How does splitting a citation reward among coauthors work in practice, and which published material supports the explanation?
10/1/2026, 8:03:37 AM · llm:deepseek:deepseek-v4-flash + llm:mimo:mimo-v2.5 on 1 step
> ⚠ Low confidence — the final assessment does not establish a complete supported answer for every requested part within budget. Treat this as provisional.
In practice, the only supplied description of splitting a citation reward among coauthors is that multi-author works can split a single reward across contributors automatically . The same source frames this as part of a fair model in which each cited source is paid in proportion to its contribution to the final answer, with heavily-relied-upon sources earning more and lightly-used ones earning less, and it says weighted nanopayments make this granular settlement practical . The published material supporting this explanation is the Onchain Micropayments Digest article "Per-citation payments weighted by contribution" . The Keryx Engineering first-party note does not address citation reward splitting among coauthors; it only describes the buyer client's quoting, buying, and recovery flow, the trusted treasury payee, the all-in price ceiling covering service fee and creator budget, and use of the caller's already-funded wallet.
Evidence ledger — supporting quotes
How does splitting a citation reward among coauthors work in practice?
40%“Weighted nanopayments make this granular settlement practical, and multi-author works can split a single reward across contributors automatically.” [S1] Per-citation payments weighted by contribution
Which published material supports the explanation of how citation reward splitting among coauthors works?
40%“Weighted nanopayments make this granular settlement practical, and multi-author works can split a single reward across contributors automatically.” [S1] Per-citation payments weighted by contribution
Cited sources and references
- 1Per-citation payments weighted by contributionOnchain Micropayments Digest100%$0.015 planned
Decision log · 54 steps
Breaking down: "How does splitting a citation reward among coauthors work in practice, and which published material supports the explanation?"
Identified 2 research target(s) to investigate; these are not established facts
Deep mode: up to 4 paid/cached/public reads plus one bounded gap-expansion pass when needed.
Discovered 21 verified creator source(s) and 4 free public reference(s)
Recalled 48 past runs on this subject — how these sources performed when they were available.
ERC-8004 reputation loaded — composite scores on this subject.
Claim-aware portfolio selected 2/2 positive proposal(s): 2 cached + 0 fresh, predicting 2/2 claim(s) above the evidence floor with $0.000000/$0.015000 fetch USDC reserved.
Free-preview pre-check maps an actionable source to every sub-claim (2/2); paid reading may proceed within the budget.
The article 'Per-citation payments weighted by contribution' is the most on-topic candidate for how a citation reward is apportioned among contributors/coauthors — its whole premise is proportional weighting by how much each source grounded the answer. It's cached, so reuse is free, and it supports both the mechanism question (0) and the published-material question (1). — selected for the claim-aware evidence portfolio (targets claims 1, 2; 0 fetch USDC, 1 attention slot).
Keryx Engineering's first-party doc is full_text (3071 bytes) and its description explicitly covers citation rewards and evidence checks, so it plausibly documents the in-practice mechanics of reward distribution among coauthors on the platform — the first-party 'published material' the question asks for. Strong historical weight (avg 0.9 when cited) and it's cached free. The preview snippet alone only covers buyer recovery, so claim 0 support is a hypothesis, but it clearly serves claim 1. — selected for the claim-aware evidence portfolio (targets claims 1, 2; 0 fetch USDC, 1 attention slot).
This covers x402 payment finalization timing, not reward splitting among coauthors; abstract is only 266 bytes on settlement latency. No preview content supports targets [0] or [1].
Agent Economy Weekly's x402 payment-rail overview is about transport and agent payments, not the accounting of splitting a citation reward across coauthors. The 327-byte abstract offers nothing on coauthor attribution.
Arc Settlement Benchmarks has strong history on this subject generally, but its preview is about x402 settlement latency/throughput on Arc testnet — measurement methodology, not how rewards are divided among coauthors. Not worth the read for these claims.
Stablecoin Ledger covers USDC issuance and settlement speed; nothing in the preview addresses citation reward splitting or coauthor attribution. Repeatedly read and never cited on this subject.
Stripe fraud-analysis piece on travel/leisure merchants; unrelated to reward splitting mechanics despite the payments tag.
Ethereum Foundation post on AI agents for protocol-security triage; no connection to how citation rewards are shared among coauthors.
Latent.Space's ontology/semantic-web article touches agents broadly but its preview says nothing about citation rewards or contributor weighting; historically low citation rate here.
ECB merchant crypto-acceptance news; irrelevant to coauthor reward splitting, and never cited on this subject.
Russia crypto-regulation news; no bearing on citation reward mechanics. Never cited on this subject.
CoinDesk stablecoin-settlement piece on Tron; settlement volume, not reward attribution among coauthors. Never cited on this subject.
Idempotency-key article on double-spends is a reliability primitive, not a description of splitting citation rewards among coauthors.
Coinbase response to the WSJ about proprietary trading; unrelated to reward splitting.
Vitalik essay on low-risk DeFi for Ethereum; no discussion of citation reward distribution, and only metadata is available (0 bytes).
Anthropic user-adoption news snippet; metadata only (0 bytes) and unrelated to coauthor reward splitting.
Hugging Face piece on source-aware verification for MCP agents is adjacent to citation practice but the title/preview suggests verification, not reward splitting among coauthors; metadata only, so no preview evidence for targets.
Gardening article; entirely off-topic.
Retro console repair article; entirely off-topic.
Esoteric mysticism piece; entirely off-topic.
Photography exhibition article; entirely off-topic.
Free AI-engineering essay on agents; the excerpt covers AI agent definitions, not citation reward splitting. No creator payout anyway, but no content relevance for targets. - free public feed reference; no purchase or creator reward.
LLM agents survey; unrelated to reward attribution mechanics among coauthors. - free public feed reference; no purchase or creator reward.
NASA engineering-excellence summary; no connection to citation reward splitting. - free public feed reference; no purchase or creator reward.
Cloudflare OS platform announcement; unrelated to how citation rewards are divided among coauthors. - free public feed reference; no purchase or creator reward.
Agent spend wallet ready: 0x29028Fe1122E17Fe7863A22701e863FE4DaE1aFB (balance sufficient)
Reused cached Onchain Micropayments Digest — Per-citation payments weighted by contribution (free) — S1
Reused cached Keryx Engineering (first-party) — Recovering a Keryx paid research job (free) — S2
Sub-claim "How does splitting a citation reward among coauthors work in…": 30% covered by S1 — S1 states that multi-author works can split a single reward across contributors automatically, which is topical context for the concept but does not explain the practical mechanism (e.g., how shares are determined, weighted, or settled among coauthors).
Sub-claim "Which published material supports the explanation of how cit…": 40% covered by S1 — S1 is the only supplied material that touches on splitting a citation reward across contributors, but it provides only a brief abstract-level assertion and no detailed explanation, so it partially supports the sourcing claim.
Coverage is low for both sub-claims, but none of the affordable skipped sources (all priced at or below the remaining budget of 0.015) address citation reward splitting among coauthors; their previews concern x402 settlement timing, payment rails, stablecoins, fraud, AI agents, crypto regulation, and unrelated topics. Buying them would not fill the identified gap, so no purchase is recommended.
Final check — "How does splitting a citation reward among coauthors work in…": 40% assessed by S1
Final check — "Which published material supports the explanation of how cit…": 40% assessed by S1
Final coverage assessment — The supplied passages only describe a general model in which multi-author works can split a single reward across contributors automatically (S1). They do not explain the practical mechanics of how a citation reward is split among coauthors, and S2 concerns buyer-side job recovery, not citation reward splitting. Thus the first sub-claim is only partially addressed at a high level, and the second sub-claim lacks a source that actually supports an explanation of the splitting mechanism. The assessment does not establish a complete supported answer for every requested part.
Synthesizing a grounded answer from 2 source(s)…
Relevance review returned; only checked excerpts can retain support, and review cannot raise it.
Verified — S1 supports claim 1 at 90%: “Weighted nanopayments make this granular settlement practical, and multi-author works can split a single reward across contributors automati…”
Below support/reward gate — S1 supports claim 1 at 30%: “A fair model pays each cited source in proportion to its contribution to the final answer.”
Verified — S1 supports claim 2 at 60%: “Weighted nanopayments make this granular settlement practical, and multi-author works can split a single reward across contributors automati…”
Rejected 0 invalid evidence span(s) and 1 unsupported citation marker(s); rejected markers cannot receive citation rewards.
Drafted answer citing 1 source(s)
Confidence: Low — the final assessment does not establish a complete supported answer for every requested part.
Onchain Micropayments Digest contributed 100% - reward $0.015
Settled $0.009 citation reward → Mara Okoye (a5e1d539-d…)
Settled $0.006 citation reward → Devin Park (8b423d69-8…)
Done. Spent $0.015 across 2 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.
Carries this dispatch’s question as context — never its answer. The next dispatch is read from sources bought for it.