The mechanical candidate set

Everything locate_shapes_en surfaced on this page, and what the reading half did with each one.

72candidates located

16altered by the pass

56left standing

0edits made by the toolkit

The locator ranks nothing and rules on nothing — it prints instances. Every disposition below was a reader's judgment. Where that judgment was written down per instance it is marked recorded; where only the governing class rule was written down it is marked class rule. The population figures come from 120M words of pre-LLM human prose measured against 1.44M words of LLM essays sampled across ten models on identical instruments.

negation 28 located · 7 altered · 21 left standing

SEPARATES - 2.23x. The only English structural shape that distinguishes the human from the machine population (human 0.97/1k, machine 2.17/1k). This page opened at 2.81, half again past the machine rate. This is the shape the pass was spent on.

LEFT STANDING recorded
RCTs are real and useful, and they sharpen the why-poor framing rather than undermining it, they are the most policy-actionable layer the stack has.
matched: rather than
Plain comparative. 'rather than undermining it' is ordinary English, not a reframe. The locator's own docs name this false-positive class.
LEFT STANDING recorded
The aggregation gap Pritchett names is not a flaw in the method; it is the framing’s own shape made visible.
matched: is not a flaw in the method; it is
EARNED. A is a position the Take's counter-section actually argued, that the gap is the method's flaw. The correction is the point.
ALTERED recorded
Asked not as a stylistic flourish but as a methodological move, with the historical record, not the present-day gap, as the starting point.
matched: not as a stylistic flourish but
CUT (first half). Two reframes in one sentence; the historical-record contrast is content and was kept as 'rather than', the stylistic-flourish denial is the page's recurring tic.
LEFT STANDING recorded
Better technology raised the population, not the wage; a good harvest meant more mouths, not richer households.
matched: , not the w
EARNED. This is the Malthusian mechanism itself, population absorbing the gain instead of the wage. Deleting the contrast deletes the claim.
ALTERED recorded
The interesting object is not the level today; it is the date and mechanism of the break.
matched: is not the level today; it is
CUT. The preceding sentence already draws the contrast, 'reads as a present-day gap, Galor reads as a phase transition'.
ALTERED recorded
Stare at the bend and a different apparatus assembles itself, the economic-historian’s stack, not the development economist’s.
matched: , not the d
CUT. 'A different apparatus' already carries the contrast; the trailing ', not the development economist's' is a reframe hiding as an appositive.
LEFT STANDING recorded
Sustained innovation is not a single invention; it is a society that keeps producing inventions, and that takes institutions of the mind.
matched: is not a single invention; it is
EARNED. A is the popular great-inventor story, which the paragraph is correcting.
LEFT STANDING recorded
The flipped framing reaches for culture, contingency, and rhetoric precisely because it is asking a historical-explanatory question, not a present-day intervention question.
matched: , not a p
EARNED. The historical-versus-intervention contrast is the page's spine, stated once here.
LEFT STANDING recorded
The formal scaffolding sits in the economics text, the dynamic-optimization backbone in Ch 13 §13.1 (the Ramsey model) and the endogenous-growth machinery, where ideas are produced rather than assumed, in Ch 13 §13.4 (Romer’s endogenous-growth model) . (Read through the flipped lens, endogenous growth stops asking “why don’t poor countries copy ideas?” and starts asking “what made the ideas inventable in the first place?”) The institutional apparatus, which the why-poor framing met as a present-day extractive-versus-inclusive distinction, returns here as a historical-mechanism question, Ch 18 §18.3 (the AJR framework) .
matched: rather than
Plain comparative ('produced rather than assumed'). False positive.
LEFT STANDING recorded
The specific question of whether slavery was the central mechanism that made the West rich, rather than one contingency among Pomeranz’s several, is its own dispute, worked at depth in the companion walkthrough “Did the West get rich because of slavery?” and in History Ch.9 (Atlantic slavery and after) .
matched: rather than
Plain comparative. False positive.
LEFT STANDING recorded
Here it appears only as one element of the apparatus the flipped framing surfaces, not as a verdict on its weight.
matched: , not as
EARNED. Scope-boundary chrome with a real function: it tells the reader what this page does and does not adjudicate.
LEFT STANDING recorded
It runs from Adam Smith’s reading of commercial society as the engine of the wealth of nations, traced in History of Economic Thought Ch.3 (Classical political economy) , through the historicist reaction that insisted economies are made by specific histories, not universal laws: Marx’s account of the historical rise of capitalism (the root of that tradition, in History of Economic Thought Ch.4 (Marx) ), and on through Weber’s Protestant ethic and Polanyi’s great transformation, into Pomeranz’s own work.
matched: , not u
EARNED. 'made by specific histories, not universal laws' is the historicist doctrine being described.
LEFT STANDING recorded
Mokyr’s claim is institutional, not vague.
matched: , not v
LEFT STANDING this run. 'not vague' answers the weak section's charge that culture is an unfalsifiable placeholder.
LEFT STANDING recorded
McCloskey adds the rhetorical hinge, a new dignity granted to commerce and invention, so that the people who improved things were honored rather than scorned.
matched: rather than
Plain comparative ('honored rather than scorned'). False positive.
LEFT STANDING recorded
Allen answers that prices do the heavy lifting and culture is downstream: it was Britain’s wage-and-energy structure that made the spinning jenny pay, and the inventors followed the money, not the dignity.
matched: , not the d
EARNED. 'followed the money, not the dignity' is Allen's actual position against McCloskey.
LEFT STANDING recorded
Each made the reversal an explicit methodological commitment: Pomeranz by insisting the question is why Europe diverged, not why Asia lagged; Mokyr by building an account of the cultural-institutional preconditions of sustained innovation; Galor by writing a single model whose central object is the takeoff itself.
matched: , not w
EARNED. 'why Europe diverged, not why Asia lagged' is Pomeranz's own move, the reversal the whole page is about.
LEFT STANDING recorded
The why-poor framing keeps its priority not because it is theoretically deeper but because it is the one that can act, and acting on poverty is not a luxury that can wait for the historians to finish.
matched: not because it is theoretically deeper but
EARNED. 'not because deeper but because it can act' is a real same-plane correction.
ALTERED recorded
Pomeranz, Mokyr, and Galor are not arguing inside the development economist’s apparatus about parameter values; they are working a different apparatus stack altogether, one built for coal and culture and demography rather than for binding constraints and randomized trials.
matched: are not arguing inside the development economist’s apparatus about parameter values; they are
CUT. Near-verbatim duplicate of the Stage 3 thesis sentence; the unique content ('built for coal and culture and demography') was kept.
LEFT STANDING recorded
A great many “disputes” in growth and development are not disputes within a model but disagreements about which question the model is built to answer.
matched: not disputes within a model but
EARNED. 'not disputes within a model but disagreements about which question' is the load-bearing claim of the whole piece.
LEFT STANDING recorded
The unified theory of inclusive and extractive institutions is what lets the two halves speak to each other rather than sitting in separate books.
matched: rather than
Plain comparative. False positive.
LEFT STANDING recorded
The counters are not refutations of the synthesis; they are reminders that the institutional category is wide and that the other apparatus the flip surfaced — culture, contingency, geography — operates alongside institutions rather than reducing to them.
matched: are not refutations of the synthesis; they are
EARNED. A is a reading someone would actually take from the counter-section just presented.
ALTERED recorded
So the verdict is layered, not flat: the book is the strongest demonstration that the framings converge at the institutional layer, while framings being upstream of frameworks, and each framing having its own domain, keep that convergence from hardening into a one-cause theory of everything.
matched: , not f
CUT. Nobody proposed a flat verdict. Manufactured foil.
LEFT STANDING recorded
The framing is not neutral; the choice of question has apparatus consequences; and knowing which framing you are inhabiting sharpens the apparatus rather than weakening it.
matched: rather than
LEFT STANDING. The sentence is the Stage 3 judgment's topic sentence.
LEFT STANDING recorded
Her bourgeois-dignity account is itself the proof, it became thinkable only once she asked why the modern world arose rather than why the rest stayed behind.
matched: rather than
EARNED. 'why the modern world arose rather than why the rest stayed behind' IS the flip.
ALTERED recorded
This is the strongest case against treating the flip as a commitment rather than a curiosity, and the verdict does not brush it aside, it grants it.
matched: rather than
CUT (whole sentence). Appraisal plus a claim restated three sentences later.
LEFT STANDING recorded
The second layer of the verdict exists precisely to honor this objection: each framing has a domain, and the policy-actionable present is the why-poor framing’s domain by right, not on sufferance.
matched: , not o
CUT (trailing half). 'by right' already excludes 'on sufferance'.
LEFT STANDING recorded
A methodology built to answer “what works at this intervention point?” will never reach for the status of merchants in seventeenth-century Holland, not because that factor is unreal but because the question rules it out of view.
matched: not because that factor is unreal but
EARNED. 'not because that factor is unreal but because the question rules it out' is the conclusion's actual mechanism.
ALTERED recorded
So the verdict is layered rather than declared for one side.
matched: rather than
CUT. Third statement of a claim already made twice.

capsule 11 located · 4 altered · 7 left standing

NO SEPARATION (~1.0x). Capsule openers occur at the same rate in human and machine prose. Cutting them is style preference, not de-slopping.

LEFT STANDING class rule
That is a factor of more than fifty between top and bottom.
matched: That is a
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
It is the most disciplined form the why-poor framing has taken.
matched: It is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
This is the apparatus speaking at full strength.
matched: This is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
This is the Malthusian trap, and it held everywhere, for almost everyone, for almost all of history.
matched: This is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED class rule
That is the claim underneath: the question is historical because the gap is a historical anomaly, and a historical question selects a historical apparatus.
matched: That is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
That is the why-poor framing in miniature, a present-day gap, a policy-actionable cause, a fence you could in principle move.
matched: That is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
That is the why-rich framing.
matched: That is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED class rule
It is the discipline’s quiet recognition that when both framings are applied honestly — one to the present gap, one to the historical bend — they keep landing on the same answer.
matched: It is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED class rule
This is the case we’re making, and McCloskey states its sharpest form.
matched: This is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
It is the thing that lets you notice when a whole class of causes has been ruled out before the analysis even began.
matched: It is the
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED recorded
This is the strongest case against treating the flip as a commitment rather than a curiosity, and the verdict does not brush it aside, it grants it.
matched: This is the
CUT (whole sentence). Appraisal plus a claim restated three sentences later.

superlative 10 located · 3 altered · 7 left standing

NO SEPARATION (~1.0x). Measured across ten models; superlatives are not an AI tell at population scale.

LEFT STANDING class rule
It is the most disciplined form the why-poor framing has taken.
matched: the most disciplined
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING recorded
RCTs are real and useful, and they sharpen the why-poor framing rather than undermining it, they are the most policy-actionable layer the stack has.
matched: the most policy
Plain comparative. 'rather than undermining it' is ordinary English, not a reframe. The locator's own docs name this false-positive class.
LEFT STANDING class rule
Both slogans dodge the actual claim, which is narrower and more interesting than either.
matched: the actual
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED class rule
This is not a strawman, and it is the strongest thing the why-poor framing can say back.
matched: the strongest
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Granting every word of the flip — that the takeoff is the real anomaly, that the historical apparatus explains it — still leaves the development minister exactly where she started.
matched: the real
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Why Nations Fail is the canonical case of one set of authors holding both framings at once and using a single institutional theory to bridge them.
matched: the canonical
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Why Nations Fail genuinely is the canonical case of holding both framings, and it earns that standing because the institutional theory, applied honestly to both questions, keeps producing convergent answers.
matched: the canonical
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED recorded
So the verdict is layered, not flat: the book is the strongest demonstration that the framings converge at the institutional layer, while framings being upstream of frameworks, and each framing having its own domain, keep that convergence from hardening into a one-cause theory of everything.
matched: the strongest
CUT. Nobody proposed a flat verdict. Manufactured foil.
ALTERED recorded
This is the strongest case against treating the flip as a commitment rather than a curiosity, and the verdict does not brush it aside, it grants it.
matched: the strongest
CUT (whole sentence). Appraisal plus a claim restated three sentences later.
LEFT STANDING class rule
Framing-direction is upstream of framework-disagreement; each framing earns its keep in its own domain; and where the two converge, they converge on institutions, with Why Nations Fail as the canonical case of one institutional theory holding both questions at once.
matched: the canonical
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.

address 16 located · 2 altered · 14 left standing

NO SEPARATION (~1.0x). Imperative address to the reader is this page's deliberate method - the whole piece is an instruction to flip a question.

LEFT STANDING class rule
Ask why countries are poor and you reach for one toolkit.
matched: Ask
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Ask why they are rich and a different one appears.
matched: Ask
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Notice the verb: end .
matched: Notice
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Turn the question around.
matched: Turn
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Watch a different apparatus come up in your hands.
matched: Watch
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Picture the whole human income chart as a flat line running ten thousand years long.
matched: Picture
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Ask “why are countries poor?” and you stare at the right-hand edge of the chart.
matched: Ask
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Ask “why are countries rich?” and you stare at the bend.
matched: Ask
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED recorded
Stare at the bend and a different apparatus assembles itself, the economic-historian’s stack, not the development economist’s.
matched: Stare
CUT. 'A different apparatus' already carries the contrast; the trailing ', not the development economist's' is a reframe hiding as an appositive.
LEFT STANDING class rule
Notice what just happened to the toolkit.
matched: Notice
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Reverse the question and a whole class of explanations comes into view that was invisible before.
matched: Reverse
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Picture the income gap as a hill that, once climbed, is hard to fall off.
matched: Picture
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
ALTERED class rule
Turn the question around and a different one comes up in your hands.
matched: Turn
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Ask why countries are poor and you pick up the development-economics apparatus — Solow, ideas, institutions, RCTs — a single stack that asks, step by step, what is blocking convergence, and that is policy-actionable by design because the framing treats poverty as a present-day failure to fix.
matched: Ask
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Hold the same data and ask why countries are rich, and against the ten-thousand-year Malthusian baseline wealth becomes the anomaly, a one-and-a-half-century bend in the chart.
matched: Hold
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Hold both questions, know which one you are asking, and you can see the gap from both vantage points at once, the bottom of the hill and the summit, the failure to converge and the anomaly that needs explaining.
matched: Hold
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.

signpost 5 located · 0 altered · 5 left standing

NO SEPARATION (~1.0x). The First/Second/Third run labels three genuinely distinct bolded claims, so the order is real rather than imposed.

LEFT STANDING class rule
If two framings of the same question select two different apparatus stacks, what follows for policy?
matched: what follows
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
And what follows for the verdict, is one framing right and the other wrong, or do they coexist, each earning its keep somewhere?
matched: what follows
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
First, framing-direction is upstream of framework-disagreement.
matched: First,
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Second, each framing has a natural domain where it earns its keep.
matched: Second,
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
Third, where the framings converge, they converge on institutions.
matched: Third,
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.

tricolon 2 located · 0 altered · 2 left standing

NO SEPARATION - 0.85x, running slightly BELOW the machine rate. This overturns an earlier 3.7x reading taken from 7,331 words, which had been reported as confirming rule-of-three overuse as an AI tell. It is not one.

LEFT STANDING class rule
Each is policy-actionable by design: a binding constraint to diagnose, an intervention to run, an outcome to measure, an iteration to make.
matched: 3x 'an'
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.
LEFT STANDING class rule
That is the why-poor framing in miniature, a present-day gap, a policy-actionable cause, a fence you could in principle move.
matched: 3x 'a'
No per-instance ruling was recorded. Governed by the class rule above: this shape shows no separation between the human and machine populations.