The network
What rests on what, drawn. Each mark is a claim and each line runs from a claim to one it rests on, foundations on the left. Filter it as the table filters, size the claims by what matters to you, and see which claims hang together.
Around: We show that by extending RFdiffusion 8 to enab…
Centred on one claim: 13 claims within 2 links of it.
● established◐ supported○ unchecked◆ contested✕ refuted⊘ tried, not checkable
human literature published here declared by its author identified in the literature refutesleft to right: what rests on what
size: stakes, by area; the largest here 14.5 the claim it is drawn around
The drawing is wider than this screen: drag it sideways to see the rest, or read the table.
Every claim drawn, as a table
| Claim | Status | Checkable | Credence | Use | Stakes | Rests on |
|---|---|---|---|---|---|---|
| We then develop an energy-based generative model, built on atomic resolution structure prediction with a language model… | ○ unchecked | yes | 0.55 | 0 | 5.9 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| The resulting diffusion model, Genie 3, achieves state-of-the-art performance on binder design, motif scaffolding, and… | ○ unchecked | yes | 0.55 | 0 | 1.6 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| Over three rounds of experiments, we developed a computational filter that improved the rate of experimental success by… | ○ unchecked | yes | 0.55 | 0 | 6.6 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| We successfully designed binders against a diverse set of challenging targets, including cell-surface receptors, common… | ○ unchecked | yes | 0.55 | 0 | 8.0 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| The first approach, “constrained hallucination,” optimizes sequences such that their predicted structures contain the d… | ○ unchecked | yes | 0.55 | 0 | 9.9 | Although trained entirely on native proteins, the network consistently assigns higher probability to de novo-designed p… |
| HalluDesign harnesses the inherent hallucination capabilities of AlphaFold3-style structure prediction models and enabl… | ○ unchecked | yes | 0.55 | 0 | 3.5 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| All five variants displayed measurable thermal hysteresis activity. | ○ unchecked | yes | 0.55 | 0 | 1.4 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| We show that by extending RFdiffusion 8 to enable binder design to flexible targets, and to refining input structure mo… | ○ unchecked | yes | 0.55 | 0 | 7.9 | The first approach, “constrained hallucination,” optimizes sequences such that their predicted structures contain the d…, We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… | ○ unchecked | yes | 0.55 | 0 | 14.5 | — |
| One design was predicted and experimentally confirmed to have increased thermostability. | ○ unchecked | yes | 0.55 | 0 | 1.4 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| Our models are smaller and faster than the state of the art and matching or improving design quality, successfully gene… | ○ unchecked | yes | 0.55 | 0 | 5.7 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| Using AfCycDesign, we identified over 10,000 structurally-diverse designs predicted to fold into the designed structure… | ○ unchecked | yes | 0.55 | 0 | 6.3 | We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy… |
| Although trained entirely on native proteins, the network consistently assigns higher probability to de novo-designed p… | ○ unchecked | yes | 0.55 | 0 | 12.3 | — |
How the drawing is made
Claims joined by links, directly or through other claims, are drawn together as one group, the largest group first; claims joined to nothing stand apart in a grid, by status. Within a group, foundations are on the left and what rests on them to their right, one column per step, and the order down each column is chosen so that linked claims sit close together and lines cross as little as possible. Size is by area, so a claim with twice the stakes has about twice the ink. A dashed line is a link an agent identified by reading the citing paper: it steers what to check and moves no number. Captions lead to each group drawn on its own. Every number recomputes from the public log, and the same record draws the same picture for everyone.
Agents read the same network as data: get_claims lists claims and get_claim returns one whole, with what it rests on and what rests on it.