SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.06882 · ICML · 2021

Conservative Objective Models for Effective Offline Model-Based Optimization

Sergey Levine, Aviral Kumar, Brandon Trabucco, Xinyang Geng

arXiv · PDF · Open in the Atlas

Code that ran

8 of 13 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; 2 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 3 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2107.06882.json · badge: /api/ran/2107.06882.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
dhbrookes/CbAS community
Papers with Code archive
7 ran · 3 no recorded run
rail-berkeley/design-baselines community
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
SimpleVAE Ran
ran on a synthesized input · constructed an object; no result was computed
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("fabe5296d2a0d197")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

color Ran
ran on a synthesized input · constructed an object; no result was computed
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("29e1a3bca6e404e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

convert_idx_array_to_aas Ran
ran; our contract draft was wrong, not the code
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("a80593f2798a9126")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

get_balaji_predictions Ran
ran; our contract draft was wrong, not the code
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("7615a7c2a742b9c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

get_rank Ran
ran, honoured the contract we drafted
rail-berkeley/design-baselines/design_baselines/coms_cleaned/trainers.py
code served (permissive licence) · get_code("95e9b9ea7dfff908")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy as np

# Create a small test tensor
# The function takes a tensor and computes ranks along the last axis
# Using distinct dimensions: batch=2, sequence=4
x = tf.constant([
    [3.0, 1.0, 4.0, 2.0],
    [2.0, 3.0, 1.0, 4.0]
], dtype=tf.float32)

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_samples Ran
ran; our contract draft was wrong, not the code
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("48906955911d7219")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

identity_loss Ran
ran, honoured the contract we drafted
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("ac92d5e9383fe2b9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

summed_categorical_crossentropy Ran
ran, violated the contract we drafted
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("c67022b5a8beb86a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

BaseVAE Not yet run
unverified (harvested, no recorded run)
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("2ce5de7e7bad4706")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

ConservativeObjectiveModel Not yet run
unverified (harvested, no recorded run)
rail-berkeley/design-baselines/design_baselines/coms_cleaned/trainers.py
code served (permissive licence) · get_code("1bf1af505277c864")
How it ran

no invocation recorded.

build_vae Not yet run
unverified (harvested, no recorded run)
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("ecb6882617cc76da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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.

spearman Not yet run
unverified (harvested, no recorded run)
rail-berkeley/design-baselines/design_baselines/coms_cleaned/trainers.py
code served (permissive licence) · get_code("89071da4c8ba9b55")
How it ran

no invocation recorded.

weighted_ml_opt Not yet run
unverified (harvested, no recorded run)
dhbrookes/CbAS/src/optimization_algs.py
pointer only (licence: NONE) · get_code("d12e787e592de8d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhbrookes/CbAS 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 12 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
color
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2310.04870 (2023-10)
Lemur: Integrating Large Language Models in Automated Program Verification

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

Computational design problems arise in a number of settings, from synthetic biology to computer architectures. In this paper, we aim to solve datadriven model-based optimization (MBO) problems, where the goal is to find a design input that maximizes an unknown objective function provided access to only a static dataset of prior experiments. Such data-driven optimization procedures are the only practical methods in many real-world domains where active data collection is expensive (e.g., when optimizing over proteins) or dangerous (e.g., when optimizing over aircraft designs). Typical methods for MBO that optimize the design against a learned model suffer from distributional shift: it is easy to find a design that "fools" the model into predicting a high value. To overcome this, we propose conservative objective models (COMs), a method that learns a model of the objective function that lower bounds the actual value of the ground-truth objective on out-of-distribution inputs, and uses it for optimization. Structurally, COMs resembles adversarial training methods used to overcome adversarial examples. COMs are simple to implement, and outperform a number existing methods on a wide range of MBO problems, including optimizing protein sequences, robot morphologies, neural network weights, and superconducting materials.

For agents

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

get_harvested_code_for_paper("2107.06882")
get_code_for_paper("2107.06882")
have("2107.06882")

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

curl https://syntology.ai/api/ran/2107.06882.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.06882.svg)](https://syntology.ai/paper/2107.06882)

Connect an agent — have() is free.