Archived dispatch

How can a single citation reward be split fairly across multiple authors?

Lowconfidence1 sub-claim remain below the evidence threshold

7/30/2026, 12:23:13 PM · llm:deepseek:deepseek-v4-flash

The dispatch, itemised.

§ IThe decision$0.02 / $0.04
50%$0.02 under cap
Decompose

Breaking down: "How can a single citation reward be split fairly across multiple authors?"

Decompose

Identified 3 sub-claim(s) to support

Discover

Discovered 20 verified source(s)

Discover

Recalled 7 past runs on this subject — how these sources performed when they were available.

Discover

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

DecideCACHE
Onchain Micropayments Digest$0.005 · EV 90%

Highest reputation (77/100) on this subject; cited in 7/7 runs; preview discusses weighting by contribution, directly supporting proportional split and fairness.

DecideSKIP
Arc Settlement Benchmarks$0.003 · EV 15%

Focuses on settlement latency benchmarks, not on splitting citation rewards.

DecideSKIP
Web Payments Review$0.002 · EV 10%

Covers x402 settlement timing, not relevant to reward splitting.

DecideSKIP
Agent Economy Weekly$0.004 · EV 15%

Covers agent economy and x402, but not directly about fair split of citation rewards.

DecideSKIP
Stablecoin Ledger$0.003 · EV 10%

Focuses on stablecoins and settlement, not on splitting citation rewards.

DecideSKIP
Distributed Systems Notes$0.003 · EV 10%

Covers idempotency and consensus, not relevant to citation reward splitting.

DecideSKIP
Simon Willison's Weblog$0.003 · EV 10%

General tech blog, not specifically about splitting rewards.

DecideSKIP
Stripe Blog$0.002 · EV 5%

Focuses on payments disputes and trends, not on splitting rewards.

DecideSKIP
Ethereum Foundation Blog$0.002 · EV 5%

Covers Ethereum protocol and Devcon, not relevant to citation rewards.

DecideSKIP
Cointelegraph.com News$0.002 · EV 5%

General crypto news, not focused on citation reward splitting.

DecideSKIP
Latent.Space$0.004 · EV 10%

Covers AI agents and models, no direct link to citation reward split.

DecideSKIP
Decrypt$0.002 · EV 5%

News about crypto and stablecoins, not directly about splitting rewards.

DecideSKIP
CoinDesk: Bitcoin, Ethereum, Crypto News and Price Data$0.002 · EV 5%

General crypto news, no specific relevance to citation reward splitting.

DecideSKIP
Hugging Face - Blog$0.003 · EV 5%

ML and robotics focus, irrelevant to citation rewards.

DecideSKIP
The Coinbase Blog - Medium$0.003 · EV 5%

Focuses on regulatory and company news, not on citation reward distribution.

DecideSKIP
Vitalik Buterin's website$0.004 · EV 5%

Covers cryptography and formal verification, not citation splitting.

DecideSKIP
Garden & Soil Monthly$0.002 · EV 0%

Irrelevant topic: gardening.

DecideSKIP
Retro Game Hardware$0.002 · EV 0%

Irrelevant topic: retro gaming hardware.

DecideSKIP
Inner Axiom — The Codex$0.002 · EV 0%

Esoteric content, completely irrelevant.

DecideSKIP
Conzit Labs$0.002 · EV 0%

General lifestyle and technology articles, not relevant.

Fetch

Agent spend wallet ready: 0x29028Fe1122E17Fe7863A22701e863FE4DaE1aFB (balance sufficient)

Fetch

Reused cached Onchain Micropayments Digest (free) — S1

Re-evaluate

Sub-claim "The fairness of a split depends on the contributions of each…": 80% covered by S1 — S1 states 'A fair model pays each cited source in proportion to its contribution,' directly linking fairness to contributions.

Re-evaluate

Sub-claim "A citation reward can be split proportionally to each author…": 90% covered by S1 — S1 explicitly describes per-citation payments weighted by contribution and mentions automatic splitting for multi-author works.

Re-evaluate

Sub-claim "Alternative methods include equal split or weighting by auth…": 0% covered — S1 only covers proportional splitting; no gathered source discusses equal split or author order weighting.

Re-evaluate

Only the third sub-claim is poorly covered (0.0), but no skipped source appears relevant to alternative splitting methods. All other claims are well covered by the single gathered source. No purchase is necessary as additional sources would not address the gap affordably.

Sufficiency

Final check — "The fairness of a split depends on the contributions of each…": 90% assessed by S1

Sufficiency

Final check — "A citation reward can be split proportionally to each author…": 100% assessed by S1

Sufficiency

Final check — "Alternative methods include equal split or weighting by auth…": 0% assessed

Sufficiency

Final coverage assessment — The gathered text only covers proportional splitting based on contribution, but does not address alternative methods like equal split or author order weighting. More sources are needed for sub-claim 3.

Synthesize

Synthesizing a grounded answer from 1 source(s)…

Evidence

Verified — S1 supports claim 1 at 100%: “A fair model pays each cited source in proportion to its contribution to the final answer.”

Evidence

Verified — S1 supports claim 2 at 100%: “A fair model pays each cited source in proportion to its contribution to the final answer.”

Synthesize

Drafted answer citing 1 source(s)

Verdict

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

Attribute

Onchain Micropayments Digest contributed 100% → reward $0.02

Settle

Settled $0.012 citation reward → Mara Okoye (312b6324-1…)

Settle

Settled $0.008 citation reward → Devin Park (17beb88e-e…)

Done

Done. Spent $0.02 across 2 payment(s) to creators.

§ IIIThe settlementweighted · USDC on Arc
100%
100%
1

Onchain Micropayments Digest

batched

100%+$0.012
2

Onchain Micropayments Digest

batched

100%+$0.008
§ IIThe reading1 cited
Lowconfidence1 sub-claim remain below the evidence threshold

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

A single citation reward can be split fairly across multiple authors by paying each author in proportion to their contribution to the final answer. This is made practical through weighted nanopayments, which allow granular settlement of very small amounts .

Evidence ledger — quotes verified before rewards

  1. The fairness of a split depends on the contributions of each author.

    90%
    A fair model pays each cited source in proportion to its contribution to the final answer. [S1] Onchain Micropayments Digest
  2. A citation reward can be split proportionally to each author's contribution.

    100%
    A fair model pays each cited source in proportion to its contribution to the final answer. [S1] Onchain Micropayments Digest
  3. Alternative methods include equal split or weighting by author order.

    0%

    No reward-qualifying evidence

Footnotes — each one pays its author

  • 1Onchain Micropayments Digest100%+$0.02
Helpful?
Spent$0.02
To creators100%
Decisions0 bought · 1 cached · 19 skipped
llm:deepseek:deepseek-v4-flash
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