Real reference, absent claim
In a fictional case, a page lacks the reported figure. Mark the claim unestablished and locate the exact table; domain identity does not validate it.
In-depth practical guides
Link important claims to source passages and check numbers, versions, omissions and uncertainty.
Updated :

AI-generated illustration
Fluent summaries may invent references, misattribute facts or add unsupported links. The NIST generative AI profile addresses confabulation risk. This method checks reading and provenance, not truth by writing style.
Identify statements about facts, numbers, causation or identity. Separate document statements from inference; prioritise claims affecting the decision.
Check title, author, identifier, date and version. Find the exact supporting passage; an existing URL alone is not evidence.
Check units, denominators, periods and change signs. Review negations, qualifications, excluded populations and association versus causation.
Mark claims supported, contradicted or unestablished in the corpus. Revise or seek another item; retain original output and correction reasons.
Reading workshop
The DEMO report and summary are invented. Classifications state what the supplied passages support, rather than universal truth.
Fictional data and records for learning: none of these results comes from a live service query.
The dossier contains March and June versions. Every row below uses the June version; June findings must not silently be attributed to March. The excerpts are fictional.
If the table exceeds the screen, scroll horizontally; arrow keys work when the region is focused.
| Summary claim | June DEMO passage | Class in this review | Review action |
|---|---|---|---|
| The pilot involves volunteers | “Test conducted only with volunteers.” | Supported in this version | Keep the volunteer population and pilot scope. |
| The results received an external audit | “No external audit was performed.” | Contradicted by the passage | Restore the negation; remove invented validation. |
| Costs fell by 25% | “Costs are not collected in this report.” | Not established in this corpus | Remove the figure or request a cost record. |
| The tool caused the improvement | “Improvement observed after the change; no control group.” | Added causal inference | Describe the observation without claiming a demonstrated cause. |
Open each proposition to compare its diagnosis. More checks may still be needed.
No. The population is limited and the passage denies an audit. This combines overgeneralization and contradiction.
Yes. This retains population, version and qualifications. Keep the undocumented cost figure out of the summary.
This review assesses individual claims. One contradiction does not automatically refute separate supported propositions.
Source: DEMO report, June version Supported: pilot limited to volunteers Contradicted: claim of an external audit Not established: 25% cost reduction Inference: causality attributed to the tool Next: retain passages, original answer and corrected text
The March version remains a separate record. “Not established” does not mean “refuted”. These passages illustrate human reading, without automatic verdicts.
In a fictional case, a page lacks the reported figure. Mark the claim unestablished and locate the exact table; domain identity does not validate it.
An illustrative summary changes “in this sample” to “in all cases”. Restore population and limits even if the sentence becomes less categorical.
Fictional example: a document gives a share rising from 20% to 30%, but the summary calls it a 10% rise. Recalculate: it is 10 percentage points, or a 50% increase relative to the starting level. Choose the expression matching the question and retain both source values so the correction can be checked.
In an illustrative dossier, a January version states a target and a June version reports a different achievement. The summary attributes the achievement to January by combining passages. Match each fact to its version and date; write two dated statements instead of a sentence supported by neither record.
Worked exercise
Fictional example: the values and documents teach the method and do not describe a real organisation.
Groups were selected differently. The summary attributes their difference to a causal effect of the tool.
If the table exceeds the screen, scroll horizontally; arrow keys work when the region is focused.
| Group | Successes | Count |
|---|---|---|
| Using the tool | 8 | 10 |
| Other group | 6 | 10 |
Observed rates are 80% and 60%, a 20-point gap. The supplied file does not establish that the tool causes it: selection and other differences are uncontrolled. Correct the claim to a descriptive comparison with that limitation.
If a causal-inference method is documented, examine its assumptions instead of automatically repeating its conclusion.
Keep counts, selection, protocol and corrected claim with its evidence level.
A claim, passage, version and decision matrix with corrected text.
No. Each link must support its associated passage. Repeated links to one source are not independent confirmations.
Retain URL, date and access state. Mark the claim unchecked in this review; seek an accessible version without treating access failure as refutation.
Keep the original answer, problematic passage, examined record and revised wording. An unsupported claim can leave the summary while remaining in the control log. Record the reason without turning absence of support into a refutation.
Priorize the statements that influence the decision, the figures and the sensitive proposals. A major error can justify a broader control of the synthesis and its production method.
TOOLS / REGISTERS
Reviewing a small corpus certifies neither all model behaviour nor facts beyond the documents. Do not send confidential records to a third-party tool without an appropriate access framework.
Proposed exercise: this protocol is not a performed service test.
Ask a dated question; record search activity, then open the cited passage.
Retain the answer and available traces; mark search as unestablished if they are missing.
Compare an open question with an instruction limited to one URL; record tools actually used.
Separate document discovery from document reading; a related citation can still lack a supporting passage.
Choose a precise claim from the summary and open its supposed supporting page; check date and scope.
Record any summary–passage discrepancy; do not treat the summary as validation of its own source.
DOCUMENTED REFERENCE
A text selector answers “which passage?”; a state answers “which representation?”. Keeping both helps an evidence record or AI-summary check avoid attributing a quotation to the wrong version.
| Reference | Value or form | What it identifies |
|---|---|---|
| selector | SpecificResource.selector | A selector describes a source segment. On its own, it does not freeze a changing page. |
| state / cached | TimeState · cached | TimeState can describe the appropriate time and a copy of the representation. cached links to that copy; it certifies neither integrity nor availability. |
| sourceDate · W3C example 31 | 2015-07-20T13:30:00Z | W3C requires sourceDate to be an xsd:dateTime in UTC using Z. Its example 31 uses 2015-07-20T13:30:00Z; this belongs to that example, not an observation on this site. |
| HttpRequestState | Accept · Accept-Language | HttpRequestState preserves request headers needed for the representation. Accept or Accept-Language is distinct from a capture date. |
Neither selector nor state proves a claim. Connect the URL, passage, preserved version, extraction and integrity check actually performed. Keep a translation distinct from the original-language passage.
No. The server may no longer supply that state, and representation can depend on requested language or format. Check the copy actually obtained and record text transformations before recomputing offsets.
Documentation consulted on .
DEEPER READING / PRACTICE
A summary seems clear but changes a reserve or gathers incompatible numbers. The verification must start with important proposals and find out the passages that support them.
Updated on .
Cut the summary into affirmations, open the sources and control scope, date, unit and level of certainty. Release the omissions that change the meaning of the original document.
A reference present at the end of the text may support only a part of the statement. The fluidity of the writing does not give any indication of the accuracy of the approaches.
The verification matrix combines affirmation, source passage, concordance and correction. Non-established items shall be reformulated or explicitly suspended.