Methodology/Validation

Does the Geometry Work

Canonical-pair ranks vs. random baseline

Rodin makes a falsifiable prediction. If the matching geometry recovers real intellectual kinship, then pairs of writers with documented historical relationships — mentor & mentee, antagonist & antagonist, lineage holder & inheritor — should rank one another well above chance among the 250 rival profiles in the archive.

The fixture below is hand-curated from textual record: Kant on Hume, Pascal on Montaigne, Wollstonecraft to Shelley. Three independent metrics are evaluated — the production cosine ranker, the Jaccard + topology blend, and Burrows’ Delta on function-word frequencies. A random metric would place each partner at a median rank near 125. The numbers below are what the live system returns.

Summary

Cosine

Documented median rank

6.0

Controls median rank

178.0

Random baseline

125

Blend

Documented median rank

37.0

Controls median rank

117.0

Random baseline

125

Stylometric

Documented median rank

44.0

Controls median rank

210.0

Random baseline

125

Lower is better. Documented pairs should sit far below the random baseline of 125; negative controls (unrelated thinkers from different eras and domains) should sit near it. Rank is the smaller of A→B and B→A — matching is symmetric in intent, but the geometry is not always perfectly so.

Documented Pairs (23)

PairLabelCosBlendStyloΔ

Ralph Waldo Emerson

× Henry David Thoreau

RWE mentored HDT; close friends

MENTOR MENTEE16/25031/250104/2501.13

Ralph Waldo Emerson

× Walt Whitman

RWE: "I greet you at the beginning of a great career"

CHAMPION2/25038/25069/2501.03

Henry David Thoreau

× Walt Whitman

Met 1856; transcendentalist circle

CONTEMPORARY26/25025/250110/2500.98

Immanuel Kant

× David Hume

Kant: "Hume awakened me from dogmatic slumber"

LINEAGE CRITICAL1/25082/250121/2501.16

Immanuel Kant

× Jean-Jacques Rousseau

Kant hung Rousseau's portrait in his study

ASYMMETRIC INFLUENCE21/25091/250199/2501.33

David Hume

× John Locke

Hume built on and departed from Locke

LINEAGE63/25037/25019/2500.91

John Locke

× Jean-Jacques Rousseau

Rousseau critiqued Locke on social contract

ANTAGONISTIC1/25017/25028/2500.90

Friedrich Nietzsche

× Arthur Schopenhauer

N read S deeply, later moved beyond

INFLUENCE REBELLION1/2502/25018/2500.85

Friedrich Nietzsche

× Plato

N framed much of his work anti-Platonic

ANTAGONISTIC5/25015/25013/2500.87

René Descartes

× Blaise Pascal

Pascal critiqued Cartesian certainty

ANTAGONISTIC20/25016/25044/2500.95

Blaise Pascal

× Michel de Montaigne

Pascal wrestled with Montaigne's skepticism

PRODUCTIVE FRICTION10/25037/2503/2500.70

Leo Tolstoy

× Fyodor Dostoevsky

Contemporaries who never met, mutual awareness

MUTUAL AVOIDANCE6/25013/250178/2501.29

Mary Wollstonecraft

× Mary Shelley

Mother/daughter; W died at M's birth

FILIAL INFLUENCE57/2509/25063/2501.13

Lao Tzu

× Zhuangzi

Taoist succession

LINEAGE31/25051/250202/2501.46

Confucius

× Lao Tzu

Legendary opposition of Chinese traditions

PHILOSOPHICAL OPPOSITION2/25061/25035/2501.08

William James

× John Dewey

American pragmatist colleagues

COLLEAGUES102/2509/2506/2500.67

William James

× Bertrand Russell

Russell engaged James's pragmatism

CRITICAL DIALOGUE1/25046/25027/2501.03

Tyler Cowen

× Alex Tabarrok

Marginal Revolution co-authors 20+ years

COLLABORATORS1/2501/2501/2500.00

Ezra Klein

× Matt Yglesias

Co-founded Vox

CO FOUNDERS3/25054/25016/2501.21

Scott Alexander

× Gwern Branwen

Rationalist blogosphere core

PEER NETWORK11/250131/25045/2500.87

Robin Hanson

× Eliezer Yudkowsky

Famous FOOM debate; same field, opposed priors

ANTAGONISTIC SAME FIELD2/2502/25036/2500.84

Naval Ravikant

× Balaji Srinivasan

Crypto/sovereignty thought space

PEER NETWORK41/25048/25088/2501.16

Nassim Taleb

× Nassim Nicholas Taleb (Incerto)

Same person — expected rank 1 or 2

IDENTITY DUPLICATE1/25037/25053/2501.12

Negative Controls (4)

Pairs with no documented intellectual contact, drawn from different eras and disciplines. A working metric should rank these near the random baseline — not high, not low.

PairLabelCosBlendStyloΔ

Confucius

× Ali Abdaal

Ancient Chinese / modern productivity YouTuber

UNRELATED CONTROL170/250237/250210/2501.52

Immanuel Kant

× Bryan Johnson

German idealism / longevity biohacker

UNRELATED CONTROL178/250117/250

Lao Tzu

× Tomas Pueyo

Taoist sage / viral infographic writer

UNRELATED CONTROL164/25057/25097/2501.21

Rabindranath Tagore

× Shreyas Doshi

Bengali polymath / product management coach

UNRELATED CONTROL223/250112/250

What this measures — and what it doesn’t

What it does measure. Whether the geometry is structurally non-random. If documented pairs cluster well below the 125-rank baseline, the metric is recovering real signal — not perfectly, but reliably above chance.

What it does not measure. Whether the matches are good in the felt sense — whether the writer would, on reading the suggested mind, recognize kinship. That is a human judgment the geometry approximates but does not replace. The fixture is also small (n ≈ 23) and curated; it tests whether the geometry behaves sanely on hand-picked positives, not whether it generalizes to every possible pair.

Why three metrics.The production matcher blends them. Cosine catches semantic neighborhood; the Jaccard+topology blend reads structural resemblance and surface motif overlap; Burrows’ Delta reads prose at the function-word grain. The three answer different questions about kinship, and a pair the geometry truly recovers should land well across more than one of them.

Generated 2026-04-29· refreshed daily