlement Talks Over Illegal UK Crypto Promotions: Report$0.002 · EV 14%

Already cached and still relevant (matches claim, settlement); reuse for free instead of paying again. — cached bytes are free, but this read does not clear the attention gate (EV 0.14, minimum 0.45, with a required claim target).

DecideSKIP
CoinDesk: Bitcoin, Ethereum, Crypto News and Price Data — Crypto Long & Short: Inside the 300-to-1 onchain gap between the dollar and euro$0.002 · EV 7%

Weak match (only settlement); not worth 0.002 USDC.

DecideSKIP
Inner Axiom — The Codex — The Journey of the Soul$0.002 · EV 0%

Weak match (no key terms); not worth 0.002 USDC.

DecideSKIP
Conzit Labs — St. Louis Stakes Its Claim in the AI Infrastructure Race$0.002 · EV 7%

Weak match (only claim); not worth 0.002 USDC.

DecideSKIP
Arc Settlement Benchmarks — Measuring x402 settlement latency on Arc$0.003 · EV 21%

Already cached and still relevant (matches arc, settlement, benchmarks); reuse for free instead of paying again. — cached bytes are free, but this read does not clear the attention gate (EV 0.21, minimum 0.45, with a required claim target).

DecideSKIP
Web Payments Review — How long do x402 payments take to finalize?$0.002 · EV 7%

Weak match (only settlement); not worth 0.002 USDC.

DecideSKIP
Keryx Engineering (first-party) — Recovering a Keryx paid research job$0.002 · EV 7%

Weak match (only evidence); not worth 0.002 USDC.

Fetch

Agent spend wallet ready: 0x29028Fe1122E17Fe7863A22701e863FE4DaE1aFB (balance sufficient)

Fetch

Paying $0.002 toll to read Cointelegraph.com News — SoFi tie-up shows stablecoins can provide alternative blockchain settlement rail…

Fetch

Paid $0.002 to Cointelegraph.com News — SoFi tie-up shows stablecoins can provide alternative blockchain settlement rail (settled d6bf3c42-c…) — S1

Sufficiency

Sub-claim "What specific claim does Arc Settlement Benchmarks make abou…": 0% covered

Sufficiency

Sub-claim "What specific claim does Arc Settlement Benchmarks make abou…": 0% covered

Sufficiency

Sub-claim "What evidence or support does Arc Settlement Benchmarks prov…": 0% covered

Sufficiency

The only gathered source (S1) is a Cointelegraph abstract about SoFi moving its card program to stablecoin settlement. It contains no mention of "Arc Settlement Benchmarks," no median Arc settlement measurement, no p95 Arc settlement measurement, and no supporting evidence for such claims. Therefore none of the sub-claims are addressed by the supplied text. The assessment does not establish a complete supported answer for every requested part.

Re-evaluate

Sub-claim "What specific claim does Arc Settlement Benchmarks make abou…": 0% covered — The only gathered passage (S1) concerns SoFi moving its card program to stablecoin settlement with $25B annualized volume; it says nothing about Arc Settlement Benchmarks or any median Arc settlement measurement. The Arc Settlement Benchmarks source itself was skipped, so no median figure or claim is present.

Re-evaluate

Sub-claim "What specific claim does Arc Settlement Benchmarks make abou…": 0% covered — No supplied passage mentions Arc Settlement Benchmarks or any p95 Arc settlement measurement. S1 is unrelated to Arc latency benchmarks.

Re-evaluate

Sub-claim "What evidence or support does Arc Settlement Benchmarks prov…": 0% covered — No passage describes methodology, data, or support from Arc Settlement Benchmarks. The skipped Arc source preview mentions 'Benchmark methodology and results for x402 batched-settlement finality on Arc testnet,' but a preview/title is not an answer and was not read.

Re-evaluate

All three sub-claims are entirely uncovered (0.0). The directly relevant skipped source is 'Arc Settlement Benchmarks — Measuring x402 settlement latency on Arc' at $0.003, which fits the remaining budget of $0.013 and is the only skipped item whose scope matches the question. Secondary candidate 'Web Payments Review — How long do x402 payments take to finalize?' ($0.002) is broader and less likely to contain Arc-specific median/p95 claims, so it is not recommended unless the primary source proves insufficient.

Re-evaluate

Filling gap — buying Arc Settlement Benchmarks — Measuring x402 settlement latency on Arc ($0.003)…

Re-evaluate

Paid $0.003 to Arc Settlement Benchmarks — Measuring x402 settlement latency on Arc (settled 7f986296-3…) — S2

Sufficiency

Final check — "What specific claim does Arc Settlement Benchmarks make abou…": 100% assessed by S2

Sufficiency

Final check — "What specific claim does Arc Settlement Benchmarks make abou…": 100% assessed by S2

Sufficiency

Final check — "What evidence or support does Arc Settlement Benchmarks prov…": 100% assessed by S2

Sufficiency

Final coverage assessment — S2 directly states the median and p95 Arc settlement measurements and attributes them to thousands of submitBatch calls on Arc testnet, which supports the claims. S1 is unrelated to Arc settlement benchmarks and provides no coverage.

Synthesize

Synthesizing a grounded answer from 2 source(s)…

Evidence

Relevance review returned; only checked excerpts can retain support, and review cannot raise it.

Evidence

Verified — S2 supports claim 1 at 100%: “Across thousands of submitBatch calls on Arc testnet, x402 batched settlements finalize in roughly 180 milliseconds (measured median 178ms, …”

Evidence

Verified — S2 supports claim 2 at 100%: “Across thousands of submitBatch calls on Arc testnet, x402 batched settlements finalize in roughly 180 milliseconds (measured median 178ms, …”

Evidence

Below reward gate — S2 supports claim 3 at 30%: “Arc's BFT consensus delivers sub-second finality, so a Gateway-batched payment confirms in well under a quarter second — it is not block-tim…”

Evidence

Rejected 0 invalid evidence span(s) and 1 unsupported citation marker(s); rejected markers cannot receive citation rewards.

Synthesize

Drafted answer citing 1 source(s)

Verdict

Confidence: Low — 1 sub-claim remains below the evidence threshold.

Attribute

Arc Settlement Benchmarks contributed 100% → reward $0.015

Settle

Settled $0.015 citation reward → Arc Settlement Benchmarks (b9723a8c-b…)

Done

Done. Spent $0.02 across 3 confirmed/simulated payment(s) to creators.

Portable research receipt

Take the evidence trail with you

One deterministic JSON bundle binds the answer, visible decisions, exact article versions, claim evidence and a Circle-settlement snapshot under SHA-256. Retain the digest to detect later changes; the self-check is not a publisher or Keryx signature.

Exact receipt still current

1 exact cited article version still match Keryx's current index.

Inspect machine-readable audit

Ask a follow-upNew dispatch · creators paid again

Carries this dispatch’s question as context — never its answer. The next dispatch is read from sources bought for it.

From the archive

Related dispatches