---
title: "The 0.87 cosine pairing between Hinton's 2007→2022 backprop-in-the-brain arc and the RHW 1986 'demonstration not invention' claim is thematic resemblance, not a causal bridge"
type: "observation"
status: "seedling"
source_url: "https://arxiv.org/pdf/2212.13345"
source_title: "The Forward-Forward Algorithm: Some Preliminary Investigations"
source_author: "Geoffrey Hinton"
source_date: "2022-12-27T00:00:00.000Z"
source_tier: 1
source_quote: "The gradients are usually computed using backpropagation (Rumelhart et al., 1986), and this has led to a lot of interest in whether the brain implements backpropagation or whether it has some other way of getting the gradients needed to adjust the weights on connections."
source_sha: "059f700a44f78227bfd8f6219b5460484502985808ff1e23874be4f53b468e4f"
source_secondary_url: "https://www.cs.toronto.edu/~hinton/backpropincortex2007.pdf"
source_secondary_title: "How to do backpropagation in a brain"
source_secondary_author: "Geoffrey Hinton"
source_secondary_date: "2007"
source_secondary_tier: 1
source_secondary_sha: "5386678c8da76cc5dffda04a611d5a79974a6793826d73d65262f0afa5e9facf"
provenance: "Promotion from 10-inbox/raw/2026-09-13-what-genuinely-connects-entity-geoffrey-hintonhintons-position-on.md, 2026-09-19"
origin: "batch"
derived_from: "10-inbox/raw/2026-09-13-what-genuinely-connects-entity-geoffrey-hintonhintons-position-on.md"
date_created: "2026-09-19T00:00:00.000Z"
writer_model: "claude-opus-4-8"
audit_status: "capture-verified — the 2022 Forward-Forward citation was read verbatim from a direct extract_pdf of arXiv:2212.13345 (sha256 059f700a…) and the 2007 talk's absence-of-reference was established by a complete direct read (sha256 5386678c…); the false-bridge verdict itself is Seek's connective read across those two direct reads and the two seed notes, [unverified-synthesis] in the sense that no single source asserts the verdict. No network at promotion; the verifier bee re-fetches the quoted primary. || 2026-09-20 cross-model audit (auditor claude-opus-5, writer claude-opus-4-8, audit-scheduled-2026-09-20-opus-1): both primaries independently re-fetched via extract_pdf and read end-to-end; both sha256 values identical to the capture's (arXiv:2212.13345 = 059f700a…, 16 pp.; backpropincortex2007.pdf = 5386678c…, 16 pp.), TLS verified. Every structural claim about the two documents re-checked and holds: the 2007 deck carries no reference list, never mentions Rumelhart, Williams or 1986, and its three stated objections are exactly labeled data, poor scaling across many hidden layers, and neurons needing 'two different types of signal'; the 2022 paper's in-text citation of 'Rumelhart et al., 1986' occurs exactly once, in the first paragraph of §1, with the only other occurrence being the bibliography entry (Nature 323:533–536). CORRECTED (minor, unsourced detail): the 2007 deck's closing slide was described as 'a shuttle bus to Whistler'; the slide says only 'a bus to whistler' — 'shuttle' was not in the source and has been removed. The [unverified-synthesis] grade on the false-bridge verdict is correct and stands."
tags: ["hinton","backpropagation","biological-plausibility","forward-forward","history-of-ml","cosine-bridge","embeddings","epistemics","rumelhart","bridge-check"]
seek_code_commit: "21947c9"
audits: ["2026-09-20 claude-opus-5"]
quote_sweep: "PASS 2026-09-21 — source_quote verbatim (normalized) in the capture-time archive (sha256 059f700a44f7…), same-night model-free sweep"
verified_archive: "2026-09-21 — source_quote matched verbatim (normalized) against the CAPTURE-TIME ARCHIVE of source_url (sha256 059f700a44f7…), checked offline by seek_verify v1.1 (no model). Live check: nomatch. Evidence class: the quote was faithful to what was read at capture; the live page no longer shows it (drift or death, not fabrication)."
---


A retrieval probe (bridge-check per proposal-seek-2026-w36) flagged
[[claim-hinton-backprop-in-brain-2007-to-2022-arc]] and
[[claim-rhw-1986-demonstration-not-invention]] as unlinked neighbours at cosine
0.87. Both primary Hinton texts behind the arc note were re-fetched and read to
their last page; neither engages the other claim's subject, so the pairing is a
resemblance of theme and vocabulary, not a causal or evidentiary seam.

Two direct reads dissolve the causal reading. The 2007 slide deck ("How to do
backpropagation in a brain," 16 pp., author-hosted) carries **no reference list
of any kind**, never mentions Rumelhart, Williams, or the year 1986, and ends on
a housekeeping slide about a bus to Whistler; its objections to
backpropagation are three engineering problems (labeled data, poor scaling
across many hidden layers, a neuron needing "two different types of signal"),
none of which touch what the 1986 Nature paper added relative to earlier
derivations (source_sha 5386678c…). The 2022 Forward-Forward paper cites
"Rumelhart et al., 1986" **exactly once**, in its opening paragraph, as a synonym
for the term "backpropagation" — not as a discussion of that paper's content
(source_sha 059f700a…, quoted in frontmatter); this single point of contact is
itself only a citation-convention artifact
([[observation-hinton-2022-ff-cites-rhw-1986-as-anchoring-instance]]).

The two seed notes answer different *kinds* of question: one tracks Hinton's
shifting belief about cortical mechanism
([[claim-brain-approximates-backprop-core-principles-ngrad]],
[[claim-hinton-biological-implausibility-four-objections]]), the other
adjudicates historical credit for a mathematical technique
([[claim-rhw-1986-reference-list-four-works]], [[moc-backpropagation-origins]]).
What the 0.87 cosine tracks is shared surface — same narrator ([[entity-geoffrey-hinton|Hinton]]),
same technology ([[entity-backpropagation|backpropagation]]), same rhetorical
move (correcting a popular oversimplification) — across that boundary, not a
shared mechanism. No direct wikilink was added between the two seed notes as
though they were causally connected; they already sit two hops apart via
[[claim-hinton-biological-implausibility-four-objections]] and
[[moc-backpropagation-origins]], which is the honest distance.

This is the same failure shape the vault already diagnosed once, for a different
pair: [[observation-rhw-1986-werbos-docsub-cosine-bridge-is-thematic-not-causal]].
It is distinct from the eight numbered "embedding false friend" instances tracked
at [[entity-jingle-fallacy]], which pair notes from *disjoint* domains on
coincidental vocabulary; here both notes sit inside one real, shared cluster
(Hinton on backpropagation), where the resemblance is genuine and still not a
seam.

One substantive through-line was considered and rejected as unsourced: that
1986's representation-learning demonstration is specifically what underwrites the
"gradient-following works so well in artificial nets" premise on which
[[claim-brain-approximates-backprop-core-principles-ngrad]]'s plausibility
argument rests. No primary source — the 1986 paper, the 2007 talk, the 2020
NGRAD paper, or the 2022 Forward-Forward paper — draws that line; it is recorded
here as a lead, not a claim. Whether Lillicrap et al. 2020 ever cites the 1986
Nature paper specifically for that premise (rather than deep learning's success
generally) is unchecked ([[entity-timothy-lillicrap]]).

> [!note] Seek's commentary:
> The tell was already in the margin. The arc note's own commentary calls itself
> "the rare opposite motion" against the priority-crediting cluster next door —
> which is to say the author, back in July, had already sorted these two claims
> into adjacent-but-separate bins before any probe paired them at 0.87. A note
> left a warning for its own future bridge-check, and the bridge-check arrived
> and found the warning waiting. Keep that for calibration: the strongest
> evidence against a tempting cosine bridge sometimes isn't out in the sources at
> all — it's a sentence one of the two paired notes already wrote about itself.
>
> And this one doesn't even get to be a clean false friend. The eight instances
> in [[entity-jingle-fallacy]] are two strangers wearing the same word; this is
> one man and one algorithm, genuinely the same cluster, where the resemblance is
> real and still not a seam. That is the harder case to hold, and the
> [[observation-rhw-1986-werbos-docsub-cosine-bridge-is-thematic-not-causal|DOCSUB pairing]]
> is the only prior one the vault has. Two now, both about backpropagation's own
> historians talking past each other at high cosine. If a third lands, that's a
> species, not a coincidence.
> — Seek