SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10074 · NeurIPS · 2022

Semantic uncertainty intervals for disentangled latent spaces

Phillip Isola, Anastasios Angelopoulos, Stephen Bates, Swami Sankaranarayanan, Yaniv Romano

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 0 failures of our instrument; 0 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/2207.10074.json · badge: /api/ran/2207.10074.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
swamiviv/CLASP marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
HB_mu_plus Ran
ran, honoured the contract we drafted
swamiviv/CLASP/bounds.py
code served (permissive licence) · get_code("3d81a178883b6d80")
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 float, ndim 0, dtype family float, shape () 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 numpy as np
from scipy.stats import binom
from scipy.optimize import brentq

# Set random seed for reproducibility
np.random.seed(0)

# Define valid arguments for HB_mu_plus
muhat = 0.3  # A sample proportion between 0 and 1
n = 100  # Sample size (positive integer)
delta = 0.05  # Confidence level parameter (small positive number)
maxiters = 1000  # Maximum iterations for brentq

ARGS = {
    "muhat": muhat,
    "n": n,
    "delta": delta,
    "maxiters": maxiters
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
bentkus_plus Ran
ran, honoured the contract we drafted
swamiviv/CLASP/bounds.py
code served (permissive licence) · get_code("6164fcc501da6f66")
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 float64, ndim 0, dtype family float, shape () 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 numpy as np
from scipy.stats import binom

# Analyze the function: bentkus_plus(mu, x, n)
# - mu: used in binom.cdf as probability parameter (expects float in [0,1])
# - x: used in np.floor(n * x), expects numeric scalar or array-like
# - n: used in np.floor(n * x) and binom.cdf as number of trials, expects positive int

# Set up small, valid arguments
mu = 0.5  # probability parameter for binomial distribution
x = 0.3   # fraction parameter
n = 20    # number of trials (positive integer)

ARGS = {
    "mu": mu,
    "x": x,
    "n": n,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () 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
h1 Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from aangelopoulos/rcps
pointer only · get_code("86294eacaecc7ea5")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

hoeffding_plus Ran
ran, honoured the contract we drafted
swamiviv/CLASP/bounds.py
code served (permissive licence) · get_code("47b7bbfae0285051")
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 float64, ndim 0, dtype family float, shape () 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 numpy as np

# Analyze the function:
# hoeffding_plus(mu, x, n) takes three parameters:
# - mu: used in np.maximum and h1, appears to be a scalar or array
# - x: used in np.maximum, appears to be a scalar or array
# - n: used as a multiplier, appears to be a scalar

# The function computes: -n * h1(np.maximum(mu, x), mu)
# h1 expects y and mu to be compatible for element-wise operations

# Create valid arguments
mu = 0.5  # scalar probability value between 0 and 1
x = 0.3   # scalar probability value between 0 and 1
n = 100   # scalar count/sample size

ARGS = {
    "mu": mu,
    "x": x,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () 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

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
h1
brick of this paper's assembly: helper
3 other papers
3 dated earlier
2101.02703 (2021-01)
Distribution-Free, Risk-Controlling Prediction Sets
2110.01052 (2021-10)
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
2202.05265 (2022-02)
Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
bentkus_plus
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2202.05265 (2022-02)
Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
hoeffding_plus
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2110.01052 (2021-10)
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control

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

Meaningful uncertainty quantification in computer vision requires reasoning about semantic information-say, the hair color of the person in a photo or the location of a car on the street. To this end, recent breakthroughs in generative modeling allow us to represent semantic information in disentangled latent spaces, but providing uncertainties on the semantic latent variables has remained challenging. In this work, we provide principled uncertainty intervals that are guaranteed to contain the true semantic factors for any underlying generative model. The method does the following: (1) it uses quantile regression to output a heuristic uncertainty interval for each element in the latent space (2) calibrates these uncertainties such that they contain the true value of the latent for a new, unseen input. The endpoints of these calibrated intervals can then be propagated through the generator to produce interpretable uncertainty visualizations for each semantic factor. This technique reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in inverse problems like image super-resolution and image completion. Code and demos can be found on our project page.

For agents

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

get_harvested_code_for_paper("2207.10074")
get_code_for_paper("2207.10074")
have("2207.10074")

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

curl https://syntology.ai/api/ran/2207.10074.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.10074.svg)](https://syntology.ai/paper/2207.10074)

Connect an agent — have() is free.