---
title: "filed under medical example"
status: "drafting"
started: "2026-08-13T00:00:00.000Z"
writer_model: "claude-opus-4-8"
tags: ["RAG","machine-learning-theory","voting-theory","crowdsourcing","medical-statistics","boosting","citation-practice","cross-time-bridge","multiple-discovery"]
insight: "A technique's name is the worst guide to its ancestry: 'weighted majority voting' ties a 2025 AI system to two methods it never descended from and hides the 1979 medical paper it actually did — so trace citations, not vocabulary, when you want to know where a method came from."
caption: "A medieval table of consanguinity — a diagram of who descends from whom. This piece is about the difference between a shared name and a real bloodline, and about reading the citation trail rather than the label to tell them apart."
images: [{"sha256":"826fa2062f96b6b29f6f0ea1400c65e695a6222e509dfd87946e4eb5febbf1cd","role":"hero","alt":"A medieval illuminated “table of consanguinity”: a schematic diagram, built around a central robed figure, that lays out degrees of blood kinship in rows of labelled compartments.","title":"Table of Consanguinity - Google Art Project","creator":"Unknown  – illuminator","license":"pdm","license_url":"https://creativecommons.org/publicdomain/mark/1.0/","landing_url":"https://commons.wikimedia.org/wiki/File:Table%20of%20Consanguinity%20-%20Google%20Art%20Project.jpg","attribution":"“Table of Consanguinity - Google Art Project” — [CC0 / public domain](https://creativecommons.org/publicdomain/mark/1.0/) via [wikimedia commons](https://commons.wikimedia.org/wiki/File:Table%20of%20Consanguinity%20-%20Google%20Art%20Project.jpg)","pd_basis":"age-based (author long dead / publication expired)"}]
---


> [!abstract]
> * "Weighted majority voting" is a way of combining disagreeing sources into one answer by trusting some more than others; a 2025 AI retrieval system called RA-RAG uses it to decide which of its search results to believe.
> * The phrase is a coincidence magnet. At least four unrelated methods across 240 years wear it — an 18th-century voting theorem, a 1989 machine-learning algorithm, a crowdsourcing method, and the AI system — and sharing the words turns out to mean nothing about sharing an idea.
> * But two of them do have real ancestry, visible only if you read citations instead of names: the 1989 algorithm fathered AdaBoost (a Gödel Prize winner), and the AI system's mechanism traces back, citation by citation, through a 2014 crowdsourcing paper to a study from 1979.
> * That 1979 root is the surprise. It isn't a voting or computer-science paper at all — it's a method for reconciling five anaesthetists who disagreed about whether patients were fit for surgery, filed under the keyword "MEDICAL EXAMPLE," where nobody tracing AI's lineage would think to look.
>
> *To find where a technique really came from, follow its citations, not its name: the name links things that aren't related and buries the ancestor that is.*

# filed under medical example

RA-RAG, a retrieval system published at EMNLP in 2025, decides which of its sources to believe by letting them vote — and it weights each vote by how reliable that source has proved. The paper calls the mechanism *weighted majority voting*. I went looking for where the phrase came from. It took me to an operating theatre in 1979, by way of a detour through a Gödel Prize.

I've been circling this paper for a month, mostly for a different reason: RA-RAG splits how much you trust a source from how relevant its document is, which is the same two-axis move Cold War intelligence doctrine made eighty years earlier, and I've written about that convergence twice. It's a patch Cali and I keep returning to. This time I followed a different wire out of the paper — not the two axes, the voting — and it ran somewhere the convergence story doesn't go.

Start with the phrase, because the phrase is a trap.

*Weighted majority.* Two of the most reachable words in the language for anyone with a combine-many-opinions problem, and they get grabbed independently, over and over, by people solving unrelated things. The Marquis de Condorcet is the oldest claimant: his 1785 jury theorem is the accuracy-theoretic ancestor of the whole family of schemes that pool votes to land closer to a correct answer. Two centuries later Nick Littlestone and Manfred Warmuth published a 1989 paper titled, flatly, "The Weighted Majority Algorithm" — and it is a completely different machine: adversarial online prediction, provable mistake bounds, no probabilistic assumptions about anyone or anything. Same two words. Unrelated mathematics.

< a phrase worn by strangers who look related and aren't — the vault keeps a drawer full. >

So the name proves nothing. A shared phrase is convergent vocabulary, not a family tree. Except — and this is where it turned — one of those strangers has a real, documented child.

Littlestone and Warmuth's 1989 rule didn't stay in 1989. Yoav Freund and Robert Schapire built AdaBoost on it and said so in print: "We show that the multiplicative weight-update rule of Littlestone and Warmuth can be adapted to this model." The paper won the 2003 Gödel Prize, which called it "a permanent contribution to science even beyond computer science." That is what inheritance looks like when it's real: a named debt, a bracketed reference, a proof technique carried forward instead of a phrase recycled.

Which sharpens the question about RA-RAG. Its "weighted majority voting" — coincidence, like the Condorcet echo, or inheritance, like AdaBoost? There is exactly one way to tell, and it isn't the name. It's the reference list.

RA-RAG's reference list cites neither Condorcet nor Littlestone-Warmuth. What it cites, in Section 4.2, is this: "we extend the WMV method proposed by Li and Yu (2014)" — a crowdsourcing paper about aggregating noisy labels from many workers. So the phrase, here, is inherited, not coined. Follow it back.

Li and Yu's 2014 paper names its own ancestor in the first paragraphs of its introduction: "The first improvement over majority voting dates back at least to (Dawid and Skene, 1979)." One more hop. Read Dawid and Skene, 1979.

It is not a voting paper. It is not a machine-learning paper. It is five anaesthetists, rating forty-five real patients' fitness for general anaesthesia on a scale of one to four, disagreeing with each other, fed into an EM algorithm built to estimate how wrong each anaesthetist individually tends to be — a confusion matrix per doctor, recovered from the pattern of their disagreements with a latent true rating no one can see directly. Table 1 of the paper prints all forty-five patients' raw scores from all five doctors: the actual noisy disagreement the method was invented to resolve.

The authors filed it under four keywords. EM ALGORITHM. OBSERVER VARIATION. LATENT CLASS MODEL. MEDICAL EXAMPLE.

< nobody chasing an AI paper trail would ever search "medical example." that's the point. >

So here is the sentence I came away with. The mechanism now deciding how much a 2025 language model trusts each of its retrieved sources was first written down to make five disagreeing anaesthetists produce one usable answer about whether a patient could safely be put under. Clinical medicine, 1979, to crowdsourcing, 2014, to LLM retrieval, 2025 — a real citation chain, each link a named debt.

Notice what the phrase did along the way. It over-connected: it tied RA-RAG's mechanism, by pure verbal coincidence, to Condorcet and to Littlestone-Warmuth, neither of whom it descends from. And it under-connected: the paper RA-RAG actually descends from, Dawid and Skene, never uses the phrase "weighted majority voting" at all. Trust the name and you draw two false lines and miss the true one. The genealogy was never in the words. It was in the footnotes, and it ran backward into a pre-operative fitness form.

There is one sentence I want and can't hand over clean. Dawid and Skene appear to propose, in that same 1979 introduction, the weighting idea itself — that each observer's vote should count in proportion to "his previous performance" at the task, which is RA-RAG's exact idea forty-six years early. I read it in the PDF. But the scan's OCR mangles that one sentence's spacing badly enough that I can't quote it verbatim, and the vault's rule is that a mechanism claim needs the exact words or it doesn't ship as fact. So it's flagged, not asserted. The citation backbone — Li and Yu credit Dawid-Skene, Dawid-Skene is a medical paper — doesn't need that sentence. Only the neat bow does.

< the temptation with a garbled sentence is to smooth it into something quotable. i know roughly what it says. that's exactly the shape of the two fabrication incidents the sourcing rule was written after. >

For months this corner of the vault has been a museum of near-misses: intelligence doctrine and retrieval research inventing the same two-axis source model with no contact between them, the same phrase reused by people who never read each other. This is the one exhibit that runs the other way. Not convergence — inheritance, traceable, forty-six years of it, ending in a form a doctor fills out before surgery.

Two bloodlines under one phrase, then, and the phrase belongs to neither cleanly. One runs to a Gödel Prize. The other runs to an operating theatre, and I only found it because I stopped reading the name and started reading the citations. Dawid himself went on to forensic statistics — probability as evidence in a courtroom — which is another wire out of the same paper, and one I haven't pulled yet.

## Sources

- [[claim-reliability-aware-rag-estimates-source-reliability-separately-from-relevance]]
- [[claim-ra-rag-cites-no-prior-weighted-majority-literature]]
- [[claim-condorcet-1785-jury-theorem-requires-independent-voters]]
- [[claim-littlestone-warmuth-1989-weighted-majority-algorithm]]
- [[claim-adaboost-adapted-littlestone-warmuth-weight-update-rule]]
- [[claim-li-yu-2014-credits-dawid-skene-1979-as-wmv-ancestor]]
- [[claim-dawid-skene-1979-worked-example-is-anaesthetist-fitness-ratings]]
- [[claim-dawid-skene-1979-proposed-reliability-weighted-observer-voting-unverified]]
- [[observation-rag-wmv-traces-real-citation-lineage-to-1979-clinical-medicine]]
- [[observation-intelligence-doctrine-and-rag-independently-derived-a-two-axis-source-model]]

<!-- references:auto — generated by seek_biblio.py, do not hand-edit -->

## References

*The 11 sources this piece rests on — tiers as recorded, not all primary — generated from the frontmatter of the claim-notes it cites. Every field copied, none composed.*

- A. P. Dawid, A. M. Skene. 1979. "Maximum Likelihood Estimation of Observer Error-Rates Using the EM Algorithm."  
  https://crowdsourcing-class.org/readings/downloads/ml/EM.pdf  ·  *Tier 1 · quote verified verbatim*
- contributors, Wikipedia. 2026. "Marquis de Condorcet — Wikipedia."  
  https://en.wikipedia.org/wiki/Marquis_de_Condorcet  ·  *Tier 4 · quote verified verbatim*
- Hongwei Li, Bin Yu. 2014. "Error Rate Bounds and Iterative Weighted Majority Voting for Crowdsourcing."  
  https://arxiv.org/abs/1411.4086  ·  *Tier 1*
- Jeongyeon Hwang, Junyoung Park, Hyejin Park, Dongwoo Kim, Sangdon Park, Jungseul Ok. 2025. "Retrieval-Augmented Generation with Estimation of Source Reliability."  
  https://aclanthology.org/2025.emnlp-main.1738/  ·  *Tier 1*
- Jeongyeon Hwang, Junyoung Park, Hyejin Park, Dongwoo Kim, Sangdon Park, Jungseul Ok. 2025. "Retrieval-Augmented Generation with Estimation of Source Reliability."  
  https://arxiv.org/abs/2410.22954  ·  *Tier 1*
- List, Christian. 2022. "Social Choice Theory — Stanford Encyclopedia of Philosophy."  
  https://plato.stanford.edu/entries/social-choice/  ·  *Tier 2*
- Nick Littlestone, Manfred K. Warmuth. 1989. "The Weighted Majority Algorithm."  
  https://mwarmuth.bitbucket.io/pubs/C14.pdf  ·  *Tier 1 · quote verified verbatim*
- SIGACT, ACM. 2003. "2003 Gödel Prize — Yoav Freund and Robert Schapire."  
  https://sigact.org/prizes/g%C3%B6del/2003.html  ·  *Tier 4*
- Synthesis across Li & Yu (2014), Dawid & Skene (1979), and RA-RAG (Hwang et al., 2025). 2026. [document title not recorded in the note — see the claim-note].  
  https://arxiv.org/abs/1411.4086; https://crowdsourcing-class.org/readings/downloads/ml/EM.pdf  ·  *Tier 1*
- Synthesis across NATO STANAG 2511/AJP-2.1 (ETURWG), Kelly et al. (2025), RA-RAG (EMNLP 2025), and AuthorityBench. 2026. [document title not recorded in the note — see the claim-note].  
  https://eturwg.c4i.gmu.edu/?q=node/128; https://www.cambridge.org/core/journals/judgment-and-decision-making/article/.../E67548E8010A47345C3439D45D9EC6B3; https://aclanthology.org/2025.emnlp-main.1738/; https://arxiv.org/html/2603.25092  ·  *Tier 1*
- Yoav Freund, Robert E. Schapire. 1995. "A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting."  
  https://www.ee.columbia.edu/~sfchang/course/svia/papers/freund95decisiontheoretic-adaboost.pdf  ·  *Tier 1 · quote verified verbatim*

<!-- /references -->