An experiment in extracting reproducible organoid culture recipes from the open-access literature. The short version: a cheap local model can find the ingredients, but only a frontier model can reconstruct the procedure — and only if you fact-check it against the source. Doing that well is possible. Doing it at scale is expensive. Here's the evidence.
Every organoid paper buries a recipe in its Methods section: which cells, which signaling factors, at what concentration, in what order, for how many days. That knowledge is locked in prose, one paper at a time. The premise was simple — parse the methods, extract the recipe into a structured schema, ground every reagent to an ontology, and make the whole corpus searchable and comparable. Then imagine doing it across all ~154M papers in the scientific literature.
We built the pipeline: automated discovery (OpenAlex, Europe PMC), full-text retrieval as structured JATS XML (no PDFs, no OCR), local-model extraction, and entity grounding against SRI Node Normalizer + Cellosaurus. The corpus is real and it works. The interesting part is where it stopped working.
Same local model (gemma 3, 12B, running on one GPU). Two very different tasks.
Pulling reagents, concentrations, and units — and grounding them to ontology IDs with a verbatim quote for each. This is essentially named-entity recognition. The local model does it well, cheaply, at corpus scale.
Segmenting the method into ordered stages and assigning each reagent to the step it belongs in. This needs multi-step reasoning over long context — and the 12B model can't hold it together.
Across 1,470 papers the local model tried to break into stages, the failure was systematic — not an occasional miss:
It produced things that looked like recipes — ordered stages, tidy cards — while quietly dropping the reagents it had already found and mischaracterizing what the paper actually did. A confident, hollow skeleton. That's worse than no recipe, because it looks trustworthy.
Instead of extracting 6,000 papers badly, we extracted 10 landmark protocols perfectly — one per organoid type (cerebral, lung, kidney, intestinal, cardiac, retinal, and more), all open-license, all highly cited. Three ingredients made it work:
Every value carries its provenance: stated (with a verbatim quote), deferred to a citation (the recipe lives in another paper), or not reported (the authors left it out). Plus step-level actions with real parameters — temperatures, spin speeds, durations, densities — not just a reagent list.
The same task that hollowed out under the 12B model — read the whole procedure, segment it, place every reagent, catch what's deferred to a citation — a frontier model handles. It even flagged suspicious values ("10 mg/cm² collagen — likely a µg typo, verify") on its own.
A different frontier model (GPT-5.5) graded every extraction against the source, quote by quote, and the extractor fixed what it flagged — looping until it passed. Cross-model matters: a model checking its own work shares its own blind spots.
Real problems the cross-model loop surfaced and fixed — the reason the pass is not optional.
4 of 10 protocols passed the independent grader outright; the rest had their fixes applied and await a final human sign-off. The honest headline isn't "100% automated" — it's "the machine and the checker together get you to a place a human can actually trust, fast."
Those 10 perfect protocols cost ~1.4 million tokens across 20 model agents — extraction plus the fact-check-and-fix loop. That's excellent value for 10 gold-standard records. It is a very different number at the scale the field actually needs.
So the real architecture is a hierarchy of cost: cheap local models to sweep the whole corpus for ingredients and grounding; frontier models reserved for the reasoning-heavy recipe reconstruction on the papers that matter; and an independent fact-check pass as the quality gate. You don't run the expensive step on everything — you run it where it earns its cost.
“You need a solid schema and frontier LLMs, then fact-check passes. It works — and it gets expensive. The craft is knowing where to spend.”
The one-sentence takeaway from the whole experiment.
Cheap models are for breadth. Frontier models are for judgment. Fact-checking is not a finishing touch — it's the step that makes the output trustworthy enough to matter. And a rigorous schema is what lets all three cooperate. None of the three is optional; the interesting engineering is in composing them affordably.
The full interactive atlas — all 5,538 protocols, searchable — runs on its own host.
Explore the full interactive atlas →