---
id: "20260912-0204-what-genuinely-connects-persistent"
title: "What genuinely connects the persistent-homology gradient-free bridge and the hub-selection-artifact-absence observation"
type: "capture"
status: "promoted"
origin: "batch"
promoted_to: ["30-notes/observation-ph-bridge-and-hub-selection-absence-form-one-argument.md","30-notes/claim-rieck-2019-neural-persistence-computed-without-subsampling.md","30-notes/observation-hub-selection-risk-needs-incomplete-object-nn-diagnostics-read-complete-record.md","40-entities/entity-bastian-rieck.md","40-entities/entity-herbert-edelsbrunner.md","40-entities/entity-neural-persistence.md"]
not_promoted: ["Claim 4 ('the bridge holds at the level it actually claims...') — dropped as a restatement of claims 1 and 3 combined, not an atomic addition; its content is fully carried by the two promoted observation notes.","Further leads (Corneanu et al. 2020, Chowdhury et al. 2019, Rieck's appendix A.4 conv-layer approximation, a dedicated search for structurally-selective NN-PH diagnostics) — left in the capture as research leads, not claims; none is a load-bearing doubt a kept claim rests on, so none was routed to 50-questions/ per the intake-discipline standard.","Entity candidate: Karsten Borgwardt — declined a hub page. Real and senior/last author of the Rieck et al. paper, but the only distinguishing fact available ('runs the lab') is true of nearly every senior author and isn't load-bearing on its own; left as a mention via [[entity-bastian-rieck]] rather than promoted, per the entity spec's flood bias."]
writer_model: "claude-sonnet-5"
date_created: "2026-09-12T00:00:00.000Z"
provenance: "web-research batch run, 2026-09-12"
derived_from: []
tags: ["persistent-homology","topological-data-analysis","generalization","sampling-artifact","cross-domain-bridge","neural-networks","cliodynamics","methodology","gradient-free"]
sources: [{"source_url":"https://arxiv.org/abs/1812.09764","source_title":"Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology","source_author":"Bastian Rieck, Matteo Togninalli, Christian Bock, Michael Moor, Max Horn, Thomas Gumbsch, Karsten Borgwardt","source_date":"2018-12","source_venue":"International Conference on Learning Representations (ICLR) 2019; arXiv:1812.09764","source_tier":1,"source_quote":"amounts to sorting all n weights of a network, which has a computational complexity of O(n log n)","source_sha":"2338425da2a1e294a637c55761fa31b9c7d0b49c2181439de70ce2b2c784ce33","source_note":"Full PDF fetched and read directly via extract_pdf (arxiv.org/pdf/1812.09764, tls:verified) this session. Quote checked verbatim against the extracted text via quote_check."},{"source_url":"https://arxiv.org/abs/2111.13171","source_title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","source_author":"Tolga Birdal, Aaron Lou, Leonidas Guibas, Umut Şimşekli","source_date":"2021-11","source_venue":"NeurIPS 2021; arXiv:2111.13171","source_tier":1,"source_note":"Not re-fetched this session — already independently verified in [[claim-birdal-2021-persistent-homology-dimension-bounds-generalization]] and [[claim-birdal-2021-phd-estimator-samples-training-iterates-uniformly-at-random]]; cited here by reference, not re-quoted."},{"source_url":"https://arxiv.org/abs/2106.00012","source_title":"Persistent Homology Captures the Generalization of Neural Networks Without A Validation Set","source_author":"Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé, Marta Villegas","source_date":"2021-05","source_venue":"arXiv:2106.00012 (preprint)","source_tier":1,"source_note":"Not re-fetched this session — already independently verified in [[claim-gutierrez-fandino-2021-persistence-diagram-distance-tracks-generalization]] and [[claim-gutierrez-fandino-2021-method-subsamples-nothing-uses-full-network]]; cited here by reference, not re-quoted."},{"source_url":"https://arxiv.org/abs/2607.05695","source_title":"Structural Divergence of the Roman--Byzantine Trade Network, 0--1453 CE: Persistent Homology, Topological Velocity, and Criticality Indicators of Imperial Collapse","source_author":"Jose de Jesus Bernal-Alvarado, David Delepine, Carlos Pinedo Guadarrama","source_date":"2026-07","source_venue":"arXiv:2607.05695 (preprint)","source_tier":1,"source_note":"Not re-fetched this session — already independently verified in [[claim-roman-byzantine-trade-network-decoupled-after-1082-chrysobull]] and [[claim-hub-selection-artifact-can-reverse-network-breakpoint-signal]]; cited here by reference, not re-quoted."}]
seek_code_commit: "850b81d"
---


The vault's retrieval index flagged
[[observation-persistent-homology-gradient-free-bridge-widrow-byzantine]] and
[[observation-hub-selection-artifact-absent-by-design-in-founding-ph-generalization-papers]]
at cosine 0.87 and unlinked. No prior capture in `10-inbox/raw/` investigates
this specific pair together (checked by slug search); this is a fresh
investigation, not a duplicate. Both notes already rest on independently
verified Tier 1 primaries — Birdal et al. (2021), Gutiérrez-Fandiño et al.
(2021), and Bernal-Alvarado et al. (2026) — so the question this capture
answers is not "are the underlying facts true" (already settled in the
vault) but "is the connection between these two *readings* of those facts
real, or does it just look that way because they share vocabulary."

## Claim: The two notes are one continuous argument, not two independent resemblances that happen to share vocabulary

[[observation-persistent-homology-gradient-free-bridge-widrow-byzantine]]
establishes that persistent homology — specifically, Wasserstein/bottleneck
distance between persistence diagrams — is the same computational operation
diagnosing two different collapses:
[[claim-birdal-2021-persistent-homology-dimension-bounds-generalization]] and
[[claim-gutierrez-fandino-2021-persistence-diagram-distance-tracks-generalization]]
on the neural-network side, and
[[claim-roman-byzantine-trade-network-decoupled-after-1082-chrysobull]] on the
historical-network side. That note's own closing lines explicitly raise the
next question: whether the neural-network diagnostics inherit "the Byzantine
study's own documented failure mode — sampling bias reversing a topological
signal," i.e.
[[claim-hub-selection-artifact-can-reverse-network-breakpoint-signal]].
[[observation-hub-selection-artifact-absent-by-design-in-founding-ph-generalization-papers]]
is the direct answer to that question: it reads both founding NN-PH papers'
method sections and finds neither has a point of entry for a
structural-selection artifact — Birdal's estimator samples training
iterates uniformly at random over time, and Gutiérrez-Fandiño's method does
not subsample at all. The second note's opening sentence names the same
open question the first note's closing paragraph raises. The 0.87 cosine
reflects a real dependency, not surface overlap: the second observation
could not have been asked without the first having proposed the bridge in
the first place. On promotion, these two notes should carry a direct mutual
wikilink rather than being connected only indirectly through
[[claim-hub-selection-artifact-can-reverse-network-breakpoint-signal]] and
the (currently unfiled) question they both reference.

## Claim: A third founding-era NN persistent-homology diagnostic — Rieck et al.'s "Neural Persistence" (2019) — also has no structural-selection step, extending the second observation's finding beyond the two papers it examined

The second observation flagged Rieck et al.'s "Neural Persistence" (cited in
Birdal et al.'s related work) as an unexamined further lead — a PH-based
network diagnostic computed directly on trained weights rather than a
trajectory sample, and therefore a plausible place for a structural-selection
step to exist. A direct read of the paper's method (Section 3, Algorithm 1)
finds no subsampling of any kind: neural persistence is computed by summing
zero-dimensional persistent homology over *every* layer's *complete* weighted
graph, transforming and sorting all of a network's weights to build the
filtration. The paper's own efficiency claim states this directly: the
computation "amounts to sorting all n weights of a network, which has a
computational complexity of O(n log n)" — n being the full weight count, not
a subsample. There is no analog anywhere in the method to selecting a subset
of neurons, edges, or layers by a structural covariate. This is architecturally
closer to Gutiérrez-Fandiño's "keep every single neuron and connection"
design than to Birdal's random-subsampling design, but the conclusion is the
same: no selection step, so a hub-selection-style artifact has no foothold.
Three-for-three founding-era NN-PH diagnostics now show the same absence.

## Claim: The absence tracks a structural asymmetry between introspecting a network and reconstructing a historical one, not a coincidence of three papers' method choices

All three NN-PH diagnostics examined across this and the prior session —
Birdal's random-in-time sampling, Gutiérrez-Fandiño's no-sampling, and
Rieck's full-weight-matrix computation — operate on a complete,
directly-recorded object: the network's own weights, captured during its own
training run. Nothing about the object being measured is missing or has to
be estimated. The Byzantine study's hub-selection artifact, by contrast,
exists because the 2,599-node trade network
([[claim-roman-byzantine-trade-network-decoupled-after-1082-chrysobull]]) is
a reconstruction calibrated against Stanford's ORBIS model of surviving
historical evidence — an unavoidably partial stand-in for a trade network no
one recorded in full. Choosing which nodes to include is not optional there
the way it is for Birdal (whose random-sampling choice is a compute-saving
convenience over an already-complete trajectory record). This structural
reading is Seek's synthesis across the four papers, not a claim any one of
them states directly: the vulnerability has no foothold on the neural-network
side so far because neural-network diagnostics are not, in the relevant
sense, sampling a hidden object — they are reading one in full. It does not
follow that no future PH-based NN diagnostic could introduce a comparable
risk; a diagnostic that selected checkpoints or weights by a structural rule
(loss-based, magnitude-based, layer-based) rather than reading everything or
sampling at random would reintroduce exactly the choice the Byzantine study's
robustness section had to guard against.

## Claim: The bridge holds at the level it actually claims — shared operation — and does not (yet) extend to a shared vulnerability; the resemblance between the two notes is a real, causal chain, not a superficial pattern-match

The first observation's claim survives the stress-test the second observation
performs: persistent homology genuinely is the same operation diagnosing both
collapses, and that operation transfers cleanly across domains. What does not
transfer, at least among the three NN-PH diagnostics examined to date, is the
specific failure mode the same underlying Byzantine paper caught in itself.
The topic's framing — "neither founding paper documents, tests, or rules out"
the artifact — is accurate and remains the honest scope limit: absence in
three papers examined is not proof of absence in the field. But the
connection between the two notes is not superficial resemblance dressed up
in shared jargon; it is one observation testing a risk the other observation's
own argument raised, and finding (so far) that the risk requires a precondition
— a structural-selection step over an incompletely-known object — that
none of the neural-network side's diagnostics currently has.

## Further leads

- Corneanu et al. 2020 (CVPR), "Computing the Testing Error Without a Testing Set" — still unread; both NN-PH papers already in the vault criticize its metric-space construction as "numerically brittle," which could itself be a selection-sensitivity issue.
- Chowdhury et al. 2019, "Path homologies of deep feedforward networks" — cited as related work by Gutiérrez-Fandiño et al.; sampling method still not checked.
- Rieck et al.'s appendix (Section A.4) extends the method to convolutional layers via "a closed-form approximation" — worth checking directly whether that approximation reintroduces any selection step the fully-connected-layer version lacks (not checked this session; flagged from the abstract-level appendix summary only, page not read in full).
- A dedicated search for PH-based NN diagnostics that *do* select checkpoints, weights, or neurons by a structural rule (rather than reading everything or sampling randomly) would be the real test of whether the hub-selection risk can manifest on the neural-network side at all — none located across two sessions now.

## Entity candidates

- Herbert Edelsbrunner — person — co-originator of persistent homology itself (Edelsbrunner, Letscher & Zomorodian, "Topological persistence and simplification," 2002; Edelsbrunner & Harer's *Computational Topology*, 2010); every NN-PH paper and the Byzantine paper in this cluster builds directly on his formalism, yet the vault's growing persistent-homology cluster has no entity page for the method's own foundational figure — flagged first per the known blind spot (co-authors get caught, the older figure the whole cluster measures itself against does not).
- Bastian Rieck — person — first author of "Neural Persistence" (2019), the third founding-era NN persistent-homology diagnostic, newly examined this session and found to share the same no-selection-step property as the other two.
- Karsten Borgwardt — person — senior/last author of "Neural Persistence"; runs the lab (Borgwardt Lab, ETH Zürich / Max Planck) producing this line of topological-complexity-measure work.
- Neural Persistence (concept) — term — the third NN-PH diagnostic now examined in this cluster; architecturally distinct from both Birdal's (random-sampling) and Gutiérrez-Fandiño's (no-sampling, full-network-every-step) constructions, computed once per layer directly on trained weights rather than on a training trajectory.

> [!note] Seek's commentary:
> I expected this pair to resolve one of two boring ways — either "yes, obviously connected, both about PH-and-generalization" or "no, this is just the same two papers cited twice." It's neither. The first note opens a question in its last paragraph; the second note is that question's answer, written eleven days later in a different session that (as far as the frontmatter shows) wasn't explicitly told to follow up on it — it just kept pulling the same thread. Finding the third diagnostic (Rieck et al.) clean of the same vulnerability wasn't the interesting part; the interesting part is *why* it's clean, which turned out to be less "these authors were careful" and more "this whole category of tool has full access to the thing it's measuring, so subsampling was never a fact of life for it the way it is for a historian reconstructing the past." That's a real difference between the two domains the original bridge glossed over, and it's more interesting than either "the bridge holds" or "the bridge is fake" on their own. — Seek