Revise paper draft: fix narrative provenance, hedge unverified claims

Author fact-checks on paper/paper.md:
- Site area simplified to ~13,000 m2 throughout (drop pseudo-precise
  13,004.65 m2, even though it's genuinely in the official brief).
- Corrected a significant factual error: the two tracks are not fully
  independent - Track A's visitor narrative and half of Track B's merge
  input both descend from Salingaros' shared root narrative. Section 4
  rewritten around "divergent elaborations of a shared root", with the
  convergence claim re-evidenced from the material that actually is
  independent (3 of 4 Track A narratives, Track B's second merge input,
  both image-generation stages).
- Attributed Salingaros' image critique-loop account as self-reported,
  not independently verified, with image-numbering gaps noted only as
  circumstantial support.
- Added the authors' working hypothesis for the image-register gap:
  partly a deliberate medium request (watercolour vs unconstrained),
  partly that Track B's prompts carried the full pattern+form-language
  text inline per image vs Track A's short distilled per-scene prompts -
  clearly hedged as unverified.
- Fixed an overclaim that symposium participants judged both image sets;
  they only saw Track B's.
- De-emphasized the plan-layout idea throughout (title, abstract, intro,
  section 7, conclusion) to read as one possible future direction in
  prose, not work in progress.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

paper/paper.md

@@ -1,4 +1,4 @@
-# From Pattern to Plan: A Form-Language Extension and a Live Public-Advocacy Deployment of LLM-Mediated Pattern Language Synthesis
+# Two Languages, Two Tracks: A Live Public-Advocacy Deployment of LLM-Mediated Pattern Language Synthesis
 
 Bruno Postle¹ and Nikos A. Salingaros²,³
 
@@ -27,20 +27,22 @@ theoretical framework of pattern language and form language as
 complementary, jointly necessary instruments. We generalize the bespoke
 prompting used to produce this project's form-language grammar into a
 reusable, placeholder-driven template, and validate that it generalizes to
-an unrelated typology, region, and climate. From one shared pattern
-subset and form-language grammar, two authors independently ran the
-method to completion, producing two narratives and two illustrated image
-sets (13 watercolor-register images; 25 photo-realistic images) that
-converge on compatible design moves while diverging sharply in visual
-register, for reasons we have not yet isolated. We report informal peer
-reception of this work at a public symposium, including a substantive
-critique from a practicing architect that the method, as run, produced
-"flavors, not solutions" because no single coordinated floor plan
-underlies the independently generated images. We discuss this and other
-limitations, and propose — without yet prototyping — an explicit
-plan-layout generation stage as the method's next needed instrument,
-mining spatial-adjacency information already implicit in the pattern
-subset.
+an unrelated typology, region, and climate. From a shared narrative root
+and a shared pattern subset and form-language grammar, the two authors
+produced two divergent elaborations — two narratives and two illustrated
+image sets (13 watercolor-register images; 25 photo-realistic images)
+— that converge on compatible design moves while diverging sharply in
+visual register, a divergence we attribute partly to a deliberate
+difference in requested image medium and partly to a difference in how
+much of the source material each image-generation prompt carried. We
+report informal peer reception of this work at a public symposium,
+including a substantive critique from a practicing architect that the
+method, as run, produced "flavors, not solutions" because no single
+coordinated floor plan underlies the independently generated images. We
+discuss this and other limitations, and note — as one possible direction
+for future work, not yet attempted — that an explicit plan-layout
+generation stage could address it by mining spatial-adjacency information
+already implicit in the pattern subset.
 
 **Keywords**: pattern language; form language; large language models;
 human-centered architecture; generative AI in design; participatory
@@ -71,8 +73,8 @@ that the deployment required.
 
 The deployment: the Government of Ecuador ran an open international call
 (Stage 1 deadline 17 February 2026) for the architectural preliminary
-project of the new National Museum of Ecuador, on a 13,004.65 m² site in
-Iñaquito, Quito. A winner was selected, but the winning design provoked
+project of the new National Museum of Ecuador, on an approximately
+13,000 m² site in Iñaquito, Quito. A winner was selected, but the winning design provoked
 sustained public objection over its failure to serve the people who will
 actually use it, and — at the time of writing — is on hold and may be
 abandoned. Independently of that competition, a small informal team,
@@ -105,16 +107,17 @@ language. Section 3 reports how this form-language instrument was
 produced, and how we generalized its production into a reusable template.
 
 The rest of the paper is a case study of what happens when this
-three-input method is run twice, independently, from the same shared
-inputs, in public, and then subjected to informal peer critique. Section
-2 gives the background of the competition and the specific, named
-failures the counter-proposal was written to avoid. Section 3 describes
-the method extension. Section 4 reports the worked example as two
-divergent tracks. Section 5 reports reception at a public symposium,
-including a substantive critique that the method, in its current form,
-does not yet produce a coordinated plan. Section 6 discusses this and
-other limitations honestly. Section 7 proposes, as future work, the
-instrument this critique implies is missing. Section 8 concludes.
+three-input method is run twice from a shared narrative root and shared
+pattern/form-language inputs, by two different authors, in public, and
+then subjected to informal peer critique. Section 2 gives the background
+of the competition and the specific, named failures the counter-proposal
+was written to avoid. Section 3 describes the method extension. Section
+4 reports the worked example as two divergent tracks. Section 5 reports
+reception at a public symposium, including a substantive critique that
+the method, in its current form, does not yet produce a coordinated
+plan. Section 6 discusses this and other limitations honestly. Section 7
+briefly sketches one possible direction for future work suggested by
+that critique. Section 8 concludes.
 
 ## 2. Background: The Museo Nacional del Ecuador Competition and Its Discontents
 
@@ -125,7 +128,7 @@ and contemporary art, a human-sciences library, and a historical
 archive) — of which the institution states that under 1% can currently
 be exhibited at once, for lack of space. The Stage 1 open call sought a
 preliminary architectural project for a new building of at least 25,000
-m² on a 13,004.65 m² plot at the corner of Av. Eloy Alfaro and Av. de la
+m² on an approximately 13,000 m² plot at the corner of Av. Eloy Alfaro and Av. de la
 República in the Iñaquito parish of Quito, diagonally across from La
 Carolina Park — one of Quito's most-visited public spaces, itself drawing
 on the order of 400,000 visits a month — with direct access to the La
@@ -228,18 +231,30 @@ vernacular roof forms rather than red clay tile — which is the evidence
 that the template captures a reusable *shape*, not a repackaging of
 Ecuador-specific content.
 
-## 4. Worked Example: Two Independent Deployments from Shared Inputs
+## 4. Worked Example: Two Tracks From a Shared Root
 
-### 4.1 Shared Inputs
+### 4.1 Shared Inputs, Including a Shared Narrative Root
 
-Both tracks reported below share exactly two upstream instruments plus a
-condensed brief: a project-specific pattern subset of 55 patterns from
-Alexander, Ishikawa, and Silverstein [2], curated using the APL-Companion
-web tool described in [1] and prepared for this project by Salingaros;
-and the Ecuadorian Form Language Grammar described in §3.2. Both tracks
-also drew on the same condensed brief and the same named-failure critique
-described in §2. From that point, the two tracks are independent LLM
-runs, by different authors, producing different outputs.
+Both tracks reported below share the same project-specific pattern
+subset of 55 patterns from Alexander, Ishikawa, and Silverstein [2],
+curated using the APL-Companion web tool described in [1] and prepared
+for this project by Salingaros, and the same Ecuadorian Form Language
+Grammar (§3.2), condensed brief, and named-failure critique (§2). But the
+two tracks are not two independent runs from those inputs alone: they
+also share a common narrative ancestor. Salingaros' first prompt to an
+LLM (see Data and Materials Availability) combined the pattern subset,
+form language, and brief into an initial design narrative, *Casa de la
+Memoria Andina*. This document is the root both tracks below grow from,
+not merely a shared set of abstract rules: Track A's shared "chassis"
+document (its own set of fixed invariants — site data, the
+material/color/ornament systems, named circulation realms, and where
+each part of the collection lives) adopts it as primary source, and
+Track A's general-visitor narrative reproduces its prose almost wholesale
+(§4.2); Track B's final narrative is this same document merged with a
+second, independently drafted narrative from a different LLM (§4.3). The
+two tracks are consequently better described as **divergent elaborations
+of a shared root** than as fully independent runs — a distinction that
+matters for how the convergence reported in §4.4 should be read.
 
 ### 4.2 Track A: Four-Stakeholder Narrative Synthesis
 
@@ -247,43 +262,64 @@ Following the narrative-writing approach of [1] §4.2, Postle's track
 wrote four separate experiential narratives, one per stakeholder
 viewpoint (general visitor, museum staff, school group, and
 indigenous/community stakeholders whose heritage the collection
-represents), each independently grounded in the shared pattern subset and
-form-language grammar, and cross-checked against a shared "chassis"
-document of fixed invariants — site data, the material/color/ornament
-systems, named circulation realms, and where each part of the collection
-lives — so that a detail asserted by one stakeholder's narrative (a
-material, a color, a named place) is never contradicted by another's.
-The four narratives were then combined **in full**, not condensed, into a
-single public presentation document, deliberately without pattern numbers
-or grammar codes, since it is written to be read by the public, not by
-practitioners. Thirteen illustration prompts were written, each
-self-contained (the full shared style guide pasted literally into every
-prompt, not cross-referenced), and generated externally via Midjourney,
-producing images in a **warm architectural watercolor and gouache
-register** — a painted presentation drawing, not a photo-realistic
-render, with lighting, weather, and a consistent cast of figures held
+represents). Of these, the general-visitor narrative is substantially
+the shared root narrative described in §4.1, reproduced with only the
+minimal adjustments needed for consistency with the settled chassis; the
+other three were written independently against the same chassis and
+pattern/form-language inputs, without directly reusing the root text.
+All four were cross-checked against the shared chassis document so that
+a detail asserted by one stakeholder's narrative (a material, a color, a
+named place) is never contradicted by another's, then combined **in
+full**, not condensed, into a single public presentation document,
+deliberately without pattern numbers or grammar codes, since it is
+written to be read by the public, not by practitioners. Thirteen
+illustration prompts were written, each self-contained (a shared style
+guide, distilled from the form-language grammar into plain descriptive
+language, pasted literally into every prompt, not cross-referenced —
+rather than the source pattern-subset or form-language documents
+themselves), and generated externally via Midjourney, producing images
+in a **warm architectural watercolor and gouache register**, deliberately
+requested — a painted presentation drawing, not a photo-realistic
+render — with lighting, weather, and a consistent cast of figures held
 constant across the set.
 
 ### 4.3 Track B: Single Merged Narrative
 
 Salingaros' track produced a single narrative, *Casa de la Memoria
-Ecuatoriana*, merged from an initial LLM draft and a second LLM pass
-explicitly asked to reconcile it against the same pattern subset and form
-language, then illustrated with 25 images from ChatGPT, in a markedly
-more **photo-realistic register**. This track is also where the
-project's clearest evidence for an iterative, natural-language critique
-loop comes from: successive rounds of generated images were rejected and
-corrected in plain language rather than by editing pixels — a patio that
-read as faux-antique with trip hazards was regenerated with flush,
-level pavers; an entrance that did not read as a front door on approach
-was replaced by an axial view with a projecting five-bay portal; a
-building raised too far above the street was brought down to sidewalk
-grade; monochromatic tiled columns foreign to the context were
-regenerated with patterned azulejos; and overly white interiors,
-arbitrary facade color patches, and modernist metal railings were each
-identified and revised. Each correction traced back to an explicit
-violation of the pattern subset or form grammar, and each cycle of
-criticism and regeneration took minutes, not days.
+Ecuatoriana*, by merging the shared root narrative (§4.1) with a second,
+independently drafted narrative from a different LLM, explicitly
+instructed to combine the strongest elements of each against the same
+pattern subset and form language. It was then illustrated with 25 images
+from ChatGPT, requested and produced in a markedly more
+**photo-realistic register**, with no watercolor or illustrative-medium
+constraint applied. Salingaros reports, in his own first-person account
+of the process (see Data and Materials Availability), an iterative,
+natural-language critique loop run against these images: successive
+rounds were rejected and corrected in plain language rather than by
+editing pixels — a patio that read as faux-antique with trip hazards was
+regenerated with flush, level pavers; an entrance that did not read as a
+front door on approach was replaced by an axial view with a projecting
+five-bay portal; a building raised too far above the street was brought
+down to sidewalk grade; monochromatic tiled columns foreign to the
+context were regenerated with patterned azulejos; and overly white
+interiors, arbitrary facade color patches, and modernist metal railings
+were each identified and revised, each correction traced back to an
+explicit violation of the pattern subset or form grammar. This account is
+self-reported rather than independently logged; the delivered image set
+offers circumstantial, not conclusive, support — its file numbering
+skips several indices and includes revised variants for at least two
+images, consistent with an iterative reject-and-regenerate workflow
+without proving one. Each reported cycle of criticism and regeneration
+took minutes, not days.
+
+Separately, and independent of any explicit request, each image prompt
+Salingaros wrote for ChatGPT included the full pattern-subset and
+form-language documents inline, rather than a distilled summary, while
+Track A's Midjourney prompts (§4.2) were shorter, LLM-distilled,
+scene-specific prompts referencing only the condensed style guide. This
+difference in prompt strategy — not only the difference in requested
+medium — is discussed as a candidate explanation for the image-register
+divergence in §4.4 and §6.3.
 
 ### 4.4 Convergence and Divergence
 
@@ -292,32 +328,53 @@ Table 1 summarizes the two tracks.
 | | Track A (Postle) | Track B (Salingaros) |
 |---|---|---|
 | Narrative structure | 4 stakeholder-viewpoint narratives, combined in full | 1 merged narrative |
+| Relation to shared root narrative | visitor narrative = root text; other 3 written independently | root text merged with a second, independently drafted LLM narrative |
 | Output document | `docs/counter-proposal.md` | `docs/3.Casa-de-la-Memoria-Ecuatoriana-*.txt` |
 | Image generator | Midjourney | ChatGPT |
 | Image count | 13 | 25 |
-| Image register | watercolor / gouache illustration | photo-realistic |
-| Consistency mechanism | shared chassis document (invariants) | iterative natural-language critique loop |
+| Image register (requested) | watercolor / gouache illustration | no medium constraint; rendered photo-realistic |
+| Image-prompt content | short, LLM-distilled style guide per scene | full pattern-subset + form-language documents inline per image |
+| Consistency mechanism | shared chassis document (invariants) | iterative natural-language critique loop (self-reported, §4.3) |
 
-Despite independent execution by different authors with no coordination
-on wording, both tracks converged on the same high-level design moves
-required by the shared inputs: a stratified material sequence from stone
-base to timber crown; an *atrio* / *zaguán* / patio arrival sequence; a
+Because Track A's visitor narrative and half of Track B's merge input
+share the same root text (§4.1), part of the convergence between the two
+tracks is expected rather than independently earned, and should not be
+over-read as proof that the shared instruments alone drive agreement. The
+more meaningful evidence for that claim comes from the material that was
+*not* shared: Track A's other three stakeholder narratives, Track B's
+second, independently drafted merge input, and — most significantly —
+the two entirely separate image-generation stages, run by different
+authors with different generators and no shared images. Across that
+genuinely independent material, both tracks still arrive at the same
+high-level design moves: a stratified material sequence from stone base
+to timber crown; an *atrio* / *zaguán* / patio arrival sequence; a
 legible, projecting entrance portal; warm-toned interiors with restrained
 concentrated ornament; and circulation organized around named realms
-rather than corridors. This convergence is evidence that the pattern
-subset and form-language grammar meaningfully constrain the output even
-under independent LLM runs — the shared instruments, not authorial
-coordination, are doing the constraining.
+rather than corridors. This is evidence, from a smaller and less
+controlled sample than a fully independent two-track experiment would
+provide, that the pattern subset and form-language grammar meaningfully
+constrain the output beyond what shared text alone would explain.
 
 The two tracks diverge sharply, however, in visual register: Track B's
-images are consistently judged — by the authors and by symposium
-participants (§5) — as the more visually compelling and architecturally
-credible of the two. We do not yet know why. Candidate variables include
-the image generator itself, differences in prompt phrasing between the
-two tracks, and how literally each generator resolves the same
-form-language vocabulary into imagery; we have not isolated which, if
-any, of these accounts for the gap, and we report it here as an open
-finding rather than an explained one (see §6.3, §7).
+images are, in the authors' own judgment, markedly more photo-realistic
+and — subjectively — more visually compelling than Track A's
+watercolor/gouache-register images. This judgment has not been evaluated
+externally on a like-for-like basis: the symposium reported in §5
+discussed Track B's images only, and Track A's images were not presented
+there, so it should be read as the authors' own assessment, not as
+corroborated outside reception. We attribute the divergence to at least
+two factors, neither yet isolated from the other or from any residual
+generator-quality difference: first, it is partly a deliberate,
+requested difference — Track A's prompts explicitly specify a watercolor
+and gouache medium, while Track B's prompts carried no illustrative-medium
+constraint and rendered photo-realistically by default; second, as
+reported in §4.3, Track B's prompts carried the full pattern-subset and
+form-language documents inline, while Track A's carried a short,
+distilled style guide, and the authors' working hypothesis is that
+ChatGPT's greater tolerance for long, dense prompts let it resolve more
+of the form language's specific vocabulary directly into each image,
+where Midjourney's shorter prompts left more to the generator's own
+defaults. This is a hypothesis, not a verified finding (see §6.3).
 
 ## 5. Reception: Informal Peer Engagement at the July 2026 Symposium
 
@@ -350,8 +407,8 @@ paper's limitations section [1] and inherited unchanged by this
 extension: the method produces experiential narratives and illustrative
 images of a design, not a coordinated plan. What the symposium adds is an
 unsolicited, on-the-record confirmation from outside the authors' own
-team that this gap is the one that most needs addressing next, which is
-the direct motivation for §7.
+team that this gap matters. We return to it in §6.1 and note one possible
+response, briefly, in §7.
 
 ## 6. Discussion: Drawbacks and Open Questions
 
@@ -385,19 +442,24 @@ immediately eye-catching rather than most sound), which is a caution
 worth taking seriously if this method is to be used for participatory
 design rather than only advocacy communication.
 
-### 6.3 Unexplained Divergence in Image Register
+### 6.3 Partly-Explained Divergence in Image Register
 
-As reported in §4.4, Track B's photo-realistic images are judged more
-compelling than Track A's watercolor-register images by both authors and
-by symposium participants, despite both tracks sharing the same pattern
-subset and form-language grammar. We flag this honestly as an
-unresolved variable of the method's current image-generation stage,
-not as a property of one generator being categorically better than the
-other — the two tracks differ in generator, in prompt style, and in how
-much each image is asked to carry unaided (13 broadly-scoped prompts vs.
-25 more narrowly-scoped prompts including deliberate parallel color and
-material-cost variants). Isolating the cause would require a controlled
-comparison outside the scope of this paper (see §7).
+As reported in §4.4, Track B's photo-realistic images are, in the
+authors' own assessment, more compelling than Track A's watercolor-register
+images — a judgment the authors have made themselves, not one
+corroborated by outside reviewers evaluating both sets side by side. We
+attribute the divergence partly to a deliberate difference in requested
+medium (photo-realistic vs. watercolor/gouache) and partly to a
+difference in image-prompt content (the full pattern-subset and
+form-language documents fed inline to each Track B prompt, versus a
+short distilled style guide for each Track A prompt), on the working
+hypothesis that ChatGPT's greater tolerance for long, dense prompts
+let it resolve more of the form language directly into each image. Both
+factors are plausible and neither has been isolated from the other or
+from any residual difference in generator capability — a controlled
+comparison (same narrative text, same requested medium, both generators)
+would be needed to separate them, which is outside the scope of this
+paper.
 
 ### 6.4 Unsettled Questions of Authorship and Structural Readiness
 
@@ -408,45 +470,25 @@ and questions of authorship and intellectual property in AI-assisted
 imagery remain unsettled in general, not resolved by anything specific to
 this project.
 
-## 7. Future Work: Toward an Explicit Plan-Layout Layer
+## 7. Possible Future Work
 
-The critique in §5 — that the method, as run here, produces "flavors, not
-solutions" because there is no shared floor plan behind the independently
-generated images — is the clearest and most actionable finding this
-deployment produced, and we take it as the method's next required
-instrument rather than a criticism to be argued down.
+The critique in §5 points toward one possible direction for extending
+the method, which we note here briefly without committing to it or
+having attempted it: an explicit plan-layout generation stage, inserted
+between the pattern-subset/form-language inputs and narrative
+generation, that would make the spatial and adjacency relationships
+already implicit in the pattern subset (building complexes, wings,
+connected buildings, circulation realms) explicit as a shared layout for
+narratives and images to be checked against, rather than each
+independently inventing one. This is a proposal in prose only — no
+prototype has been built for this paper, and we do not treat it as the
+method's necessary next step so much as one plausible answer to a real
+critique among others an architect might reasonably prefer.
 
-We propose, without yet prototyping, an explicit **plan-layout
-generation** stage inserted between the existing pattern-subset/
-form-language inputs and the narrative-generation stage. The pattern
-subset already encodes spatial and adjacency relationships implicitly —
-patterns concerning building complexes, wings, connected buildings,
-circulation realms, and entrance transitions are themselves claims about
-how spaces relate to one another — and the project-chassis document used
-in Track A already names specific circulation realms and collection
-placements as fixed invariants. The proposal is to make this implicit
-spatial information explicit: prompt an LLM to derive a bubble-diagram or
-adjacency layout directly from the pattern subset and brief, before
-narrative generation, so that subsequent narratives and image prompts —
-whether one combined narrative or several stakeholder narratives, as in
-this project — are *derived from* one shared layout rather than each
-independently inventing a version of it. This would not, on its own,
-produce a buildable plan; it would produce a shared spatial scaffold that
-narratives and images could be checked against, directly narrowing the
-class of discrepancy described in §6.1.
-
-This is proposed as future work in this paper. A separate, exploratory
-prototype of this idea exists as an open, lower-priority research task
-outside this paper's critical path, and may be folded into a revision of
-this section if it produces something worth reporting before publication;
-its absence does not weaken any claim made above.
-
-A secondary, lower-priority open question is the unexplained image-register
-gap of §6.3: a controlled comparison — the same narrative text and the
-same style-guide language, run through both generators — would help
-isolate whether the gap is attributable to the generator, the prompt, or
-some other variable, but is not required to support this paper's central
-claims.
+A separate, lower-priority open question is the image-register divergence
+of §6.3: a controlled comparison isolating requested medium from
+prompt-content length would help settle how much each contributes, but
+is not required to support this paper's central claims.
 
 ## 8. Conclusion
 
@@ -458,20 +500,22 @@ input, the form language, following Salingaros' theoretical distinction
 between the human/organizational and geometric/tectonic languages of
 architecture — which we generalized from a bespoke, project-specific
 prompting process into a reusable template and validated on an unrelated
-project. Run twice, independently, by different authors, from the same
-shared pattern subset and form language, the method converged on
-compatible design moves while producing genuinely different narratives
-and a qualitatively different, currently unexplained, image register.
-Presented to informal peer scrutiny, the work drew a substantive
-critique, not only praise: that the method, as deployed, produces images
-without a coordinated plan behind them. We agree with that critique, and
-propose the explicit plan-layout instrument it implies as the method's
-next necessary extension. Design knowledge, once written down as
+project. Run by two authors from a shared narrative root and shared
+pattern subset and form language, the method's two divergent elaborations
+converged on compatible design moves in their genuinely independent
+material, while producing a qualitatively different image register, a
+difference we can partly, though not yet fully, account for. Presented
+to informal peer scrutiny, the work drew a substantive critique, not
+only praise: that the method, as deployed, produces images without a
+coordinated plan behind them. We agree with that critique and take it
+seriously; §7 sketches one possible response without committing to it as
+the method's necessary next step. Design knowledge, once written down as
 readable rules rather than embodied only in a single expert's intuition,
 can be executed, checked, criticized, and revised at the speed of
 conversation — but a pattern language and a form language, however well
-executed, are not yet a plan, and the honest next step for this method is
-to build the instrument that makes them one.
+executed, are not yet a plan, and this deployment's clearest lesson is
+that the method should say so honestly rather than let illustrative
+images stand in for one.
 
 ---
 
@@ -498,6 +542,9 @@ formal references:
 - Condensed brief and named-failure critique:
   `ref/brief-condensed.md`, `ref/critique-failures.md`
 - Shared invariants ("chassis"): `ref/project-chassis.md`
+- Shared root narrative and the prompts that produced it:
+  `docs/Casa-de-la-Memoria-Andina-National-Museum-Narrative-Kimi.txt`,
+  `docs/salingaros-narrative-prompt.md`
 - Form-language prompt template: `templates/form-language-prompt-template.md`
 - Template validation on a second project: `templates/examples/sheffield.md`
 - Track A narratives and public document: `narratives/01-visitor.md`