KERYX
The archive← New dispatch
Archived dispatch

How does citation-weighted settlement work?

Lowconfidence— Contains synthetic demo material; its measurements cannot support factual conclusions.

· llm:deepseek:deepseek-v4-flash + llm:mimo:mimo-v2.5 on 1 step

§ IIThe reading0 cited
Lowconfidence— Contains synthetic demo material; its measurements cannot support factual conclusions.quick researchpreview plan 0/4 claimsportfolio 0/0

Illustrative demo content: synthetic sources and measurements are not factual research evidence. Source provenance and payment status are separate; inspect the receipt for settled, pending or simulated payments. Settlement does not authenticate a source's claims.

The agent decided no source was worth paying for this question.

Source inspection unavailable: this report has no stored excerpt ledger.

Research evidence matrix

Compare unverified research targets with cited sources and inspect recorded excerpts. An empty cell means no inspectable excerpt was recorded; it does not establish whether a claim is true, false, or disputed. Coverage and agent confidence do not prove entailment, measured accuracy or complete synthesis.

Research target by cited source evidence matrix
Research target (unverified)Inspection status
Citation-weighted settlement uses patent citation counts as a proxy for the technological importance of each patent in a multi-party dispute.Evidence ledger unavailable
For each patent involved, the sum of citations it has received from other patents is calculated.Evidence ledger unavailable
Each party's share of the settlement is determined by dividing the total citation count of its patents by the aggregate citation count of all patents at issue.Evidence ledger unavailable
The total settlement fund is then distributed proportionally, so patents with higher citation influence entitle their owners to a larger payout.Evidence ledger unavailable
Spent$0
To creators—
Decisions0 bought · 0 cached · 20 skipped
llm:deepseek:deepseek-v4-flash + llm:mimo:mimo-v2.5 on 1 stepArc Testnet · historical
Decision log · 29 steps
§ IThe decision$0 settled / $0.03
0%
Decompose

Breaking down: "How does citation-weighted settlement work?"

Decompose

Identified 4 sub-claim(s) to support

Decompose

Quick mode: at most 2 paid/cached reads, with no marketplace probe or gap-expansion round.

Discover

Discovered 20 verified source(s)

Discover

Recalled 13 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 0/0 positive proposal(s): 0 cached + 0 fresh, predicting 0/4 claim(s) above the evidence floor with $0.000000/$0.015000 fetch USDC reserved.

Pre-check

Free-preview pre-check found no claim-targeted source worth its toll. No paid fetch will be attempted.

DecideSKIP
Stablecoin Ledger — Why USDC settles instantly onchain$0.003 · EV 10%

Stablecoin Ledger is cached and has low price, but its content on USDC settlement mechanics is tangentially related to the specific patent-citation-weighted settlement mechanism described in the sub-claims. It's not topically aligned, so I'll reuse it for free but low expectation. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Agent Economy Weekly — x402 turns HTTP 402 into an agent payment rail$0.004 · EV 15%

Agent Economy Weekly is cached, has zero citations on this subject historically, and its content on x402 agent payments is not directly relevant to patent citation-weighted settlement. Reusing for free but not worth paying. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Onchain Micropayments Digest — Per-citation payments weighted by contribution$0.005 · EV 80%

Onchain Micropayments Digest is cached, has high reputation (80/100) on this subject, and its preview directly mentions 'Per-citation payments weighted by contribution', which matches the core concept of citation-weighted settlement. This is highly relevant and free to reuse. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Distributed Systems Notes — Idempotency keys prevent double-spends$0.003 · EV 5%

Distributed Systems Notes is cached but has zero citations on this subject. Its idempotency keys content is only peripherally related to settlement mechanics. Not worth buying, but free to reuse. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

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

Garden & Soil Monthly on gardening is completely irrelevant to citation-weighted settlement. Skip regardless of cache status.

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

Retro Game Hardware on console recapping is completely irrelevant to citation-weighted settlement. Skip regardless of cache status.

DecideSKIP
Stripe Blog — Analyzing the evidence that helps businesses win “product not received” disputes$0.002 · EV 20%

Stripe Blog is cached and discusses dispute evidence analysis, which is tangentially related to settlement processes but not specific to citation weighting. Low relevance but free to reuse. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Ethereum Foundation Blog — The triage is the product: running AI agents against Ethereum's protocol code$0.002 · EV 10%

Ethereum Foundation Blog on AI agents and protocol code is cached and loosely related to decentralized systems, but not specific to citation-weighted settlement. Low relevance. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Cointelegraph.com News — Does the Bitcoin rally mean we haven’t wasted our lives in crypto?$0.002 · EV 5%

Cointelegraph news on Bitcoin rally is not cached, costs 0.002, and has low topical relevance to citation-weighted settlement. Not worth buying.

DecideSKIP
Latent.Space — Ontologies Are So Back: Why AI Agents Are Reviving the Semantic Web$0.004 · EV 15%

Latent Space on ontologies and AI agents is cached and could provide background on semantic structures, but is not directly relevant to citation weighting in settlements. Low relevance. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Simon Willison's Weblog — Anthropic’s best AI model struggles to attract users as cheaper tools thrive$0.003 · EV 5%

Simon Willison's Weblog on AI models is not cached, costs 0.003, and is not relevant to citation-weighted settlement. Skip.

DecideSKIP
Hugging Face - Blog — Give Your Coding Agents a Memory You Own$0.003 · EV 5%

Hugging Face Blog on coding agent memory is not cached, costs 0.003, and is not relevant to citation-weighted settlement. Skip.

DecideSKIP
Vitalik Buterin's website — The importance of full-stack openness and verifiability$0.004 · EV 15%

Vitalik Buterin's website on openness and verifiability is not cached, costs 0.004, and is high-value but broad. It may touch on settlement principles, but the price is higher than other options and I have budget constraints.

DecideSKIP
The Coinbase Blog - Medium — In response to the Wall Street Journal$0.003 · EV 10%

Coinbase Blog is cached but discusses Wall Street Journal response, not directly relevant to citation-weighted settlement. Low relevance. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Decrypt — Washington Goes All-In on Crypto: Trump Pushes Clarity, SEC Rules, and CFTC Warnings$0.002 · EV 10%

Decrypt on crypto regulation is not cached, costs 0.002, and is not directly relevant to citation-weighted settlement. Skip.

DecideSKIP
CoinDesk: Bitcoin, Ethereum, Crypto News and Price Data — SoFi, Kraken tie up as crypto and banking push into each other's turf$0.002 · EV 10%

CoinDesk on SoFi/Kraken is not cached, costs 0.002, and is about crypto banking partnerships, not citation weighting. Skip.

DecideSKIP
Inner Axiom — The Codex — As Above, so Below: The Mirrored Principle of the Tree of Life$0.002 · EV 0%

Inner Axiom on mystic topics is not cached, costs 0.002, and is completely irrelevant. Skip.

DecideSKIP
Conzit Labs — Jonquel Jones Shines as Team Spoon Triumphs in WNBA All-Star Game$0.002 · EV 0%

Conzit Labs on WNBA is not cached, costs 0.002, and is completely irrelevant. Skip.

DecideSKIP
Arc Settlement Benchmarks — Measuring x402 settlement latency on Arc$0.003 · EV 70%

Arc Settlement Benchmarks is cached, has high reputation (57/100) on this subject, and its content on x402 settlement latency is directly related to settlement mechanisms. Highly relevant and free to reuse. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

DecideSKIP
Web Payments Review — How long do x402 payments take to finalize?$0.002 · EV 40%

Web Payments Review is cached, has low reputation (2/100) on this subject, but its preview on x402 payment finalization timing is somewhat relevant to settlement. Free to reuse but low confidence in value. — the free-preview coverage check could not connect this source to any sub-claim, so no toll is authorized.

Done

Done. Spent $0 across 0 confirmed/simulated payment(s) to creators.

Read checkpoints

Read checkpoint evidence is unavailable for this report. Historical, private and unsupported native runs are not reconstructed.

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.

View JSON ↗Download
Manage question privacy

Recorded purchase outcomes

Did the exact article versions bought for this answer appear in its citations? This view scores retained BUY decisions against payment observations recorded in the same dispatch trace.

Recorded settlement bookkeeping only; Circle and chain settlement have not been independently rechecked here.

This is a partial retained trace sample, not a full payment ledger. An absent matching payment does not prove that no payment occurred; excluded and unconfirmed costs remain unknown.

Recorded network
eip155:5042002
Dispatch recorded at
2026-09-07T08:54:06.913Z
Frozen testnet archive, captured 2026-10-03T00:26:18.665Z. This is historical testnet evidence, separate from current mainnet activity.
Archive source commit
f9dca8d04f4657abbf0153175feec65728ba6a99
Archive database SHA-256
c5d9c0d2bf01099de526d7510321eabd1b0e3519f2792d40b61e49062d766272

Participant cohort: unknown. No outside-customer usage is inferred.

0 scored exact-version purchases from 0 recorded BUY decisions; 0 BUY decisions unscored. 0 of 0 trace payment observations excluded.

Each unique source + item + content version with positive matching recorded settled access counts once. Duplicate BUYs, missing identities, zero/unconfirmed access and incompatible payment observations cannot create a scored purchase. CACHE and SKIP decisions are outside this sample.

Exact-version citation hit rate
Unmeasured

No scored purchases; the hit rate is unmeasured.

Recorded access cost of uncited purchases
Unmeasured

Counts only scored purchases. Descriptive access cost, not causal regret or proof that the purchase was useless.

Predicted value and observed citations

Bins compare the recorded predicted value with citation occurrence in this one dispatch. Small samples do not validate a probability model.

Value bandPurchasesPredicted mean (0–1)Citation rate
0–0.20UnmeasuredUnmeasured
0.2–0.40UnmeasuredUnmeasured
0.4–0.60UnmeasuredUnmeasured
0.6–0.80UnmeasuredUnmeasured
0.8–10UnmeasuredUnmeasured

Missed value, cost per supported claim, budget alternatives and counterfactual outcomes are unmeasured. No extra reading or learning was performed.

View outcome JSONDownload outcomesPurchase outcomes across recent reports

A new follow-up runs on Arc mainnet with today’s sources and budget. Only the historical question supplies context.

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

Dispatch
How does Ethereum settlement versus application-level authorization work in practice, and which published material supports the explanation?
2 sources cited$0.0000 recorded creator rewards
Dispatch
How does stablecoin settlement versus card and ACH delays work in practice, and which published material supports the explanation?
1 source cited$0.0000 recorded creator rewards
Dispatch · Arc testnet history
How does final settlement before paid API access work in practice, and which published material supports the explanation?
3 sources cited0.0200 test USDC recorded creator rewards
Dispatch · Arc testnet history
How does conflicting published estimates of x402 settlement time work in practice, and which published material supports the explanation?
2 sources cited0.0200 test USDC recorded creator rewards
Browse the full archive ▸