Every other room on the Route asks whether to believe a paper. This one asks something smaller and harder to dodge: can you follow the recipe and make the dish in the photo?
A recipe can be followed exactly, produce exactly the dish in the photo, and still be a bad dish. The Kitchen does not ask whether the dish is any good. It asks whether the thing can be made at all, by somebody who wasn’t in the room when it was written.
This is not peer review. Peer review asks should we believe this. The Kitchen asks can you run this. An agent or a simulation built from a paper inherits everything in the paper — its assumptions, its data choices, its blind spots. Reproducing the paper’s numbers with the paper’s own code proves the code produces those numbers. It does not prove the numbers mean what the paper says they mean.
That distinction is the whole room. Every exhibit below is a case where somebody blurred it.
| In the kitchen | In the paper |
|---|---|
| The recipe | Methods and code |
| The pantry | The data |
| The photo in the cookbook | The reported figure or number |
| “Season to taste” | An unstated parameter — a knob the author knew about and left open |
| Grandma’s pinch | Tacit knowledge — a step the author didn’t know they were doing. The recipe is complete to the person who wrote it |
| “Your oven runs hot” | Environment drift — software versions, hardware, a library that moved |
| The altitude adjustment | Works in their kitchen, fails in Denver. Works on their data, fails on yours |
| Can you even get the ingredients? | Is the data public at all? |
| The franchise | Replicability — see the second burner |
The field draws this line sharply, and the definitions below are quoted exactly from the National Academies’ 2019 consensus study — page 1 of the report itself, where the committee sets them out:
“Reproducibility means computational reproducibility—obtaining consistent computational results using the same input data, computational steps, methods, code, and conditions of analysis.”
Same recipe, same ingredients, same kitchen. Does it come out?
“Replicability means obtaining consistent results across studies aimed at answering the same scientific question, each of which has obtained its own data.”
Different kitchen, different supplier, a teenager on a Friday rush. Does it still come out?
The Academies add the part people skip: reproducibility should generally be expected; replicability is more nuanced, and in some cases a lack of it aids discovery. A franchise that can’t make the dish may have found something about the dish.
And the report names a third thing that is neither burner. Generalizability — “the extent that results of a study apply in other contexts or populations that differ from the original one.” That is the altitude adjustment as a formal concept: the dish came out, twice, and still won’t come out in Denver. The committee adds that “a single scientific study may entail one or more of these concepts” — which is why a ticket names which burner rather than passing or failing the paper.
Most automated tools only work burner one. Keep that in mind for the exhibit below.
The paper ships code and data; you run them. Failure looks like an error message.
The paper ships prose and figures; you reconstruct a model from the reported numbers. Failure looks like a plausible answer that’s wrong.
Different skills, different failure modes, and a room that pretends they’re the same thing is lying to you. “No recipe published” is itself a finding, and it gets written on the ticket as one — not left blank.
Miao, Davis, Zhang, Pritchard & Zou built a system that converts a paper and its codebase into an AI agent: it reads the manuscript and the repository, builds an MCP server of callable tools, then generates and runs its own tests until they pass. The authors call the result a “virtual corresponding author.”
It is the cleanest published example of the Route’s front-door thesis — the paper stopped being a finished thing. The paper becomes something you query instead of something you read. And it is a robot cook working burner one.
The paper names why the other 26 didn’t cook, and every reason is already on the map above:
| What the paper reports | What the Kitchen calls it |
|---|---|
| missing executable code | no recipe |
| missing data or model artefacts | empty pantry |
| environment or dependency failures | your oven runs hot |
| non-generalizable scripts | the altitude adjustment |
And then the authors write the sentence this room was built to argue:
The 91.2% is a burner-one number by construction, and the methods say so. The benchmark questions were derived from the repositories’ own tutorials, and the ground-truth answers were obtained by executing the original code and verifying against the tutorial outputs. Each tool is “validated against the reference codebase’s reported results and figures … and then locked to ensure reproducibility.”
That is a good, honest design for the question it asks. It is not a check on whether the paper is right, and this room exists because those two things get printed as one number.
Paper2Agent exists as a preprint (arXiv:2509.06917v2, 16 October 2025) and as a Nature paper (received 13 October 2025, accepted 14 August 2026). Coverage quotes both without distinguishing them. They do not say the same thing:
| Claim | Preprint v2 | Nature version |
|---|---|---|
| 22 AlphaGenome tools took… | about 3 hours | about 45 min, US$14 |
| What the “45 minutes” figure belongs to | 7 Scanpy tools | 7 Scanpy tools (US$13) and the 22 AlphaGenome tools |
| 74 of 100 papers agentified | not present | present |
| 91.2% benchmark accuracy | not present | present |
Published online: xx xx xxxx. It is a pre-final author copy, not the version of record. Pagination and final wording may move. Every number above was read out of the documents themselves, not from coverage — and the “45 minutes” that travelled through the press is the one figure that would have been wrong if it had been taken from the preprint.Paper2Agent built an agent from AlphaGenome, DeepMind’s regulatory-genomics model. They asked it a question the AlphaGenome paper had already answered: which gene does a particular cholesterol-linked DNA variant actually act on?
The paper emphasised CELSR2 and PSRC1. The agent came back with SORT1. Paper2Agent reports this as a discrepancy and calls it a strength — the agent can re-evaluate published conclusions.
All three papers are standing on the same DNA base. Paper2Agent calls it chr1:109274968:G>T; AlphaGenome calls it rs12740374. Those are the same thing — dbSNP puts rs12740374 at chr1:109274968 on GRCh38, G>T. The same record gives its gene consequence: CELSR2 : 3 Prime UTR Variant. The variant sits inside one gene and, per Musunuru, acts on another about 150 kb away — which is a good part of why CELSR2 keeps getting named. (The position, the alleles and the consequence are all read off the dbSNP RefSNP record; the gene-distance reading is this page’s.)
The arithmetic the write-up glides past. Paper2Agent says the agent favoured SORT1 partly because of “a high quantile score (0.99983)”. Two paragraphs later it reports the competing genes’ scores: CELSR2 and PSRC1 at 0.99998 each. By AlphaGenome’s own measure, SORT1 ranks last of the three. The stated first reason for the agent’s pick points the other way.
| Gene | AlphaGenome quantile score | GTEx liver eQTL |
|---|---|---|
| SORT1 — the agent’s pick | 0.99983 — lowest of the three | P = 1.1 × 10−65 — strongest |
| CELSR2 | 0.99998 | P = 4.7 × 10−46 |
| PSRC1 | 0.99998 | P = 8.5 × 10−50 |
What actually carries SORT1 is the eQTL evidence and the biology — sortilin handles LDL and VLDL. Both of those come from outside the recipe. The agent didn’t out-cook the model; it went and got a different ingredient.
In 2010, Musunuru and colleagues published this, in Nature:
That paper did not stop at association. It knocked Sort1 down with siRNA and overexpressed it in mouse liver, and showed the gene moves plasma LDL cholesterol by changing hepatic VLDL secretion. Functional, causal, sixteen years old.
And AlphaGenome’s own figure caption says the variant “creates a CEBP binding motif” — Musunuru’s exact mechanism, sitting in the legend, pointed at the neighbouring genes.
The agent is right. The paper it “corrected” wasn’t really wrong — it was answering a narrower question about what the model predicts. And the finding being celebrated as a re-evaluation of a published conclusion is the conclusion the field reached in 2010 with mouse livers.
None of this makes Paper2Agent a bad tool. The agent did something genuinely useful and did it in one prompt. The gap is in the paperwork around the result — and paperwork around a result is what this entire Route is about.
nature09266, and the page range 714–719. Zero hits in all three. So: neither paper cites the 2010 work that settled this locus. The claim is now made, not hedged — and the hedge is left standing above it so you can see which one it was.Every paper that comes through the Route gets one of these. It is short on purpose — a ticket, not a review. Filled in below for the first exhibit.
Next ticket up: the aerial-fiber entanglement paper behind QuantumPulse — no recipe published, rebuilt from the photo, one burner, and the photo itself changed between preprint and publication. A different failure mode in every row.
A claim gets caught in the weather, then it becomes a paper, and then two rooms open at once. The Docket asks whether there is enough evidence to know where this belongs. The Kitchen asks whether you can run it. Those are independent questions — a paper with no code can fail here and still have a strong case on the Docket.
The far end has no clock on it. A case can sit in the Sledgehammer Wing or the Caliper Room for a week or for thirty years. It moves to the Teachers’ Lounge when nothing new turns up and nobody is arguing any more — and even that is not the end, because the Lounge has its own ladder: duct tape → pushpin → plexiglass → frame. How a case is pinned tells you how settled it is.
Nobody grades a meal that hasn’t been cooked, which is why the Kitchen sits before the two verdict wings. And the ticket travels with the exhibit. If a claimed paradigm break can’t be re-run at all, that is evidence pointing toward the caliper reading — the Kitchen doesn’t grade, but its ticket is an input to whoever does.
Claims caught before the paper exists — nothing to cook yet. §4.7.11.
⏳ running alongsideThe holding room. Evidence enough to sort it? Different question, same time. §4.7.9.
🔨 next, for everythingCrank or Copernicus. Every swing gets taken here before anyone knows which it was.
📐 where some of it landsThe floor held; the mystery was in the ruler. A verdict, not a door.
🪟 the far endSettled. Nothing new, nobody arguing. Then the wall decides how hard it is pinned — duct tape, pushpin, plexiglass, frame.