SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.10786 · NeurIPS · 2022

Generative Pretraining for Black-box Optimization

Aditya Grover, Satvik Mashkaria, Siddarth Krishnamoorthy

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2206.10786.json · badge: /api/ran/2206.10786.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
siddarthk97/bonet canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
brandontrabucco/design-baselines application (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Block Ran
ran on a synthesized input · constructed an object; no result was computed
siddarthk97/bonet/mingpt/model_discrete.py
pointer only (licence: NONE) · get_code("45a0c4f2576bdfcc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siddarthk97/bonet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CausalSelfAttention Ran
ran on a synthesized input · constructed an object; no result was computed
siddarthk97/bonet/mingpt/model_discrete.py
pointer only (licence: NONE) · get_code("774a4c768efc371a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siddarthk97/bonet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DiscreteGenerator Not yet run
unverified (harvested, no recorded run)
brandontrabucco/design-baselines/design_baselines/mins/nets.py
code served (permissive licence) · get_code("b167c9ef678422ae")
How it ran

no invocation recorded.

GPTDiscrete Not yet run
unverified (harvested, no recorded run)
siddarthk97/bonet/mingpt/model_discrete.py
pointer only (licence: NONE) · get_code("df722aab09c8dc16")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siddarthk97/bonet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
Block
brick of this paper's assembly: model
1 other paper
1 later
2305.04073 (2023-05)
Explaining RL Decisions with Trajectories

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Many problems in science and engineering involve optimizing an expensive black-box function over a high-dimensional space. In the offline black-box optimization (BBO) setting, we assume access to a fixed, offline dataset for pretraining and a small budget for online function evaluations. Prior approaches seek to utilize the offline data to approximate the function or its inverse but are not sufficiently accurate far from the data distribution. We propose BONET, a generative framework for pretraining a novel modelbased optimizer using offline datasets. In BONET, we train an autoregressive model on fixed-length trajectories derived from an offline dataset. We design a sampling strategy to synthesize trajectories from offline data using a simple heuristic of rolling out monotonic transitions from lowfidelity to high-fidelity samples. Empirically, we instantiate BONET using a causally masked Transformer (Radford et al., 2019) and evaluate it on Design-Bench (Trabucco et al., 2022), where we rank the best on average, outperforming stateof-the-art baselines. Fortunately, for many such black-box optimization (BBO)

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.10786")
get_code_for_paper("2206.10786")
have("2206.10786")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2206.10786.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2206.10786.svg)](https://syntology.ai/paper/2206.10786)

Connect an agent — have() is free.