What would I need to verify before relying on a claim about Keryx contribution weights for creator payouts?
· llm:deepseek:deepseek-v4-pro
> ⚠ Low confidence — Each summary sentence is tied to a verbatim excerpt and model-checked; completeness and independent factual correctness remain unverified. Evidence assessment: 6 sub-claims remain below the evidence threshold. Treat this as provisional.
Model-written summary with sentence-level citations. Each sentence is followed by the verbatim source text it was checked against; sentences without a qualifying excerpt were removed.
Research target 1
Requested topic (unverified): “What is the definition and calculation method of Keryx contribution weights?”
The reasoning model proposes contribution weights for accepted sources, but the documentation does not define the exact calculation method. Source text: “The model proposes contribution weights for accepted sources.”
Keryx resolves the proposed weights and allocates the citation pool using integer micro-USDC amounts, but the resolution formula is not specified. Source text: “Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.”
Evidence gap: the recorded assessment remains below the support threshold for this target.
Research target 2
Requested topic (unverified): “What data sources and inputs are used to compute contribution weights?”
Evidence gap: no qualifying excerpt for this research target.
Research target 3
Requested topic (unverified): “How are contribution weights updated over time, and what is their versioning or change history?”
Evidence gap: no qualifying excerpt for this research target.
Research target 4
Requested topic (unverified): “What validation or audit processes exist for contribution weights?”
Evidence gap: no qualifying excerpt for this research target.
Research target 5
Requested topic (unverified): “How are contribution weights applied to creator payouts, including any caps, thresholds, or adjustments?”
Creator payment calls use the source's authoritative payment terms, and a model-proposed weight does not choose a recipient or change the source's payout authority. Source text: “Creator payment calls then use the source's authoritative payment terms; a model-proposed weight does not choose a recipient or change the source's payout authority.”
Keryx allocates the citation pool using integer micro-USDC amounts based on the resolved weights, but no caps, thresholds, or adjustments are specified. Source text: “Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.”
Research target 6
Requested topic (unverified): “What are the known limitations, assumptions, or edge cases in the contribution weight model?”
A narrow quotation may qualify for a citation reward even when the final assessment says the wider question is only partially answered, showing a limitation in coverage assessment. Source text: “A narrow quotation may qualify for a citation reward even when the final assessment says the wider question is only partially answered.”
A reward does not establish that the job achieved adequate coverage, indicating a limitation in interpreting rewards. Source text: “A reward therefore does not establish that the job achieved adequate coverage.”
Evidence gap: the recorded assessment remains below the support threshold for this target.
Research target 7
Requested topic (unverified): “What documentation or official sources specify the contribution weight methodology and its intended use?”
The methodology is documented in first-party engineering documentation based on repository commit 9ea84fa, not independent reporting or customer evidence. Source text: “This is first-party engineering documentation based on repository commit 9ea84fa, not independent reporting or customer evidence.”
The official source is the Keryx engineering document titled 'How Keryx pays cited creators' published September 8, 2026. Source text: “# How Keryx pays cited creators Published September 8, 2026 by Keryx.”
Evidence gap: the recorded assessment remains below the support threshold for this target.
Summary sentences are model-written and model-checked, not independently verified; they claim no more than their excerpts and are not a complete synthesis. Excerpts establish source grounding, not that a source is correct. Source statements may be wrong or conflicting. Payment states remain in the separate receipt.
Next steps to complete this research
These are suggested follow-up steps; this run has not performed them. They do not change the recorded evidence or payment state.
- “Contribution Weight – LexisNexis Intellectual Property Solutions”: Original text was unavailable. Check the publisher URL and provide an accessible original of the same document; this failure does not establish that the document does not exist.
- “Contribution analysis”: Original text was unavailable. Check the publisher URL and provide an accessible original of the same document; this failure does not establish that the document does not exist.
Evidence ledger — recorded source excerpts
Research targets are unverified topics. Coverage is an estimate of excerpt support, not proof of entailment, factual truth or a complete answer.
Requested topic (unverified): “What is the definition and calculation method of Keryx contribution weights?”
0% estimated“The model proposes contribution weights for accepted sources.” [S1] How Keryx pays cited creators
“Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.” [S1] How Keryx pays cited creators
Requested topic (unverified): “What data sources and inputs are used to compute contribution weights?”
0% estimatedNo qualifying excerpt recorded
Requested topic (unverified): “How are contribution weights updated over time, and what is their versioning or change history?”
0% estimatedNo qualifying excerpt recorded
Requested topic (unverified): “What validation or audit processes exist for contribution weights?”
0% estimatedNo qualifying excerpt recorded
Requested topic (unverified): “How are contribution weights applied to creator payouts, including any caps, thresholds, or adjustments?”
50% estimated“Creator payment calls then use the source's authoritative payment terms; a model-proposed weight does not choose a recipient or change the source's payout authority.” [S1] How Keryx pays cited creators
“Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.” [S1] How Keryx pays cited creators
Requested topic (unverified): “What are the known limitations, assumptions, or edge cases in the contribution weight model?”
0% estimated“A narrow quotation may qualify for a citation reward even when the final assessment says the wider question is only partially answered.” [S1] How Keryx pays cited creators
“A reward therefore does not establish that the job achieved adequate coverage.” [S1] How Keryx pays cited creators
Requested topic (unverified): “What documentation or official sources specify the contribution weight methodology and its intended use?”
0% estimated“This is first-party engineering documentation based on repository commit 9ea84fa, not independent reporting or customer evidence.” [S1] How Keryx pays cited creators
“# How Keryx pays cited creators Published September 8, 2026 by Keryx.” [S1] How Keryx pays cited creators
What if a source were missing?
Temporarily leave out one source to see which research targets retain excerpts in this report.
Showing the original excerpt ledger. 3 targets already had no inspectable excerpts.
What is the definition and calculation method of Keryx contribution weights?
2 recorded excerpts remain.
Inspect remaining excerpts
“The model proposes contribution weights for accepted sources.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
“Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
What data sources and inputs are used to compute contribution weights?
No inspectable excerpts in the original report.
How are contribution weights updated over time, and what is their versioning or change history?
No inspectable excerpts in the original report.
What validation or audit processes exist for contribution weights?
No inspectable excerpts in the original report.
How are contribution weights applied to creator payouts, including any caps, thresholds, or adjustments?
2 recorded excerpts remain.
Inspect remaining excerpts
“Creator payment calls then use the source's authoritative payment terms; a model-proposed weight does not choose a recipient or change the source's payout authority.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
“Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
What are the known limitations, assumptions, or edge cases in the contribution weight model?
2 recorded excerpts remain.
Inspect remaining excerpts
“A narrow quotation may qualify for a citation reward even when the final assessment says the wider question is only partially answered.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
“A reward therefore does not establish that the job achieved adequate coverage.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
What documentation or official sources specify the contribution weight methodology and its intended use?
2 recorded excerpts remain.
Inspect remaining excerpts
“This is first-party engineering documentation based on repository commit 9ea84fa, not independent reporting or customer evidence.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
“# How Keryx pays cited creators Published September 8, 2026 by Keryx.”
S1 · Keryx Engineering (first-party) · How Keryx pays cited creators · version sha256:0ee74abc5d0a57df70614ed65bf58ad2a681def7f2a3ea6a49831ba68fc31d76
Targets are requested topics, not verified assertions. Excerpts do not prove truth or independent corroboration. This view keeps the answer, confidence and payments unchanged and makes no new requests.
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 (unverified) | Inspection status | [S1] How Keryx pays cited creatorsPublication: Keryx Engineering (first-party)Published: 2026-09-08T00:00:00.000Z |
|---|---|---|
| What is the definition and calculation method of Keryx contribution weights? | Recorded excerpt | Inspect 2 excerptsThe model proposes contribution weights for accepted sources. Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts. |
| What data sources and inputs are used to compute contribution weights? | No inspectable excerpt recorded | No excerpt recorded |
| How are contribution weights updated over time, and what is their versioning or change history? | No inspectable excerpt recorded | No excerpt recorded |
| What validation or audit processes exist for contribution weights? | No inspectable excerpt recorded | No excerpt recorded |
| How are contribution weights applied to creator payouts, including any caps, thresholds, or adjustments? | Recorded excerpt | Inspect 2 excerptsCreator payment calls then use the source's authoritative payment terms; a model-proposed weight does not choose a recipient or change the source's payout authority. Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts. |
| What are the known limitations, assumptions, or edge cases in the contribution weight model? | Recorded excerpt | Inspect 2 excerptsA narrow quotation may qualify for a citation reward even when the final assessment says the wider question is only partially answered. A reward therefore does not establish that the job achieved adequate coverage. |
| What documentation or official sources specify the contribution weight methodology and its intended use? | Recorded excerpt | Inspect 2 excerptsThis is first-party engineering documentation based on repository commit 9ea84fa, not independent reporting or customer evidence. # How Keryx pays cited creators Published September 8, 2026 by Keryx. |
Reference export
1 article references. Recorded titles, links and dates; observed scholarly records also include supplied authors, DOI and journal metadata with read limits. Review metadata before using in a paper. Import RIS into Zotero with File → Import.
Cited sources and references
- 1How Keryx pays cited creatorsKeryx Engineering (first-party) · 2026-09-08100%$0.025 planned
Loading feedback…
Decision log · 105 steps
Breaking down: "What would I need to verify before relying on a claim about Keryx contribution weights for creator payouts?"
Identified 7 research target(s) to investigate; these are not established facts
Deep mode: up to 7 paid/cached/public reads plus one bounded gap-expansion pass when needed.
Web search: 8/8 planned queries attempted, 4 succeeded, 24 public page previews/leads, 4 unavailable queries. Previews and supplied URLs are discovery only. Public reads spend no USDC; model and service operating costs remain separate.
Discovered 2 verified creator source(s) and 54 free public reference(s)
Claim-aware portfolio (exhaustive; bounded selection, not a claim of global optimality) selected 3/3 positive proposal(s): 3 free/cache selections + 0 paid fresh selections, predicting 7/7 claim(s) above the evidence floor with $0.000000/$0.025000 fetch USDC reserved.
Free-preview pre-check maps an actionable source to every sub-claim (7/7); paid reading may proceed within the budget.
First-party Keryx engineering documentation explicitly covers contribution weights and settlement limits; directly relevant to targets 0,1,2,3,4,5,6. — selected for the claim-aware evidence portfolio (targets claims 1, 2, 3, 4, 5, 6, 7; 0 fetch USDC, 1 attention slot).
LexisNexis IPlytics contribution weight methodology may inform definition and limitations of contribution weights, though it is a different domain. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — selected for the claim-aware evidence portfolio (targets claims 1, 6; 0 fetch USDC, 1 attention slot).
Contribution analysis evaluation approach may inform validation and methodology aspects of contribution weights, though not specific to Keryx. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — selected for the claim-aware evidence portfolio (targets claims 4, 7; 0 fetch USDC, 1 attention slot).
Article about arXiv rate limit policy; unrelated to Keryx contribution weights or creator payouts. - free public feed reference; no purchase or creator reward.
BIS paper on AI and climate change; no relevance to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Article on generation configurations; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Cloudflare Workers module registry; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Creative Commons heritage roundtable; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
DeepMind private AI compute; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
DOAJ open access interview; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Docker sandbox environments; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
DuckDB view-only mode; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
RecSys and search with LLMs; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Go 1.27 release notes; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Private federated learning; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
LLM autonomous agents; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Microsoft Quine biology AI; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Netlify AI model comparison; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Ollama decision models; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
OpenAI Developers plugin; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
OpenAlex linking research to code; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
PostgreSQL BM25 extension; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
PyTorch agentic inference; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Rust 1.99 release; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Post-training LLMs; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Spotify AI quality; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Stripe fraud at AI startups; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Supabase build anything; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Tailscale Tailcat; unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Article about agentic code generation, unrelated to Keryx contribution weights or creator payouts. - free public feed reference; no purchase or creator reward.
vLLM serving performance announcement, unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Wikimedia community meetup, unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
x402 payment protocol announcement, unrelated to Keryx contribution weights. - free public feed reference; no purchase or creator reward.
Audit of grain weighing services, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
X/Twitter creator monetization, not Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Medicaid funding methodology, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
AI audit evidence risk, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
TikTok creator fund payouts, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
General AI model article, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Plastic source reduction reporting, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Fuzzy algorithm financial analysis, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Influencer payment compliance, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Open weights limitations, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
HRSA UDS manual, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
OCC audit handbook, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Creator economy statistics, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
AI model test and evaluation framework, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Community Reinvestment Act regulations, unrelated to Keryx contribution weights. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
TikTok Creator Rewards Program is unrelated to Keryx contribution weights; no target is worth investigating. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Open-weight models are unrelated to Keryx contribution weights; no target is worth investigating. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
FDA ACE guide is unrelated to Keryx contribution weights; no target is worth investigating. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Internal audit guide is generic and unrelated to Keryx contribution weights; no target is worth investigating. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
TikTok payout restructuring is unrelated to Keryx contribution weights; no target is worth investigating. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
NTIA dual-use model weights report is unrelated to Keryx contribution weights; no target is worth investigating. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
S&P index methodology is unrelated to Keryx contribution weights; no target is worth investigating. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Official Keryx release notes may mention contribution weights in the context of creator payment validation, but the excerpt focuses on extension changes; could help with documentation target 6. — cached content is free, but this read does not clear the attention gate (EV 0.30, minimum 0.45, with a required claim target).
Agent spend wallet ready: 0x9e88d16c3ecb07b9e84df13ef38dd6b673bd285c (balance sufficient)
Reused cached Keryx Engineering (first-party) — How Keryx pays cited creators (free) — S1
READ Contribution Weight – LexisNexis Intellectual Property Solutions - selected original public page, 0 USDC; not a cache hit.
Public page unavailable (transport-unavailable); no evidence admitted. Continuing research.
READ Contribution analysis - selected original public page, 0 USDC; not a cache hit.
Public page unavailable (transport-unavailable); no evidence admitted. Continuing research.
Sub-claim "What is the definition and calculation method of Keryx contr…": 30% covered by S1 — S1 states that the model proposes contribution weights for accepted sources and Keryx resolves those weights, but does not define what a contribution weight is or explain the calculation method. Only topical context is provided.
Sub-claim "What data sources and inputs are used to compute contributio…": 0% covered — No passage mentions any data sources or inputs used to compute contribution weights.
Sub-claim "How are contribution weights updated over time, and what is …": 0% covered — No passage discusses updates, versioning, or change history of contribution weights.
Sub-claim "What validation or audit processes exist for contribution we…": 0% covered — No passage describes validation or audit processes for contribution weights.
Sub-claim "How are contribution weights applied to creator payouts, inc…": 50% covered by S1 — S1 states that Keryx resolves weights and allocates the citation pool using integer micro-USDC amounts, and that only sources accepted by the evidence ledger enter allocation. However, it does not specify caps, thresholds, or adjustments beyond integer micro-USDC allocation.
Sub-claim "What are the known limitations, assumptions, or edge cases i…": 0% covered — No passage mentions limitations, assumptions, or edge cases of the contribution weight model.
Sub-claim "What documentation or official sources specify the contribut…": 30% covered by S1 — S1 is first-party engineering documentation that mentions contribution weights, but it does not specify a detailed methodology or intended use beyond allocation to accepted sources.
Most sub-claims have low coverage. The only affordable skipped source is the Keryx owner release notes (price 0.005, within remaining budget 0.025), which may contain first-party validation details about contribution weights. Other skipped sources are unrelated to Keryx contribution weights.
Filling gap — reused cached Keryx owner release notes — first-party validation — Keryx extension 0.1.4.1 (free) — S2
Final check — "What is the definition and calculation method of Keryx contr…": 0% assessed
Final check — "What data sources and inputs are used to compute contributio…": 0% assessed
Final check — "How are contribution weights updated over time, and what is …": 0% assessed
Final check — "What validation or audit processes exist for contribution we…": 0% assessed
Final check — "How are contribution weights applied to creator payouts, inc…": 50% assessed by S1
Final check — "What are the known limitations, assumptions, or edge cases i…": 0% assessed
Final check — "What documentation or official sources specify the contribut…": 0% assessed
Final coverage assessment — The gathered sources provide only a high-level statement that the model proposes contribution weights and Keryx resolves them for allocation, but do not define the calculation method, data sources, update process, validation, payout application details, limitations, or official methodology documentation. S1 confirms weights are proposed by the model and resolved by Keryx, and that they are used to allocate the citation pool, but no specifics are given. S2 is unrelated to contribution weights. Therefore, most sub-claims have low coverage, with only the application sub-claim partially covered by S1. 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.
Delivering 8 summary sentence(s), each tied to one checked verbatim excerpt; complete synthesis remains unverified.
Source-matched reward-eligible excerpt — S1, research target 1, proposed support 40% (estimate, not entailment): “The model proposes contribution weights for accepted sources.”
Source-matched reward-eligible excerpt — S1, research target 1, proposed support 60% (estimate, not entailment): “Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.”
Below support/reward gate — S1, research target 2, proposed support 30% (estimate, not entailment): “The model proposes contribution weights for accepted sources.”
Below support/reward gate — S1, research target 3, proposed support 10% (estimate, not entailment): “The model proposes contribution weights for accepted sources.”
Below support/reward gate — S1, research target 4, proposed support 30% (estimate, not entailment): “Only sources accepted by the evidence ledger enter this allocation.”
Source-matched reward-eligible excerpt — S1, research target 5, proposed support 70% (estimate, not entailment): “Creator payment calls then use the source's authoritative payment terms; a model-proposed weight does not choose a recipient or change the s…”
Source-matched reward-eligible excerpt — S1, research target 5, proposed support 50% (estimate, not entailment): “Keryx resolves those weights and allocates the citation pool using integer micro-USDC amounts.”
Source-matched reward-eligible excerpt — S1, research target 6, proposed support 50% (estimate, not entailment): “A narrow quotation may qualify for a citation reward even when the final assessment says the wider question is only partially answered.”
Source-matched reward-eligible excerpt — S1, research target 6, proposed support 50% (estimate, not entailment): “A reward therefore does not establish that the job achieved adequate coverage.”
Source-matched reward-eligible excerpt — S1, research target 7, proposed support 70% (estimate, not entailment): “This is first-party engineering documentation based on repository commit 9ea84fa, not independent reporting or customer evidence.”
Source-matched reward-eligible excerpt — S1, research target 7, proposed support 60% (estimate, not entailment): “# How Keryx pays cited creators Published September 8, 2026 by Keryx.”
Prepared a sentence-cited summary from 1 source(s)
Confidence: Low — Each summary sentence is tied to a verbatim excerpt and model-checked; completeness and independent factual correctness remain unverified. Evidence assessment: 6 sub-claims remain below the evidence threshold.
Keryx Engineering (first-party) contributed 100% - reward $0.025
Settled $0.025 citation reward → 0x3d609eF127094624cC434aAd5A9fAcA0851dAa2D (cbefe443-d…)
Done. Spent $0.025 across 1 confirmed/simulated payment(s) to creators.
Sign in with the original report owner to review its decisions.
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.
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
- eip155:5042
- Dispatch recorded at
- 2026-10-13T08:02:41.468Z
Participant cohort: unknown. No outside-customer usage is inferred.
0 scored exact-version purchases from 0 recorded BUY decisions; 0 BUY decisions unscored. 1 of 1 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
- Recorded access cost of uncited purchases
- Unmeasured
No scored purchases; the hit rate is 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 band | Purchases | Predicted mean (0–1) | Citation rate |
|---|---|---|---|
| 0–0.2 | 0 | Unmeasured | Unmeasured |
| 0.2–0.4 | 0 | Unmeasured | Unmeasured |
| 0.4–0.6 | 0 | Unmeasured | Unmeasured |
| 0.6–0.8 | 0 | Unmeasured | Unmeasured |
| 0.8–1 | 0 | Unmeasured | Unmeasured |
Missed value, cost per supported claim, budget alternatives and counterfactual outcomes are unmeasured. No extra reading or learning was performed.
Exact receipt still current
1 exact cited article version still match Keryx's current index. The source cited here has published nothing new since this dispatch settled.
Carries this dispatch’s question as context — never its answer. The next dispatch is read from sources bought for it.