How does why a source marker alone cannot support a claim work in practice, and which published material supports the explanation?
10/12/2026, 1:21:25 AM · 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: 3 evidence-verified sources cover every sub-claim, but corroboration or support strength is limited. 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 a source marker in the context of supporting claims?”
A source marker is a citation to a scholar or researcher who notices the same or similar idea, thereby supporting your claim. Source text: “Serve as a supporting expert: you want to offer a claim, and you cite a scholar or researcher who notices the same or similar idea, thereby supporting your claim.”
Research target 2
Requested topic (unverified): “Why can a source marker alone not support a claim?”
A source marker alone cannot support a claim because a claim mismatch happens when the cited source does not support the exact thing the sentence is claiming. Source text: “A claim mismatch happens when the source you cited does not support the exact thing your sentence is claiming.”
Research target 3
Requested topic (unverified): “How does the limitation of source markers manifest in practice?”
In practice, when the original source does not support a widely repeated claim, you should not continue citing it for that proposition; instead establish what the source actually supports and look for independent evidence that directly addresses the claim. Source text: “If the original source does not support a widely repeated claim, do not continue citing it for that proposition; establish what the source actually supports and then look for independent evidence that directly addresses the claim.”
Research target 4
Requested topic (unverified): “Which published material supports the explanation of why source markers alone cannot support claims?”
Published material from manuelgarcia.info explains that a compound claim should not inherit broader support simply because one part is substantiated. Source text: “A compound claim should not inherit broader support simply because one part is substantiated.”
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.
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 a source marker in the context of supporting claims?”
70% estimated“Serve as a supporting expert: you want to offer a claim, and you cite a scholar or researcher who notices the same or similar idea, thereby supporting your claim.” [S1] A Source's Role in Your Paper | Harvard Guide to Using Sources
Requested topic (unverified): “Why can a source marker alone not support a claim?”
70% estimated“A claim mismatch happens when the source you cited does not support the exact thing your sentence is claiming.” [S3] Your Source Is Real, but Your Claim Is Wrong: How to Fix It
Requested topic (unverified): “How does the limitation of source markers manifest in practice?”
80% estimated“If the original source does not support a widely repeated claim, do not continue citing it for that proposition; establish what the source actually supports and then look for independent evidence that directly addresses the claim.” [S2] What If the Original Source Does Not Support the Claim?
Requested topic (unverified): “Which published material supports the explanation of why source markers alone cannot support claims?”
80% estimated“A compound claim should not inherit broader support simply because one part is substantiated.” [S2] What If the Original Source Does Not Support the Claim?
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.
What is a source marker in the context of supporting claims?
1 recorded excerpt remain.
Inspect remaining excerpts
“Serve as a supporting expert: you want to offer a claim, and you cite a scholar or researcher who notices the same or similar idea, thereby supporting your claim.”
S1 · harvard.edu · A Source's Role in Your Paper | Harvard Guide to Using Sources · version d3ea71e5d10c36fc715b405607d027b478b8c835cd054fa247dc2f2da122032b
Why can a source marker alone not support a claim?
1 recorded excerpt remain.
Inspect remaining excerpts
“A claim mismatch happens when the source you cited does not support the exact thing your sentence is claiming.”
S3 · jenni.ai · Your Source Is Real, but Your Claim Is Wrong: How to Fix It · version f287b6a6f8f8f381f2db68856cb05ba42cccb9256eb927e10032dc81730e9144
How does the limitation of source markers manifest in practice?
1 recorded excerpt remain.
Inspect remaining excerpts
“If the original source does not support a widely repeated claim, do not continue citing it for that proposition; establish what the source actually supports and then look for independent evidence that directly addresses the claim.”
S2 · manuelgarcia.info · What If the Original Source Does Not Support the Claim? · version d771dee1c4543c6d26e917d1d952973da85ee6b4c95c4b1c41482a3df8603c88
Which published material supports the explanation of why source markers alone cannot support claims?
1 recorded excerpt remain.
Inspect remaining excerpts
“A compound claim should not inherit broader support simply because one part is substantiated.”
S2 · manuelgarcia.info · What If the Original Source Does Not Support the Claim? · version d771dee1c4543c6d26e917d1d952973da85ee6b4c95c4b1c41482a3df8603c88
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] A Source's Role in Your Paper | Harvard Guide to Using SourcesPublication: harvard.eduPublished: Not recorded | [S2] What If the Original Source Does Not Support the Claim?Publication: manuelgarcia.infoPublished: Not recorded | [S3] Your Source Is Real, but Your Claim Is Wrong: How to Fix ItPublication: jenni.aiPublished: Not recorded |
|---|---|---|---|---|
| What is a source marker in the context of supporting claims? | Recorded excerpt | Inspect 1 excerptServe as a supporting expert: you want to offer a claim, and you cite a scholar or researcher who notices the same or similar idea, thereby supporting your claim. | No excerpt recorded | No excerpt recorded |
| Why can a source marker alone not support a claim? | Recorded excerpt | No excerpt recorded | No excerpt recorded | Inspect 1 excerptA claim mismatch happens when the source you cited does not support the exact thing your sentence is claiming. |
| How does the limitation of source markers manifest in practice? | Recorded excerpt | No excerpt recorded | Inspect 1 excerptIf the original source does not support a widely repeated claim, do not continue citing it for that proposition; establish what the source actually supports and then look for independent evidence that directly addresses the claim. | No excerpt recorded |
| Which published material supports the explanation of why source markers alone cannot support claims? | Recorded excerpt | No excerpt recorded | Inspect 1 excerptA compound claim should not inherit broader support simply because one part is substantiated. | No excerpt recorded |
Reference export
3 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
- 1A Source's Role in Your Paper | Harvard Guide to Using Sourcesharvard.eduFree public reference · no creator payment · extracted html text20%
- 2What If the Original Source Does Not Support the Claim?manuelgarcia.infoFree public reference · no creator payment · extracted html text50%
- 3Your Source Is Real, but Your Claim Is Wrong: How to Fix Itjenni.aiFree public reference · no creator payment · extracted html text30%
Loading feedback…
Decision log · 95 steps
Breaking down: "How does why a source marker alone cannot support a claim work in practice, and which published material supports the explanation?"
Identified 4 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.
Web search: 5/5 planned queries attempted, 4 succeeded, 24 public page previews/leads, 1 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)
Recalled 23 past runs on this subject — how these sources performed when they were available.
Loaded local scores from recorded citation history on this subject.
Claim-aware portfolio (exhaustive; bounded selection, not a claim of global optimality) selected 3/17 positive proposal(s): 3 free/cache selections + 0 paid fresh selections, predicting 4/4 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 (4/4); paid reading may proceed within the budget.
Harvard guide on a source's role in a paper likely explains how sources support claims, relevant to targets 0, 1, 2, and 3. - 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, 2, 3, 4; 0 fetch USDC, 1 attention slot).
Directly addresses when an original source does not support a claim, highly relevant to targets 1, 2, and 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — selected for the claim-aware evidence portfolio (targets claims 2, 3, 4; 0 fetch USDC, 1 attention slot).
Article directly addresses claim mismatch and why a real source may not support a claim, highly relevant to targets 1, 2, and 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — selected for the claim-aware evidence portfolio (targets claims 2, 3, 4; 0 fetch USDC, 1 attention slot).
Article about arXiv rate limit policy unrelated to source markers or claim support. - free public feed reference; no purchase or creator reward.
BIS paper on gold prices and geopolitical risk, no relevance to source markers. - free public feed reference; no purchase or creator reward.
Open source AI tools survey, not about source markers or claim support. - free public feed reference; no purchase or creator reward.
Cloudflare Workers cryptographic algorithms, unrelated to source markers. - free public feed reference; no purchase or creator reward.
Open Heritage roundtable discussion, not about source markers. - free public feed reference; no purchase or creator reward.
DeepMind private AI compute memory, no relevance to source markers. - free public feed reference; no purchase or creator reward.
OA Journals Toolkit in library publishing, unrelated to source markers. - free public feed reference; no purchase or creator reward.
Docker agent permissions spec, not about source markers. - free public feed reference; no purchase or creator reward.
DuckDB view-only database, no relevance to source markers. - free public feed reference; no purchase or creator reward.
Working with AI article, not about source markers. - free public feed reference; no purchase or creator reward.
Go source-level inliner, unrelated to source markers. - free public feed reference; no purchase or creator reward.
Google Research generative UI for teachers, no relevance. - free public feed reference; no purchase or creator reward.
LLM autonomous agents, not about source markers. - free public feed reference; no purchase or creator reward.
Microsoft Research Asia Singapore update, unrelated. - free public feed reference; no purchase or creator reward.
Netlify Git storage, not about source markers. - free public feed reference; no purchase or creator reward.
Ollama decision models, no relevance to source markers. - free public feed reference; no purchase or creator reward.
OpenAI Developers plugin, unrelated to source markers. - free public feed reference; no purchase or creator reward.
OpenAlex linking research to code, not about source markers. - free public feed reference; no purchase or creator reward.
dbForge PostgreSQL tooling, no relevance. - free public feed reference; no purchase or creator reward.
PyTorch agentic inference, unrelated to source markers. - free public feed reference; no purchase or creator reward.
Rust 1.99.0 announcement, not about source markers. - free public feed reference; no purchase or creator reward.
Post-training LLMs, no relevance to source markers. - free public feed reference; no purchase or creator reward.
LLMs in A/B tests, not about source markers. - free public feed reference; no purchase or creator reward.
Stripe stablecoin OUSD, unrelated to source markers. - free public feed reference; no purchase or creator reward.
Supabase MCP server, not about source markers. - free public feed reference; no purchase or creator reward.
Tailscale Codex Cloud support, no relevance to source markers. - free public feed reference; no purchase or creator reward.
Article about NASA engineering excellence, unrelated to source markers and claim support. - free public feed reference; no purchase or creator reward.
vLLM performance announcement, unrelated to source markers and claim support. - free public feed reference; no purchase or creator reward.
Wikimedia Spain conference report, unrelated to source markers and claim support. - free public feed reference; no purchase or creator reward.
x402 Foundation launch announcement, unrelated to source markers and claim support. - free public feed reference; no purchase or creator reward.
Discusses limitations of source materials in historical research, relevant to why sources alone may not support claims (targets 1, 2). - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Dictionary entry for 'published', unrelated to source markers and claim support. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Guide on making solid evidence and supporting claims, likely discusses why a source marker alone is insufficient, relevant to targets 1, 2, 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Source limitations guide may explain why a source marker alone cannot support a claim, relevant to targets 1, 2. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Dictionary definition of 'published', unrelated to source markers and claim support. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
AI source checker workflow discusses verifying whether sources support claims, directly relevant to targets 1, 2, 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Instagram post explicitly states a reference does not automatically support a claim, relevant to targets 1, 2, 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Limitations of historical sources may explain why sources alone cannot support claims, relevant to targets 1, 2. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Dictionary definition of 'published', unrelated to source markers and claim support. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Supporting claims with evidence guide likely explains the role of sources and why a marker alone is insufficient, relevant to targets 1, 2, 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Supporting claims with reasons and evidence likely discusses why sources must provide evidence, relevant to targets 1, 2, 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Source types value and limitations may explain why a source marker alone cannot support a claim, relevant to targets 1, 2. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Dictionary definition of 'publish', unrelated to source markers and claim support. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Credible sources and evidence for claims guide likely explains why a source marker alone is insufficient, relevant to targets 1, 2, 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Using evidence to support an argument likely discusses why a reference alone does not support a claim, relevant to targets 1, 2, 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Lesson on source strengths and limitations likely discusses why sources alone cannot support claims, relevant to targets 1 and 2. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Dictionary definition of 'published' does not address source markers or claim support. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Writing center guide on source usage and claims likely explains that citations alone are insufficient, relevant to targets 1, 2, and 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Evaluating sources guide explicitly discusses checking citations and not accepting claims without verification, directly relevant to targets 1, 2, and 3. - free public original-page READ selection (not a cache hit); no purchase or creator reward. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.025000 fetch-budget caps, so this proposal stays unspent.
Derivative classification flashcards concern security markings, not source markers for claims. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Vocabulary definition of 'published' does not address source markers or claim support. - free public original-page READ selection (not a cache hit); no purchase or creator reward.
Keryx release notes about extension update are unrelated to source markers and claim support.
Keryx engineering doc on recovering a paid research job is unrelated to source markers and claim support.
READ A Source's Role in Your Paper | Harvard Guide to Using Sources - selected original public page, 0 USDC; not a cache hit.
Read extracted public text from https://usingsources.fas.harvard.edu/sources-role-your-paper-0 - S1; quote matching establishes source grounding, not fact verification.
READ What If the Original Source Does Not Support the Claim? - selected original public page, 0 USDC; not a cache hit.
Read extracted public text from https://manuelgarcia.info/guides/research/guide/original-source-does-not-support-claim - S2; quote matching establishes source grounding, not fact verification.
READ Your Source Is Real, but Your Claim Is Wrong: How to Fix It - selected original public page, 0 USDC; not a cache hit.
Read extracted public text from https://jenni.ai/blog/source-is-real-but-claim-is-wrong - S3; quote matching establishes source grounding, not fact verification.
Sub-claim "What is a source marker in the context of supporting claims?": 50% covered by S1 — S1 describes roles a source can play (evidence, context, supporting expert, etc.) but does not explicitly define 'source marker' as a term. It implies that a source is used to support a claim, but the specific concept of a 'source marker' (e.g., a citation or reference) is not directly defined.
Sub-claim "Why can a source marker alone not support a claim?": 80% covered by S2, S3 — S2 states that if the original source does not support a widely repeated claim, do not continue citing it; establish what the source actually supports. S3 explains that a citation supports a claim only if it matches three things, implying a marker alone is insufficient. However, neither explicitly says 'a source marker alone cannot support a claim' in those words, but the reasoning is directly present.
Sub-claim "How does the limitation of source markers manifest in practi…": 70% covered by S2, S3 — S2 provides practical steps: identify what later authors claim, inspect original source, narrow statement or provide additional evidence. S3 gives patterns of claim mismatch and a self-check. These illustrate practical manifestations, but no single passage explicitly ties the limitation to 'source markers' as a general concept; it is about sources not supporting claims.
Sub-claim "Which published material supports the explanation of why sou…": 90% covered by S1, S2, S3 — All three sources are published web pages (Harvard Guide, manuelgarcia.info, jenni.ai) that discuss the role of sources and the need for actual support. They collectively support the explanation, though none uses the exact phrase 'source marker'.
Coverage is adequate for all sub-claims. The first sub-claim has moderate coverage (0.5) because the term 'source marker' is not explicitly defined, but the context is clear from S1's discussion of source roles. The other sub-claims are well covered by S2 and S3. No additional sources are needed, especially given the remaining budget is very small and skipped sources are mostly irrelevant to the topic.
Final check — "What is a source marker in the context of supporting claims?": 70% assessed by S1
Final check — "Why can a source marker alone not support a claim?": 90% assessed by S2, S3
Final check — "How does the limitation of source markers manifest in practi…": 80% assessed by S2, S3
Final check — "Which published material supports the explanation of why sou…": 100% assessed by S2, S3
Final coverage assessment — S1 defines source roles but does not explain why a marker alone cannot support a claim. S2 and S3 directly address the limitation: S2 shows that a source may not substantiate a claim and requires checking original evidence; S3 explains claim mismatch and exact wording requirements. The practical manifestation is covered by S2's examples and S3's patterns. Published material supporting the explanation includes S2 and S3.
Synthesizing a grounded answer from 3 source(s)…
Relevance review returned; only checked excerpts can retain support, and review cannot raise it.
Delivering 4 summary sentence(s), each tied to one checked verbatim excerpt; complete synthesis remains unverified.
Source-matched public excerpt (no creator reward) — S1, research target 1, proposed support 80% (estimate, not entailment): “Serve as a supporting expert: you want to offer a claim, and you cite a scholar or researcher who notices the same or similar idea, thereby …”
Source-matched public excerpt (no creator reward) — S3, research target 2, proposed support 70% (estimate, not entailment): “A claim mismatch happens when the source you cited does not support the exact thing your sentence is claiming.”
Source-matched public excerpt (no creator reward) — S2, research target 3, proposed support 90% (estimate, not entailment): “If the original source does not support a widely repeated claim, do not continue citing it for that proposition; establish what the source a…”
Source-matched public excerpt (no creator reward) — S2, research target 4, proposed support 80% (estimate, not entailment): “A compound claim should not inherit broader support simply because one part is substantiated.”
Prepared a sentence-cited summary from 3 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: 3 evidence-verified sources cover every sub-claim, but corroboration or support strength is limited.
harvard.edu contributed 20% - free public reference; reward share withheld
manuelgarcia.info contributed 50% - free public reference; reward share withheld
jenni.ai contributed 30% - free public reference; reward share withheld
Keryx operating fee withheld: reviewed authority, unclaimed-source proof or funding capacity is unavailable. The answer remains available.
Done. Spent $0 across 0 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
- 2026-10-11T18:21:25.524Z
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
- 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.
Carries this dispatch’s question as context — never its answer. The next dispatch is read from sources bought for it.