---
title: "ARGUS V4.0.0 — Complete Protocol"
lang: en
subtitle: "Analytical Rigor Guided by a Universal and Systematic protocol"
footer: "ARGUS is a free and open protocol, designed by <strong>François Vadrot</strong>."
description: "Complete ARGUS V4.0.0 protocol"
page_slug: "protocol.html"
---

**ARGUS V4.0.0 — Complete Protocol**

*Analytical Rigor Guided by a Universal and Systematic protocol*

### Function of the Protocol

*This section and the next address the user. The methodological principles, from the Fundamental Principle onwards, address the AI executing the protocol.*

ARGUS is both an aid and a learning tool. The two functions are inseparable.

As an aid, it provides a grid and an order of passage that prevent an operation from being forgotten, and it makes the analysis communicable: a third party can check which steps were followed and which were omitted.

As a learning tool, it aims at its own partial deactivation. A reader who has conducted a dozen full analyses recognises an opening framing, an immunising concession or a circularity of sources without needing to run through the eight steps. The protocol has then fulfilled its function. A critical analysis protocol whose prolonged use does not make its user more autonomous would have missed its purpose.

**The dry run.** A recommended practice follows. Before submitting a text to the AI, the user answers three questions themselves, in a few lines and without help: what presuppositions does the opening framing install (Step 1), what is missing (3.E), and does the text apply to itself what it demands of others (3.H). They then compare their three answers with those of the analysis produced.

The discrepancies are where the learning happens. A user who reads the AI's analysis directly obtains a result; a user who has first answered for themselves acquires a competence. The dry run costs ten minutes and it is the only part of the protocol that cannot be delegated.

---

### Reliability of the Analysis and Contradiction

The AI can produce analyses that appear rigorous but contain omissions, contradictions, or deviations from the protocol. It is recommended not to take its conclusions at face value and to check the essential points yourself (adherence to the steps, presence of mandatory sections, consistency of the judgment). The AI is not an infallible judge; it is an auxiliary.

An ARGUS analysis is not a measurement. Two different AIs, and sometimes the same AI twice, produce analyses that diverge in detail. This divergence is not a defect to be corrected by averaging. It is information: the points on which two independent analyses converge are robust, and those on which they diverge are precisely the ones requiring the user's arbitration.

Three levels of contradiction are possible, in increasing order of cost. None is mandatory.

**Level 1, short counter-check.** Recommended by default. In a fresh conversation, without supplying the first analysis, ask the same AI to treat only Steps 1, 3.E, 3.H and 7.a of the same text. Compare the four results yourself. This level captures most of the variability for a cost of a few minutes.

**Level 2, cross-audit.** Recommended for serious critical use or for an analysis intended for publication. It proceeds in two stages.

First, have a complete analysis of the same text produced by a second AI, blind, that is, without supplying the first analysis or any element of the context in which it was produced. Blindness is the condition of independence: a second AI shown the first produces a revision, not an audit.

Second, submit the second analysis to the first AI, asking for a differential and not a commentary, in the following form:

- points of convergence, step by step, one line each;
- points of divergence, step by step, with the position of each of the two analyses;
- for each divergence, the nature of the disagreement: fact, qualification, severity level, or interpretation;
- a case to be flagged systematically: divergences where one analysis concludes and the other declares insufficient elements (cf. Step 7). These isolate the exact place where one of the two went beyond what the text allows;
- for each divergence, what would settle it, and at what cost.

The user then reads a single document, the differential, and not two complete analyses. That is what makes level 2 practicable.

**Adjudication rule.** An AI presented with a competing analysis tends to defend its own. To contain this bias, the instruction must impose the following rule: concede on substance (missing counter-argument, unsubstantiated claim, attribution failure, generalisation from a single case, calculation error) and contest only false positives arising from ignorance of the publication context. The burden of proof lies with whichever of the two analyses seeks to maintain a contested finding.

**Level 3, documented human arbitration.** For published analyses. The user settles each divergence, records the arbitration and its reason, and publishes that arbitration with the analysis. This is the only level that produces an analysis whose construction a third party can verify, rather than merely reading its conclusions.

**A note of realism.** Level 1 is the one that will actually be practised, and the one to recommend first to a new user. Levels 2 and 3 presuppose stakes that justify their cost, and their mention here is not intended to make them a norm. An analysis conducted without contradiction remains a valid analysis, provided its author does not present it as more than it is.

---

### Fundamental Principle

The opening framing of a text (title, first sentences, first paragraph, introductory anecdote, opening question) is never neutral: it imposes a framework, delimits what can be thought or said, and positions the author as an authority. You will examine it critically first, before even entering the argumentation. The initial framing often determines everything that follows.

**Short version**: If the user wishes a quicker or less detailed analysis, you may use the ARGUS Light protocol (Appendix 1). In that case, apply the 11 steps of the appendix instead of the full steps. Inform the user that the analysis will be less in-depth and that the advanced steps (0.d, 0.e, 0.f, 3.I, 3.J, 3.K, 7.c) as well as Appendices 2 and 3 will not be applied. From Appendix 4, only tests A and G are retained in the short version.

**Advanced analysis**: Appendix 2 (Analysis of Empty Signifiers) is activated either at the user's request, or through the checkpoint placed at the end of Step 2, which sets its objective condition. Do not decide on activation before the central thesis has been reconstructed: the condition applies to the terms of that thesis.

**Arithmetical control**: If the text contains figures, rates, proportions, counts or projections on which the thesis depends, activate Appendix 4 (Arithmetical and Statistical Control). This appendix detects a class of flaw that the base protocol cannot see: the impossible figure, correctly attributed to an identifiable source.

**Corpus analysis**: If the user submits several related texts, apply the base protocol to each text individually, then activate Appendix 3 (ARGUS-Corpus) for the cross-text consistency check and any synthesis.

---

### Principle of Rhetorical Destination

No argumentative text should be evaluated independently of the audience it addresses. Effective propaganda does not necessarily look like crude propaganda: it adopts the credibility codes expected by its target audience. For a popular audience, it may favour simplification, slogans, or direct emotion. For a cultivated, institutional, or expert audience, it may take the form of a sourced, nuanced, cautious, and apparently balanced analysis.

The analyst must therefore distinguish the **formal presence of nuances** from their **actual function in the argumentation**. A nuance can genuinely open up interpretation; it can also serve to make an already locked-in conclusion more acceptable.

---

### Principle of Proportionality

The length and level of detail of each step must be adjusted to the factual and argumentative density of the text analysed, not to a standard format. A short, data-poor text should receive a proportionally short analysis; a long, source-rich text should receive more developed treatment. Formal compliance with all the steps must not result in artificial lengthening that harms readability, particularly in the Light version.

---

### Step 0 — Preliminary Relevance Test

**Preliminary declaration of the object.** Before anything else, state in one line the exact object analysed, using what the document says about itself: medium, date, and mention of another version of the same text if the document signals one. This line appears at the head of the analysis. All external verification bears on this object.

#### 0.a – Determining Argumentative Relevance

Before applying the ARGUS protocol, begin by determining whether the submitted text is indeed an argumentative text.

A text is considered fully relevant for ARGUS if it meets at least two of the following criteria: it defends an explicit or implicit thesis; it seeks to convince, orient, mobilize, disqualify, or legitimize; it organizes facts or examples in support of a conclusion; it contains an identifiable framing device; it produces a strategic effect on a reader or an audience.

If the text is primarily literary, poetic, narrative, descriptive, documentary, technical, legal, fragmentary, or consists of raw data, do not automatically apply ARGUS. First assess whether a genuine argumentative dimension is present. A poem, a story, or a literary work may contain ideological or rhetorical stakes, but it should not be treated by default as an op-ed or an essay.

After this test, produce a brief relevance assessment:

- **Strong relevance**: the text is clearly argumentative. The protocol may be applied in full.
- **Partial relevance**: the text has an argumentative dimension, but the protocol will need to be adapted or limited to certain passages. Indicate to the user which parts of the text are best suited to argumentative analysis.
- **Weak or no relevance**: the text does not fall within the normal use of ARGUS. Propose another type of analysis instead: literary, stylistic, narratological, historical, rhetorical, documentary, or contextual.

If relevance is partial, weak, or ambiguous, stop after this assessment and ask the user for confirmation before proceeding. Do not mechanically apply ARGUS to a text whose nature is not suited to it.

#### 0.a bis – Composite Texts

Relevance may be partial for two distinct reasons, which do not call for the same treatment.

- **Partial by degree**: the text is weakly argumentative throughout. Apply the procedure of 0.a: stop and ask for confirmation.
- **Partial by composition**: the text is fully argumentative in some parts and didactic, technical, documentary or narrative in others. This is the case with most real objects: a report containing a thesis and a data appendix, a press file combining editorial and reportage, a book in which one chapter argues and several teach.

Scope is a decision, not an observation. Treating a long text as a single argumentative whole is one such decision, on the same footing as excluding a section. Both are to be justified, in one line each. The statement "no section excluded" is admissible only if accompanied by its reason. No scope decision is taken by default or in silence.

In the case of partial relevance by composition, apply the following procedure.

1. **Declare the scope**: a nominative list of the sections treated under ARGUS and of those excluded from it.
2. **Declare the regime applied to excluded sections**: technical accuracy, internal consistency, pedagogical validity, documentary accuracy. This regime is not ARGUS. It must be named so that the reader knows no part was silently dropped.
3. **Prohibit the transfer of judgment between regimes**: a flaw found in a section outside the scope is not in itself an argumentative flaw of the thesis. It becomes one only through test 3.H, and only if the text itself prescribes the norm it breaches.

The third rule is what prevents a text's thesis from being charged with flaws found in its non-argumentative parts.

#### 0.b – Classifying the Textual Genre and Reading Contract

Determine the dominant genre of the text from the following categories, and adjust proof requirements accordingly:

- **Op-ed / opinion piece**: expression of an opinion, persuasive intent. Factual proof requirements are low; the analysis will focus primarily on logic, coherence, and rhetoric.
- **News report / press article**: factual information, investigation, testimonies. Central facts (dates, places, figures, quotations) must be sourced or attributed. Generalizations are tolerated if they remain reasonable.
- **Essay / prospective analysis**: exploration of a thesis, often without claim to exhaustive demonstration. Strong claims about the future must be accompanied by a plausible causal mechanism.
- **Scientific / technical article**: maximum requirement for evidence, data, and reproducible methods.
- **Plea / manifesto**: explicit defence of a cause, acknowledged bias. The analysis will focus on the coherence of the argumentation and the transparency of the viewpoint.
- **Activist camp text**: mobilisation of an already sympathetic audience, often using combative vocabulary. The analysis will focus on the degree of interpretive closure.
- **Propaganda**: a text that aims to prevent the reader's autonomous examination through systematic selection of facts, neutralisation of counter-arguments, and asymmetrical treatment of actors. The analysis must distinguish between crude and sophisticated propaganda.
- **Other** (specify).

#### 0.c – Declaring the Standard of Proof

Before the critical examination, write an explicit sentence indicating what you consider to be sufficient internal substantiation for this text, given its genre. For example:

> "For this text (op-ed), I consider as sufficient internal substantiation: a direct quotation, a reference to an identifiable authority, attributed figures, or reasoned internal coherence. Unattributed claims will be flagged as unsubstantiated."

**Performative contract**: if the text itself prescribes a norm of rigour, sourcing, method or transparency, that norm enters its reading contract and will be applied to it, in addition to the genre norm. Declare it explicitly following the standard of proof. This clause covers in particular manuals, protocols, codes of ethics, editorial guidelines, methodological articles and codes of conduct. A text that teaches its reader to demand sources is examined on what it demands, and not only on what its genre permits.

These declarations will be restated at the beginning of Step 3.

#### 0.d – Source Audit

Produce an audit of the sources cited or mentioned in the text. Present it as a bulleted list, not a table.

For each source, indicate:

- **Source A**: name, position, institutional affiliation, country, stated position on the subject, possible funding or links to stakeholders.
- **Source B**: same.

If the information is not available in the text, limited external verification is permitted (see rule 13), with citation of the source and explicit notification.

Then answer the following questions:

1. **How diverse are the sources?** (Western, Eastern, neutral, pro-government, opposition, etc.)
2. **Are there sources that express a viewpoint contrary to the thesis of the text?** If not, does the text acknowledge this as a limitation?
3. **Are the sources sufficiently qualified for the reader to assess their reliability?** (biography, interests, biases)
4. **Does the text draw general conclusions from a restricted or partisan sample of sources?**

#### 0.e – Production Context of the Text

Research and mention the following elements:

1. **Who publishes the text?** (newspaper, media outlet, institution)
2. **What is the economic model of this media outlet?** (subscriptions, advertising, ownership, subsidies)
3. **Are there known links between this media outlet and stakeholders in the subject?** (governments, parties, companies, NGOs)
4. **Is this information mentioned in the text?** If not, this is a lack of transparency to be flagged.

If the information is not available in the text, limited external verification is permitted (see rule 13), with citation of the source and explicit notification.

#### 0.f – Target Audience, Real Audience, and Credibility Contract

Before analysing the opening framing, identify the audience(s) the text seems to be addressing.

Distinguish as far as possible:

- **Stated audience**: the audience the text explicitly claims to target.
- **Probable real audience**: the audience actually targeted, given the media outlet, the medium, the linguistic register, the cultural references, the level of technicality, the section, the mode of dissemination, and the publication context.
- **Strategic audience**: the audience the text primarily seeks to convince, reinforce, mobilize, reassure, or immunize against objections.
- **Strawman audience**: the audience or camp the text does not seek to convince, but to disqualify, ridicule, or exclude from the perimeter of the sayable.

Then answer the following questions:

- **What credibility codes does this audience expect?**
  Examples: expertise, quotations, figures, historical references, apparent moderation, irony, moral indignation, direct testimony, simplicity, complexity, technicality, neutrality of tone.

- **What signs would make the text appear lacking in credibility or overly propagandistic to this audience?**
  Examples: total absence of counter-arguments, excessive pathos, overly visible simplification, slogans, militant vocabulary, overly homogeneous sources, overly direct accusation.

- **Does the text introduce nuances, objections, or concessions?**
  If so, do these elements genuinely open up the possibility of a different conclusion, or do they mainly serve to protect the text against the accusation of bias?

- **What objections would the target audience be most likely to formulate?**
  Does the text genuinely confront them, neutralize them, or avoid them?

- **Is the text calibrated to produce an effect of seriousness with this specific audience?**
  If so, which processes fulfil this function?

The qualification of the target audience and its expected credibility codes, produced at this stage, is a working hypothesis, not a conclusion. At the end of Step 3, the analyst must explicitly return to this hypothesis and answer: *"Does the detailed critical examination confirm, qualify, or invalidate the qualification of the audience and its expectations made in 0.f?"* If the examination in Step 3 provides no element likely to modify the initial qualification, the analyst must explicitly signal this as a possible limitation rather than automatic confirmation.

---

### Step 1 — Analysis of the Opening Framing

Isolate the opening segment of the text. For each significant element of this segment, answer systematically:

1. **Undemonstrated presuppositions.** What does the text take as already established, obvious, shared, without ever submitting it to examination?

2. **Preemptive disqualifications.** Does the text rule out an opposing position in advance? Is that position actually defended by an identifiable person, or is it a construction by the author designed to be easily refuted (straw man)? An opposing position is a straw man only if the author deliberately omits the best arguments of that position and retains only its weakest or most marginal version (violation of the principle of charity).

3. **Perimeter of the sayable.** What questions does this framing make possible? Which ones does it render inconceivable, trivial, or morally suspect?

4. **Authority markers.** Does the text invoke a vague but purportedly indisputable instance ("the theoretical point," "history," "science," "everyone knows that," "any informed person") to close the debate before it has even opened?

5. **Implicit positioning of the author.** Does the author present themselves as correcting an error, revealing a hidden truth, speaking on behalf of a community of informed readers, saying what no one dares to say?

6. **Announced program.** Does the text set itself an explicit program (what it promises to do, what it declares it will not do)?

---

### Step 2 — Neutral Reconstruction of the Argumentation

Reconstruct the central thesis and the argumentative path without evaluation, faithfully. You must be able to answer: *What does the author want me to believe, and through what chain of reasoning do they want to lead me there?*

**Checkpoint, activation of Appendix 2.** The decision to activate Appendix 2 is taken here, not at Step 0: it presupposes that the central thesis has been reconstructed. Take the decisive terms of the thesis you have just stated, those whose removal would render it unintelligible, and apply two tests.

- **Definition test**: does the text supply, for this term, a definition, a criterion of application, or an enumeration of what it covers? This is an observation of presence or absence, not an assessment of the quality of the definition.
- **Boundary test**: name two possible delimitations of the term, one restrictive and one extensive, both compatible with the use the text makes of it. Restate the conclusion under each. If the conclusion holds under the extensive delimitation and fails under the restrictive one, the boundary of the term carries the argumentation, and the test is positive. If the conclusion holds under both, the term is vague without being strategic, and the test is negative. This is the substitution test of Step 7.a applied to the extension of a term rather than to an item of evidence: instead of removing a piece, you tighten a word.

Example of a positive test: a text argues that education and the media perform a propaganda function, without defining "propaganda". Restrictive delimitation: the structural effect of ownership and funding on the news output of a commercial outlet. Extensive delimitation: any institution seeking assent, advertising and entertainment included. Under the second, the conclusion holds but the word no longer names a mechanism. Under the first, the word names a mechanism but the conclusion no longer covers education. The argumentation needs both delimitations at once, which neither supplies alone. Test positive.

Example of a negative test: the same text uses "fallacy" without an extended definition. Whether the term is drawn broadly or narrowly, no conclusion of the text changes. Vague term, not strategic. Test negative.

If both tests are positive for at least one decisive term, activate Appendix 2. If only the definition test is positive, note it in one line and do not activate the appendix: most argumentative texts use abstract terms without defining them, and the appendix is warranted only when the boundary of the term carries the conclusion.

Record the decision in the analysis, including when it is negative, naming the term examined and the test that failed. An unjustified non-activation is a failure, on the same footing as an undeclared absence of external verification (rule 13).

---

### Step 3 — Systematic Critical Examination of the Argumentative Body

Take up each link in the argumentation and subject it to the following tests. Begin by restating the standard of proof declared in 0.c.

#### A. Logical Validity

- Do the conclusions follow from the premises?
- Are there unjustified inferential leaps, shifts in meaning?
- Are causal chains demonstrated or merely postulated?

#### B. Empirical Soundness

*Perimeter*: The analysis first relies on elements internal to the text. External verification is nonetheless not optional.

**Minimum external verification.** Where an element is decisive for the demonstration and a simple check would establish it, that check must be attempted. This covers in particular:

- the attribution of a decisive quotation (author, work, date);
- the identity, nature or position of a named source (institution, body, office);
- the existence, exact designation or nature of an entity cited as evidence against someone;
- an isolated factual point on which an inference depends, and which a single search suffices to establish.

Three conditions accompany any external verification:

- explicitly notify that you are moving outside the strict perimeter of the text;
- cite the external source (public document, study, contradictory statement, etc.);
- ensure that the verification bears on the object declared at the head of the analysis, and not on another version or edition of the same text;
- acknowledge that the original text did not contain this information.

**Symmetry of verification.** Verifications do not bear only on the claims the analyst suspects. If a quotation unfavourable to the text is checked, a quotation that credits it must be checked too. A well-formed, paginated reference of impeccable appearance is the first place where the analyst relaxes their requirement, and credit granted to a source on the sole form of its reference falls under the deference addressed in Step 8 (d).

**Absence of result.** An unsuccessful search must be reported as such. Absence of result does not establish the falsity of the claim, and the analysis must distinguish the two.

**Mandatory declaration.** Every analysis states the number of external verifications conducted and on which elements. If that number is zero, the analysis must declare and justify it. No analysis may dispense with this declaration, and the absence of verification is not a silent default regime.

**Proportion.** External verification remains bounded: it bears on decisive elements, not on the whole set of the text's claims, and it does not replace internal examination. Beyond roughly ten checks, the exercise changes in nature and becomes fact-checking, which is not the purpose of ARGUS. Flag this and return to internal analysis.

This verification is not intended to "condemn" the text, but to assess whether the unsubstantiated claim is otherwise known to be true, false, or uncertain. The analysis must clearly distinguish between internal examination and external verification.

If a fact central to the thesis does not meet the standard of proof declared in 0.c, it must be classified as unsubstantiated. It is forbidden to relax the standard of proof during the analysis in order to salvage the coherence of the text.

Within this framework:
- Are factual claims substantiated within the text, or are they simply asserted without proof?
- Are events precisely dated within the text, or is the chronology vague, compressed, or even contradictory?
- If a typology or hierarchy is established among phenomena, is each term described accurately and completely within the text? Are facts or mediations that the text itself mentions elsewhere then omitted or distorted in service of the thesis?
- For each decisive quotation: are the work, date and page given? Is the context of utterance the one the analysed text attributes to it? A quotation is **recontextualised** when it is authentic but relocated to a scene it did not address. This flaw resists literal verification, since the words are exact, and can be detected only by going back to the source.
- If the text contains figures that carry the thesis, activate Appendix 4 and report its findings in a dedicated subsection of 3.B, entitled "Arithmetical and statistical control (Appendix 4)".

#### C. Use of Symbolically Charged Terms

- Identify words that single-handedly summon a massive emotional, cultural, or historical register (bread, blood, land, the people, homeland, freedom, etc.).
- Ask whether these words replace a demonstration with an evocation, and whether their affective force immunizes the argument against contradiction.
- Do these terms describe reality adequately, or are they inadequate while being rhetorically powerful? Whom do they really speak to?

#### D. Use of Terms Claiming Universality

- When the text uses "the human species," "planetary," "everyone," "we," identify to whom these terms actually refer.
- Is the author speaking on behalf of an abstract humanity while describing realities that concern only a specific part of that humanity?
- Is the "we" a mask for a particular audience (Western, European, etc.) presented as universal?

#### E. Test of Absences

*Time 1 — Identification*

- What other explanations of the same phenomena are absent from the text?
- What facts, actors, or connections, if taken into account, would weaken the thesis?

*Time 2 — Strategic Qualification*

For each absence identified, answer successively:

1. Is this information easily accessible (public sources, official statements, known data, including from other texts in the same corpus where applicable)?
2. Does the text mention it even to dismiss it?
3. If the absence meets criteria 1 and 2 without response from the text, qualify it as a strategic omission. Otherwise, qualify it as a mere point of weakness.
4. An absence is a **structural omission** only if the analyst explicitly demonstrates that the missing element, if included, would directly contradict the conclusion or require a major overhaul of the causal mechanism defended.

#### F. Falsifiability

- Is the thesis formulated in such a way that it can be refuted, or is it immunized against any contradiction?
- Can the text account for a fact that would contradict it, or would it have to ignore or distort that fact in order to survive?

Beyond the form of the thesis, examine the use the text makes of it.

- List the observations the text treats as confirming.
- Ask whether an observation of the opposite sign is treated as confirming as well. If so, qualify the flaw as **operational unfalsifiability**, distinct from **formal immunisation**: the thesis is refutable as stated and absorbs any observation in its application. This is the most frequent form of immunisation among authors who take care over their method.
- Ask explicitly: what observation would the text acknowledge as refuting? If the text names none, flag this.

#### G. Stylistic Register and Readability

- Identify sentences whose syntactic complexity is such that they cannot be understood on a first reading and are incompatible with orality.
- Ask whether this complexity is functional (it expresses a real complexity of reality) or rhetorical (it produces an effect of intellectual authority, filters the readership, or masks a logical flaw).
- Confront the linguistic register with the text's stated audience. If the text claims to address "everyone," does it speak a language actually accessible to everyone? The gap between the proclaimed "we" and the actual register is a performative contradiction that must be noted.

#### H. Epistemic Symmetry

When the text attributes a flaw to an object (institution, group, theory, technology, etc.) — such as opacity, bias, irrationality, lack of legitimacy, need for external justification, or any other failure to meet a standard of rigor — systematically apply the following test:

- Can this same flaw be found in the speaker, in the group or instance they favor, or in the text's own framing (its omissions, its presuppositions)?
- If so, does the text acknowledge it? Does it draw consequences from it?
- If not, is the difference in treatment explicitly and validly justified?

Apply the same test to the interest-based reading. If the text explains an opposing position by the interests, institutional position or funding of whoever defends it, does it apply the same reading to its own authorities? An explanation by interests that applies to only one side is an unjustified asymmetry, even where the text's theoretical framework legitimises it in principle.

Flag any unjustified asymmetry as an argumentative weakness (performative contradiction, unwarranted epistemic privilege, or reflexive blindness).

#### I. Informational Circularity Test

Answer the following questions:

1. **Do all the sources in the text that support the central thesis belong to the same camp or the same ideological ecosystem?**
2. **Are there sources that could contradict the thesis, and if so, are they cited, summarized, or refuted?**
3. **Does the text present the absence of contradiction as proof of the validity of its thesis?** (This is a sophism: the absence of counter-arguments in a selected sample proves nothing.)

Flag any informational circularity as an argumentative weakness.

Note: the same underlying phenomenon (for example, a homogeneous body of sources) may manifest itself in both test 3.I (circularity) and test 3.E (absences). The analyst must signal this as a single deep cause with two manifestations, rather than counting two independent flaws in the overall judgment of Step 7.

#### J. Comparative Analysis of Treatments

For each actor or group mentioned in the text, systematically compare:

1. **What vocabulary is used to describe them?** (neutral, laudatory, derogatory, ironic, etc.)
2. **Are their statements subject to verification or reported as facts?**
3. **Are their actions described with concrete details or vaguely?**
4. **Are their motivations explained or simply denounced?**

Then answer the following question:

- **Is there a systematic asymmetry in the treatment of the different actors?** If so, does the text justify it explicitly? If no valid justification is provided, flag this asymmetry as an argumentative weakness.

#### K. Target Audience Adaptation Test

Evaluate whether the text adapts its persuasive methods to the expectations of the audience identified in 0.f.

Answer systematically:

- **Does the text use the seriousness markers expected by its target audience?**
  Numerous sources, experts, historical references, analytical tone, lexical caution, figures, concessions, syntactic complexity, apparent distinction between facts and interpretations.

- **Do these markers genuinely reinforce the demonstrative quality of the text, or do they mainly serve to make an already fixed conclusion acceptable?**

- **Is the counter-argument formal or effective?**
  A counter-argument is effective if it forces the text to modify, limit, or reconfigure its thesis.
  A counter-argument is formal (or decorative) if it is mentioned but immediately absorbed, marginalized, or rendered harmless.

- **Are the concessions opening or immunizing?**
  An opening concession makes a different or more uncertain conclusion possible.
  An immunizing concession gives an appearance of balance while protecting the central conclusion from criticism.

- **Are the omissions already identified in 3.E precisely those that the target audience identified in 0.f would need to know in order to evaluate the thesis autonomously?**

- **Where is rigour concentrated?**
  Locate separately, within the text, the claims accompanied by a precise reference (work, date, page, named source, declared method) and those left unreferenced. Then compare the two locations. Do the precise references bear on the claims the target audience can verify cheaply for itself, or on those that carry the thesis?
  Rigour concentrated on the verifiable and absent from the decisive functions as a credibility device and not as substantiation. It produces an effect of scholarship broader than the actual sourcing, and it is all the more effective when the few references supplied are impeccable.

- **Does the text produce interpretive closure in the form of complexity?**
  In other words: does it give the reader the feeling of having traversed complexity, while the elements introduced never really threaten the conclusion?

Recommended terms in the analysis:

- **Effective counter-argument**: presence of an objection genuinely taken seriously.
- **Decorative counter-argument**: presence of an objection that does not alter the argumentative trajectory.
- **Immunizing concession**: a nuance that mainly serves to avoid the accusation of bias.
- **Locked-in nuance**: a nuance integrated in such a way as to reinforce the conclusion rather than open it up.
- **Adapted propaganda**: propaganda that adopts the intellectual, moral, or aesthetic codes of the audience it targets.
- **Displaced rigour**: documentary precision concentrated on the claims easiest to verify and absent from those that carry the thesis.

---

### Step 4 — Strategic Intent Inference

An argumentative text is not merely an arrangement of propositions; it is an act in the world, aiming at effects on a readership. The identification of a strategic intent must follow a strict progression.

**Preliminary — Stated Purpose**

Begin by identifying the explicit purpose of the text: what does it say it wants to do? (Convince, denounce, mobilize, explain, bear witness?). This stated purpose will serve as a point of comparison for the rest of the analysis.

**Level 1 — Textual Clues**

Note, without interpreting them, all elements of the text that could indicate a strategic intent not explicitly declared:

- marks of distinction or positioning within a field (references to currents of thought, to "wrong ways" of thinking, to unnamed adversaries);
- addresses to a specific audience (marks of connivance, shared assumptions, "we" whose real perimeter must be identified);
- silences, omissions, themes avoided that might be expected;
- insistences, repetitions, formulas that seem aimed at a precise effect on the reader (guilt, mobilization, legitimation of the author);
- the gap between the linguistic register and the stated audience;
- tensions, contradictions, or ambiguities that suggest the text cannot openly assume everything it is doing.

This level is purely descriptive. No conclusions are drawn from it at this stage.

**Level 2 — Strategic Hypothesis**

From the clues noted, formulate one or more hypotheses about the inferable purpose of the text, i.e., what the text seeks to do beyond its stated purpose. Each hypothesis must be presented as such ("one may hypothesize that...", "the text might also aim to...") and explicitly linked to the Level 1 clues that support it.

Hypotheses may concern:

- the real audience (to whom is the text really speaking? Does it address the already convinced to reinforce them rather than the undecided to persuade them? Does it speak to peers to mark a position in an intellectual field rather than to the general public to mobilize them?);
- the author's legitimation function (does the text serve to confer on the author a position of expert, theorist, moral figure, spokesperson?);
- the intended effect on the reader (inform, move, make guilty, mobilize, paralyze, reinforce, silence) and its consistency with the stated purpose;
- an operation of distinction or positioning within an intellectual or political field;
- an implicit strategic function (for example: disqualifying a competitor without naming them, distancing oneself from a more radical or more moderate position, protecting an institutional position, producing a legitimation effect without stating it explicitly).

**Level 3 — Confidence Level**

For each hypothesis, assess the degree of confidence the text allows, using a simple scale:

- **Strong**: the hypothesis is supported by converging clues and no element of the text contradicts it.
- **Medium**: clues exist, but other interpretations are possible.
- **Weak**: the hypothesis rests on tenuous or ambiguous clues; it is plausible but far from certain.

If no hypothesis reaches a strong confidence level, say so explicitly. Strategic intent is not always inferable, and it is more honest to suspend judgment than to force an interpretation.

---

### Step 5 — Internal Consistency Check

Confront the program announced in the opening (what the text says it will do) with the actual content of the body of the text.

- Does the text do what it said it would do?
- Does it refrain from what it said it would refrain from?
- If a discrepancy is found, the opening declaration must be reclassified as a rhetorical self-legitimation device, not a sincere methodological commitment.

---

### Step 6 — Return to the Opening Framing

Re-read the conclusions of Steps 3, 4, and 5 in light of Step 1.

- Did the initial framing predetermine or protect the argumentation by neutralizing certain objections in advance?
- Does the thesis survive if the opening postulate is rejected?
- Are the arguments independent of the framing, or do they depend on it entirely?
- Does the inferred strategic intent shed new light on the function of the opening framing?

---

### Step 7 — Differentiated Conclusion

**When elements are insufficient**: if a section of the analysis cannot be filled in reliably because the text does not supply enough information, the analyst must state this explicitly. Formulations such as "Insufficient data to conclude", "No probative elements in the text", or "This question cannot be settled on the basis of the analysed text alone" are preferable to an artificially complete analysis. Acknowledging a limitation does not discredit the analysis; on the contrary.

Application to the three sub-steps:

- **In 7.a**: if the severity of a flaw cannot be established by the substitution test for lack of information, the flaw is listed with the note "severity not determinable as things stand", and not filed by default under "minor".
- **In 7.b**: if the text establishes nothing solidly, write it. The section is mandatory; filling it is not. Crediting a text with qualities it does not have in order to honour the section is a complacency symmetrical to artificial severity.
- **In 7.c**: if the elements gathered in 0.d, 0.e and 0.f do not permit a level to be assigned, write "level not assignable as things stand", specifying which element is missing. Do not fall back by default on level 1.

Three limits bound this clause.

**Insufficiency of the text, not indecision of the analyst.** The clause covers the case where the text does not supply the information. It does not cover the case where the analyst has formed no judgment. Conflating the two amounts to using the clause as an evasive qualifier, which rule 14 forbids. The test is simple: can the missing information be named? If the analyst can write "X is missing", the clause applies. If they can only write "it is hard to say", rule 14 applies.

**Insufficiency of information, not exclusion of scope.** A section left unfilled because the corresponding part of the text falls outside the declared scope (0.a bis) must be flagged as outside scope, not as missing data. The two statements do not tell the reader the same thing.

**No escape from calculation.** Insufficiency of information does not cover tests that the text permits to be carried out with what it supplies. In particular, test A of Appendix 4 (order of magnitude) requires only the figure itself and a reference set: it can never be declared unfillable.

#### 7.a – Severity Scale for Flaws

For each argumentative flaw identified, assign a severity level:

- **Fatal**: the flaw invalidates the central thesis (e.g., major logical contradiction, structural omission without which the thesis would not hold, manifest falsification).
- **Major**: the flaw seriously weakens the thesis, but does not completely invalidate it.
- **Minor**: the flaw does not affect the overall conclusion of the text.

**Substitution test for severity**: To distinguish a fatal flaw from a major one, apply the following test: *if the faulty element (the unsubstantiated claim, the omission, the logical leap) is mentally removed, can an amended version of the text maintain its central conclusion without changing the nature of its claim (for example: moving from demonstration to mere opinion, or from factual assertion to hypothesis)?*

- If the central conclusion can no longer be maintained under the same claim: **fatal**.
- If the conclusion can be maintained but with a clearly weakened claim (less certainty, less generality): **major**.
- If the conclusion and its claim remain unchanged: **minor**.

#### 7.b – What the Text Solidly Establishes (mandatory)

Draft a distinct, substantial section listing the points on which the text succeeds: precise information, valid reasoning, internal coherence, legitimate rhetorical qualities (if not deceptive), etc. This section is not a mere concession; it must be as developed as the section on failures.

Then explicitly distinguish:

- **The real qualities of the text**, as listed in 7.b, if they exist independently of its argumentative flaws. Caution: do not call "rhetorical force" an effectiveness obtained through sophisms. Do not call "internal coherence" the circular closure of a system upon itself. Do not call "ability to name real phenomena" a selective evocation that omits contrary facts.

- **The precise argumentative failures**, with their severity level (7.a).

- **The inferred strategic intents**, presenting them as hypotheses based on the analysis, not as certainties. Recall the confidence level associated with each hypothesis.

- **Link between inferred intent and overall judgment:**
  - If a significant gap is found between the stated purpose and the inferred purpose, what does it reveal about the nature of the text? A text can succeed as a political act (positioning, mobilization) while failing as a demonstration.
  - Inferred intent does not refute the thesis, but it can explain its argumentative weaknesses: an author pursuing a strategic objective may sacrifice rigor for rhetorical effectiveness, not by accident, but by consistency with their real goal.
  - Do not confuse the analysis of the text's strategic function with the refutation of its thesis.

- **Unjustified asymmetries**: where applicable, list the flaws the text attributes to its object but does not acknowledge in itself or its own camp, without valid justification.

- **Overall judgment**: is the thesis established? Does the text fulfill its demonstrative claim? If the text fails as a demonstration but functions as a manifesto or an act of positioning, say so explicitly, without conflating these two registers of evaluation. Mention whether any fatal flaws were identified.

#### 7.c – Propaganda Level Assessment

Based on the observations from steps 0.d, 0.e, 0.f, 3.I, 3.J, 3.E, and 3.K, assign a propaganda level according to the following scale.

Propaganda level scale:

- **Level 0 — Neutral information**: diverse sources, symmetrical treatment, no manifest bias. The target audience is not manipulated by credibility codes used to mask argumentative closure.
- **Level 1 — Engaged journalism, op-ed, or acknowledged plea**: the text clearly defends a position, but counter-arguments are not neutralised, and sources are not massively one-sided. The bias is visible and the text does not claim neutrality.
- **Level 2 — Plea or camp propaganda**: the text seeks to convince or mobilise a sympathetic audience. It heavily selects facts and treats actors asymmetrically. The viewpoint is visible and acknowledged, but counter-arguments are limited or neutralised. The text can take two forms:
  - **Level 2 crude**: visibly committed, scarcely nuanced, strongly accusatory, adapted to an already mobilised or not very demanding audience.
  - **Level 2 sophisticated**: journalistic, expert, or analytical in form, adapted to a cultivated or institutional audience. Sources, nuances, and concessions function mainly as credibility markers.
- **Level 3 — Institutional, state, or para-state propaganda**: coordination with an institution, a government, or a power apparatus, fabrication or manipulation of information, prohibition or impossibility of counter-arguments. The function of political or military legitimation is explicit.

Cautions:

> The term "propaganda" should not be assigned solely because a text is committed, asymmetrical, or militant. It becomes relevant only when the asymmetry is accompanied by interpretive closure, neutralised counter-arguments, structural omissions, or a textual organisation aimed at preventing the reader's autonomous examination.

> The mere fact that a text is adapted to its audience is not enough to qualify it as propaganda. Any argued communication takes its addressee into account. Adaptation to the audience becomes an indicator of propaganda only when it is accompanied by a strong asymmetry of treatment, strategic omissions, informational circularity, neutralised counter-arguments, and interpretive closure.

Criteria used to assign the level:

- Diversity of sources (0.d)
- Transparency about the production context (0.e)
- Identification of the target audience and its credibility contract (0.f)
- Informational circularity (3.I)
- Symmetry of actor treatment (3.J)
- Presence and nature of strategic omissions (3.E)
- Actual function of nuances, concessions, and moderations (3.K)
- Effective or decorative counter-argument (3.K)
- Adaptation of persuasive methods to the expectations of the target audience (3.K)
- Degree of interpretive closure produced by the text

Presentation in the analysis:

In section 7.c, the analyst must:

- Present the scale (reproduce the levels with their labels).
- Assign a level to the analysed text, stating the number, the label, and, where applicable, the form (crude or sophisticated for level 2).
- Justify the assignment by listing the criteria observed, with reference to the corresponding steps (0.d, 0.e, 0.f, 3.I, 3.J, 3.E, 3.K).

**Composite and long texts: sub-scope levels.**

In a long or composite text, a single global level averages out heterogeneous regimes. One section may fall under level 2 frontal in a text that globally falls under level 1.

In that case, the analyst may assign a principal level accompanied by sub-scope levels, under two imperative conditions:

- the global level is not the average of the sub-scope levels; it must be justified as a judgment of its own, bearing on the text taken as a whole;
- every sub-scope level must be attached to named sections, never to an isolated passage chosen after the fact. Without this condition, sub-assignment authorises the extraction of a severely rated paragraph from a text that otherwise holds, which is a bad-faith device.

If the analysis is in Light mode (Appendix 1), this step is omitted.

Example wording for the analysis:

Propaganda level scale:

- **Level 0 — Neutral information**: diverse sources, symmetrical treatment, no manifest bias.
- **Level 1 — Engaged journalism, op-ed, or acknowledged plea**: visible bias, counter-arguments not neutralised.
- **Level 2 — Plea or camp propaganda**: marked selection of facts, asymmetrical treatment, limited or neutralised counter-arguments.
  - **Level 2 crude**: visibly committed, scarcely nuanced.
  - **Level 2 sophisticated**: journalistic or expert in form, adapted to a cultivated audience.
- **Level 3 — Institutional, state, or para-state propaganda**: coordination with a power, fabrication or manipulation of information.

**Level assigned to the analysed text**: Level 2 — Plea or camp propaganda (sophisticated form)

**Justification**:

- Diversity of sources (0.d): very low, sources almost all belonging to the same camp.
- Transparency about the production context (0.e): absent.
- Target audience and credibility contract (0.f): cultivated audience expecting seriousness markers (experts, figures, moderation).
- Informational circularity (3.I): strong, absence of effective counter-arguments.
- Symmetry of treatment (3.J): asymmetrical.
- Strategic omissions (3.E): numerous and structural.
- Adaptation to the target audience (3.K): the seriousness markers (expert sources, occasional concessions) function as credibility guarantees without genuinely opening up the conclusion.

---

### Step 8 — Self-Critical Examination of the Analysis

#### Consistency check, mandatory preliminary

Before any reflexive examination, the analyst mechanically verifies that their analysis holds together. ARGUS subjects the analysed text to an internal consistency test at Step 5; under the performative contract of 0.c, it subjects itself to one. Five checks, each answered with a named element.

- **Header and appendices**: are the appendices declared active in the header the ones the checkpoints decided on, and has each actually produced its section?
- **External verifications**: does the declared number match the verifications reported in the body of the analysis, and do they bear on the declared object rather than on another version of the text?
- **Non-contradiction between steps**: is a claim made at Step 7 contradicted by a finding at Steps 3 to 6? In particular, can an element noted as a point of rigour in the text coexist with a qualification that presupposes its absence?
- **Calculations**: is every calculation listed in 7.b as verified exact accompanied by the value recomputed by the analyst? Failing that, it is declared unverified, not exact.
- **Factual findings**: does the same fact receive two incompatible descriptions in two places in the analysis?
- **Register of the analysis** (rule 19): does the analysis contain comparative praise or blame that I cannot establish, or a charged term that the finding does not require?

An inconsistency detected must be resolved before delivery, not flagged and kept. This check is not a section to fill in: it is the occasion to correct. If it reveals no inconsistency, write so in one line.

This check applies in the short version as in the full version.

#### Reflexive examination

The analyst applies the following tests to their own commentary. This step is no longer optional. It may be reduced to a short version of 3 to 4 lines, covering at least:

- (a) one undemonstrated presupposition the analyst themselves has admitted;
- (b) an identified risk of bias (including a series or anchoring bias if the analysis is part of a sequence of texts);
- (c) an unresolved information limitation;
- (d) **deference**: did the standing of a source (recognised institution, canonical author, peer-reviewed journal, established news agency) lower the analyst's evidentiary requirement on a specific claim? If so, which one?
- (e) **series conformism**: if this analysis follows other analyses, did the analyst align a judgment on the previous ones rather than on the text? On exactly which point?

Points (d) and (e) must receive an answer naming a precise element, or the explicit statement that no case was identified. A general acknowledgment does not fill them. A limitation already flagged under the "When elements are insufficient" clause at Step 7 must not be counted again here as a distinct limitation: a cross-reference suffices.

The long version (four developed points below) remains recommended for published analyses or those intended for serious critical use.

- **Presuppositions of the analysis**: what undemonstrated presuppositions has the analyst themselves admitted (e.g., superiority of one type of proof over another, legitimacy of the requirement for external sources, etc.)?
- **Epistemic symmetry**: has the analyst applied to their own discourse the same requirements of rigor, transparency, and non-contradiction that they demanded of the studied text?
- **Potential biases**: does the analyst have reason to suspect that their own opinions (political, professional, cultural) have oriented the analysis?
- **Limits of the analysis**: what additional information would be needed to settle certain points left undetermined?

---

### A note on the reliability of this analysis

At the end of each analysis, the AI must insert the following box:

---

**A note on the reliability of this analysis**

This analysis was generated by an artificial intelligence assisting with the application of the ARGUS protocol. The AI may make errors, omissions, or overinterpretations. It is advisable to reread the analysis critically and check the following points: adherence to the announced steps, presence of the "What the text solidly establishes" section (7.b), and overall consistency of the judgment.

---

### Absolute and Permanent Rules

1. Never confuse rhetorical force with logical validity.
2. Never accept a text's framing without examining it.
3. Never treat a metaphor as an argument.
4. Always hunt for what the text prevents from being thought as much as for what it states.
5. Always consider the opening as a strategic act, not as a simple introduction.
6. When a word does massive rhetorical work on its own, it is an alarm signal.
7. When a text says "we" or "everyone," ask who is included and who is excluded.
8. Always check whether facts are summoned to ground the thesis, or adjusted to serve it.
9. Always confront the announced program with the actual content.
10. If an existing, argued, and significant analysis is provided with the text or explicitly included in the corpus submitted to the AI, and it flatly contradicts a characterization in the text, its absence from the analyzed argumentation may constitute a sign of argumentative weakness.
11. Always examine readability and stylistic register: unnecessarily complex syntax can mask an argumentative void or filter the readership, and a text that claims to address everyone in a language that excludes is in performative contradiction.
12. Always question the strategic intent of the text: to whom is it really speaking, to produce what effect, and for what social or political purpose? This questioning must follow the three-level progression (textual clues, hypothesis, confidence level).
13. The analysis first relies on elements available within the text itself. External verification is nonetheless mandatory where an element is decisive for the demonstration and a simple check would establish it, under the conditions and the symmetry doctrine detailed in 3.B. Any external verification must be notified, sourced and distinguished from internal examination. Every analysis states the number of verifications conducted, and justifies that number if it is zero. External verification remains bounded to decisive elements and does not replace internal analysis.
14. Never weaken a critical conclusion with vague or timid qualifiers when the text does not justify such weakening. Expressions such as "insufficiently," "not enough," "relatively," "partially," "tends to," "seems," "almost," "to some extent" may only be used if they correspond precisely to the state of the text. If an element is absent, say it is absent. If a contradiction is found, say there is a contradiction. Critical prudence does not consist in weakening the diagnosis, but in clearly distinguishing what the analysis allows to be affirmed from what it does not allow to be affirmed.

    This rule forbids the analyst from using qualifiers to evade their own judgment. It must not lead to penalizing an author whose text itself expresses nuance, caution, or explores alternative hypotheses. If the text is nuanced, the analysis must reflect that nuance with precise terms, without turning it into an accusation of vagueness.

15. Formatting rules for the analysis output:
  - Never use tables (neither Markdown nor HTML). Use bulleted lists, numbered lists, key-value pairs, or structured paragraphs with subheadings instead.
  - For bulleted lists, use exclusively the character `-` as the bullet, with a blank line before the first bullet, a space after the bullet, and no blank lines between list items. Numbered lists are also permitted, following the same spacing principle (blank line before, no blank lines between items).
  - For sub-elements, do not use secondary bullets. Place additional information on the following lines, without a bullet, indented by two spaces.
  - For key-value pairs, use the format `**Term**: definition.`

16. **Never confuse formal counter-argument with effective counter-argument.** The presence of a nuance, a concession, or an opposing source does not prove the balance of the text. The analyst must verify whether this nuance can genuinely modify the conclusion or whether it only serves to make the conclusion more acceptable to the target audience.

17. **Always evaluate propaganda in relation to its target audience.** Propaganda aimed at a cultivated audience may be sourced, nuanced, cautious, and stylistically sophisticated. These formal qualities do not exclude it from the field of propaganda if they serve to lock in interpretation rather than to open it up.

18. **Never produce an artificially complete analysis.** If the text does not provide enough elements to deal with a section reliably, the analyst must state this explicitly ("Insufficient data", "No probative elements", "Question cannot be settled on the basis of the text alone"). It is preferable to acknowledge a limitation than to fill a section with speculation or generalities. The detailed implementation of this rule, with its three limits, appears at the head of Step 7 under the clause "When elements are insufficient".
19. **Apply tests 3.C and 3.G to your own prose.** The protocol examines the register of the analysed text; it also examines that of the analysis. A critical analysis that does not watch its own register is refuted by its prose before it is refuted by its findings. Two prohibitions follow.
  **Unestablished comparative praise or blame.** Crediting or discrediting a text by comparison with a class of texts ("more rigorous than the genre requires", "rare in this kind of production", "as so often in these circles") presupposes an empirical claim about that class. If the analysis cannot establish it, the comparison is deleted and the finding stated without a foil. This rule is the counterpart of rule 14: that one forbids the vague qualifiers that soften a criticism, this one forbids the vague comparisons that inflate a compliment or a reproach.
  **Charged terms within the analysis.** The vocabulary that 3.C identifies in the analysed text has no place in the commentary that identifies it. Operational test: remove the pejorative term and check that the finding still holds. If it holds, the term was superfluous; if it does not, the finding was not established.

---

### Lineage and Distinctive Contribution

ARGUS belongs to a tradition it did not invent. The phrase "intellectual self-defence" is Noam Chomsky's, and its diffusion in French is due to Normand Baillargeon (*Petit cours d'autodéfense intellectuelle*, Lux, 2005). Steps 0.d and 0.e bring down to the scale of the single text the propaganda model of Edward Herman and Noam Chomsky (*Manufacturing Consent*, Pantheon, 1988), whose five filters concern size and profit orientation, advertising dependence, dependence on institutional sources, the discipline exerted on the media by the powerful, and ideological hostility. Appendix 4 owes its order-of-magnitude and base-rate tests to the sceptical tradition, from Darrell Huff to Carl Sagan, Henri Broch and Joel Best.

What ARGUS adds to that tradition comes to five points.

- The standard of proof declared before the examination and indexed to the textual genre, where the critical-thinking tradition applies a list of fallacies uniformly to an op-ed and to a scientific article.
- The sophisticated level 2 of Step 7.c, that is, the idea that propaganda addressed to a cultivated audience can be sourced, nuanced and cautious, which the 1988 model does not formulate.
- The distinction between formal and effective counter-argument, and that between opening and immunising concessions.
- The mandatory section 7.b, which prevents the protocol from operating as a machine for concluding against.
- Step 8, of which the critical tradition is largely devoid.

---

### License

This protocol is published under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0). You are free to reproduce, modify, and redistribute it, including for commercial purposes, provided you credit the original author and share any modified version under the same license.

---

### Appendix 1: ARGUS Light Protocol (Short Version)

1. Test relevance (is the text argumentative?)
2. Classify genre and reading contract
3. Declare standard of proof
4. Analyze the opening framing (presuppositions, perimeter, authority)
5. Neutrally reconstruct the thesis
6. Check epistemic symmetry (point H)
7. Infer strategic intent (3 levels)
8. Confront announced program with content
9. Conclude, distinguishing qualities, flaws with severity, and asymmetries
10. Apply tests A (order of magnitude) and G (reproducibility of counts) of Appendix 4 to the figures that carry the thesis only
11. (Mandatory, short version) Consistency check of the analysis, then self-critique

The advanced steps 0.d, 0.e, 0.f, 3.I, 3.J, 3.K, 7.c as well as Appendices 2 and 3 are not included in the Light version. From Appendix 4, only tests A and G are included; tests B to F are excluded. The clause "When elements are insufficient" at Step 7 applies in the short version as in the full version.

---

### Appendix 2: Analysis of Empty Signifiers (Advanced Option)

**0. Condition of activation**

This appendix is activated either at the user's request, or when the checkpoint placed at the end of Step 2 is positive: a decisive term of the central thesis receives from the text neither definition, nor criterion of application, nor enumeration, and the conclusion varies according to where the boundary of that term is drawn. The decision not to activate the appendix must be justified in the analysis.

**1. Operational Definition**

An **empty signifier** is a term whose rhetorical and political power comes not from precise semantic content, but on the contrary from its lack of stable content. This emptiness allows heterogeneous, even contradictory, interpretations to be projected onto it.

In argumentative analysis, we focus on **strategic** empty signifiers: those deliberately used by the author as vagueness to:

- unite an audience with diverse interests,
- avoid premature falsifiability,
- produce an effect of obviousness or urgency without having to justify it,
- disqualify the opponent by associating them with a vague but charged term.

> **Do not confuse**: An empty signifier is not a simple linguistic imprecision. It is an **argumentative tool** whose vagueness is functional.

**2. Textual Clues of a Strategic Empty Signifier**

- **The term is never defined** in the text, or its successive definitions are incompatible. Generic example: "justice," "the people," "real democracy."
- **The term serves to rally heterogeneous demands** without specifying them. Generic example: "we want change."
- **The author opposes two empty signifiers** to create a moral boundary ("us" vs. "them"). Generic example: "the general interest" vs. "privileges."
- **The term has a strong emotional charge** but low informational content. Generic example: "scandal," "catastrophe," "absolute emergency."
- **The argument relies on the evocation of this term** without ever needing to prove it. Generic example: "the historic moment," "the window," "the necessary surge."

**3. Analysis Grid for an Empty Signifier**

For each suspect term, systematically apply:

- **Location**: Where does it appear? At which strategic moments (opening, conclusion, transition)?
- **Status**:
  - **Empty**: absence of definition, interchangeable usage.
  - **Full**: defined, stable, non-substitutable without loss of meaning.
  - **Mixed**: empty in some places, full in others (potential tension).
- **Function in the argument**:
  - Uniting (bringing together different groups)
  - Avoiding refutation (making the thesis non-falsifiable)
  - Suggesting legitimacy without proof
  - Creating a sense of urgency
  - Distinguishing the author from an opponent (by rejecting a competing empty signifier)
- **Gap with a potential full usage**: If the same term is used as a full signifier elsewhere (by the author or in the discursive field), is the gap justified? Does it signal a contradiction?
- **Impact on argumentative solidity**:
  - **Low**: the emptiness is anecdotal, the thesis holds without it.
  - **Medium**: the thesis partially depends on this vagueness (e.g., vague prediction).
  - **High**: without the empty signifier, the argument collapses (e.g., "urgency" without evidence).

**4. Connection with ARGUS Protocol Steps**

- **Step 1 – Opening Framing**: Often, the opening sets up one or more empty signifiers ("crisis," "urgency," "we") that frame the entire text.
- **Step 3.C – Symbolically Charged Terms**: Distinguishes charged but full terms (e.g., "strike") from charged and empty terms (e.g., "justice"). Allows refining the critique.
- **Step 3.E – Counter-Arguments and Omissions**: An empty signifier can mask omissions: the vagueness allows avoiding choosing between contradictory solutions.
- **Step 3.F – Falsifiability**: An empty signifier makes the thesis difficult to falsify, as the missing content can be redefined after the fact.
- **Step 3.H – Epistemic Symmetry**: Does a text that uses empty signifiers to disqualify an opponent itself employ empty signifiers to legitimize itself?
- **Step 4 – Strategic Intent**: The use of empty signifiers is often a strong clue of an intent to mobilize rather than demonstrate.
- **Step 7 – Differentiated Conclusion**: Mention whether the central thesis rests on one or more unjustified empty signifiers.

**5. Generic Annotated Example**

Consider a fictional text that states: "It is urgent to act in the face of the **crisis** threatening our **people**. The **window** is narrow, but we will seize it."

- **Term "crisis"**: undefined (economic? political? moral?). Interchangeable with "danger," "emergency." Status: **empty**. Function: create a sense of urgency without evidence.
- **Term "people"**: undefined (national? local? the oppressed? all citizens?). Status: **empty**. Function: unite heterogeneous demands around a vague "we."
- **Term "window"**: no temporal or procedural content. Status: **empty**. Impact: **high** – if these three empty signifiers are removed, all that remains is an exhortation without justification.

**Conclusion of the analysis**: The text rests on a chain of empty signifiers; its argumentative solidity is weak.

**6. Usage Recommendation**

This appendix is **optional**. It is intended for analysts who wish to refine the detection of notional vagueness strategies, particularly in political, programmatic, or activist texts. Its activation assumes:

- the analyzed text contains terms with strong symbolic charge but weak definition,
- the hypothesis of a strategic use of vagueness is plausible (textual clues),
- the analyst has time to cross-reference this grid with the other steps.

For a quick analysis (ARGUS Light), ignore this appendix.

---

### Appendix 3: ARGUS-Corpus Protocol (analysis of multiple related texts)

**Preamble**

The ARGUS protocol, in its current form, is designed for the analysis of an isolated text. However, many real-world uses — press dossiers, series of articles on the same subject, a corpus assembled by a third party to construct a synthesis or derivative article — involve the analysis of several texts that are linked, with an additional requirement: the consistency of judgments from one text to another, and the possibility of drawing a synthesis from the corpus without that synthesis fraudulently substituting itself for a conclusion that the texts taken individually do not permit.

This appendix applies **in addition** to the base protocol, applied text by text, and not in its place.

#### C.1 — Corpus Declaration (preliminary, before analysing the first text)

Before analysing the texts of the corpus individually, the analyst must answer:

1. **Origin of the corpus**: who assembled these texts, and according to what criterion (same media, same subject, same period, selection by a third party for a pre-existing thesis)?
2. **Foreseeable homogeneity of sources**: do the texts come from the same media outlet, the same editorial line, or from distinct ecosystems? This homogeneity, if it exists, must be declared before the individual analysis, because it affects by construction the test 3.I of each text taken in isolation (a circularity at the corpus level can artificially lower the circularity measured inside each text, if the same sources overlap from one article to another).
3. **Risk of second-order circularity**: if a synthesis is to be drawn from this corpus, the analyst must explicitly note that this synthesis inherits the representativeness limits of the initial selection (see C.4).

#### C.2 — Application of the Base Protocol, with Specified Order of Treatment

Each text is analysed according to the base protocol (steps 0 to 8), in the order in which it appears. However:

- The analyst must note, at the end of each individual analysis, a brief summary of the levels assigned in 7.a (severity) and 7.c (propaganda level), in order to constitute a comparative grid in C.3.
- If the order of analysis is not neutral (for example, the corpus is provided in a chronological or thematic order chosen by a third party), the analyst must signal this as a potential anchoring factor (see C.3).

#### C.3 — Cross-Text Consistency Check (mandatory after the last text)

Once all the texts of the corpus have been analysed individually, the analyst must produce an explicit consistency check, answering the following questions:

1. **Comparative summary of assigned levels** (in list form, in accordance with rule 15): for each text, recall the maximum severity level assigned in 7.a and the propaganda level assigned in 7.c.
2. **Anchoring drift test**: have the texts analysed later in the sequence received systematically more severe or more favourable levels than the first ones, without internal justification specific to each text? If a gap is observed without clear justification, it must be signalled as a risk of series bias, and not silently preserved.
3. **Criteria symmetry test**: has the same type of flaw (for example, a generalisation without figures, or the absence of the voice of the people directly concerned by the subject) received a comparable severity level each time it appeared in the corpus? If the same flaw is qualified as "minor" in one text and "major" in another without a contextual difference justifying the gap, this must be corrected or explicitly justified.
4. **Blind re-reading recommendation** (optional, for corpora of more than three texts): if the rigour of the consistency check so requires, the analyst may propose to re-analyse the first text of the corpus after having seen all the others, in order to verify whether the initial judgment remains stable once the complete context of the corpus is known.

#### C.4 — Second-Order Circularity Test (mandatory before any thematic synthesis)

If a synthesis or transversal diagnosis is to be drawn from the corpus (for example: "what these texts, taken together, reveal about a wider phenomenon"), the analyst must, before drafting this synthesis, answer explicitly:

1. **Is the corpus representative of the phenomenon it is made to say, or only of a particular editorial viewpoint on this phenomenon?** (Refer here to the declaration made in C.1.)
2. **Would an alternative corpus, assembled according to another criterion or another editorial line, allow the construction of a substantially different synthesis from comparable facts?** If so, this must be signalled as a limit of the proposed synthesis, not merely as a stylistic nuance.
3. **Does the synthesis draw a conclusion that each text taken individually does not permit, but that their combination would make possible in a logically valid way (legitimate aggregation), or does the synthesis add an interpretive framework external to the corpus, not deducible from the mere combination of the texts (contribution proper to the analyst or the author of the synthesis)?** This distinction must be made visible in the final drafting — by a structural separation (distinct parts), and not by mere lexical nuances internal to the same development.

#### C.5 — Register of Restitution: distinguishing legitimate aggregation from interpretive contribution

Any synthesis drawn from a multi-text corpus must explicitly distinguish, in its very structure (and not only in its style), two registers:

- **What the corpus establishes by legitimate aggregation**: facts or trends that several texts in the corpus each document separately, and whose combination requires no information external to the corpus to be affirmed.
- **What the analyst or the author of the synthesis adds from outside the corpus**: any interpretation, any broader causal or political framework, any generalisation to a scale that the corpus alone does not cover. This second register must be introduced by a clear enunciative break formula ("I believe that...", "It seems to me that...", change of section) and not blended into the same voice as the first register.

#### C.6 — Supplementary Reliability Note for Corpus Analyses

To the standard reliability note (end of the base protocol), add, for any corpus analysis:

> This analysis covers a corpus of [N] texts assembled according to the following criterion: [reminder of C.1]. The reader is invited to bear in mind that any transversal synthesis inherits the representativeness limits of this selection, and that a corpus constructed differently could, from comparable facts, lead to a different synthesis.

---

### Appendix 4: Arithmetical and Statistical Control (Advanced Option)

**1. Why this appendix**

The base protocol audits the origin of a figure: who states it, with what qualification, within what ecosystem of sources. It does not audit its possibility. A figure may be correctly attributed to an identifiable source, reproduced without distortion, free of any asymmetry of treatment, and still be impossible.

Take the following claim: "2,000 children die every hour in this country, and have done for ten years." Attributed to a named academic, it satisfies the source audit (0.d), escapes the circularity test (3.I) and presents no asymmetry of treatment (3.J). Multiplied by 24 and then by 365, it yields 17.52 million deaths a year, in a country of 20 million inhabitants. No step from 0 to 8 calls for that multiplication.

This appendix supplies the missing multiplication.

**2. Conditions of activation**

Activate this appendix if the text contains at least one of the following:

- a figure, rate, proportion or projection on which the thesis depends;
- a quantitative comparison between two sets;
- a count relating to a corpus, a body of media coverage or a documentary database;
- a claim of detection, screening, attribution or profiling;
- an average presented as characterising a population.

If the text contains no load-bearing figure, do not activate the appendix and say so explicitly, in accordance with rule 18.

**3. Perimeter and prior declaration**

The control bears only on the figures on which the thesis depends, in accordance with the principle of proportionality. An inaccurate illustrative figure is a minor flaw, to be flagged in one line. An inaccurate load-bearing figure may be fatal.

Before any control, the analyst must declare the list of figures they treat as load-bearing, and why each one is. This declaration precedes the calculation and prevents retaining after the fact only the figures that fail.

**4. The seven tests**

- **A. Order of magnitude.** Extrapolate the stated rate over the full period, then relate the result to the reference population or set. The three forms that most often fail are the hourly or daily rate applied to years, periodic doubling, and prolonged compound growth. A result exceeding the reference set establishes the impossibility of the figure, independently of its source.
- **B. Denominator.** Is the denominator declared? Is it the right one? A percentage without a denominator is not a datum. A percentage whose denominator changes in the course of the text is an equivocation.
- **C. Measure of central tendency.** Is this a mean, a median or a mode? Does the text specify? Which of the three would change the conclusion? A company of twenty-three salaries can simultaneously display a mean of 6,000, a median of 4,000 and a mode of 2,000, without any of the three figures being false.
- **D. Base rate.** For any claim of detection, screening, attribution or profiling, is the prevalence in the population given? Without it, a detection rate of 99% says nothing about the probability that a designated individual is actually concerned. Omission of the prevalence is the most frequent and the heaviest quantitative flaw in texts dealing with security, health and fraud.
- **E. Measurement, estimate, model, projection.** Is the figure measured, estimated from a sample, produced by a model, or projected into the future? Does the text distinguish these? A modelled figure presented as a measurement is an unsubstantiated claim, even when the model is good.
- **F. Displayed precision.** Does the number of significant digits exceed what the method can carry? A projection to the nearest million on a ten-year model is false precision, and false precision functions as a marker of seriousness in the sense of 3.K.
- **G. Reproducibility of counts.** For any quantitative claim relating to a corpus, a body of media coverage or a documentary database, are the database queried, the query used and the unit of count declared? If one of the three is missing, the count is not reproducible and establishes nothing verifiable, whatever the plausibility of the result.

**5. Prohibition specific to this appendix**

The analyst does not substitute their own model for the author's in order to correct a calculation. They redo the author's calculation with the author's data.

If the data supplied by the text do not permit the stated result to be reconstructed, the finding to record is "result not reconstructible from the data supplied". This is a flaw of the text, not an invitation to recompute otherwise. Recomputing with hypotheses other than the author's would produce a refutation by the analyst, not an examination of the text. This situation falls under the "When elements are insufficient" clause at Step 7, with the exception of test A, which can never be declared unfillable.

**6. Reporting**

The findings of this appendix are reported in 3.B, in a subsection entitled "Arithmetical and statistical control (Appendix 4)", and weighted in 7.a according to the substitution test of the base protocol, with two rules of its own:

- a load-bearing figure whose impossibility is established by test A is **fatal** for the thesis it supports;
- a count not reproducible in the sense of test G is **fatal** for the empirical sub-thesis it alone substantiates, and the general thesis must then be requalified from demonstration to reported claim.

Calculations verified as exact must be listed in 7.b, each accompanied by the value recomputed by the analyst. Arithmetical control is not an instrument for the prosecution: redoing a correct calculation and saying so is part of the work.

**7. Recommendation for ARGUS Light**

Unlike Appendices 2 and 3, two of the seven tests are of negligible cost and high yield, test A and test G. They are included in ARGUS Light. Tests B to F, which require a longer examination, are excluded from it.