SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.11853 · NeurIPS · 2021

Credal Self-Supervised Learning

Eyke Hüllermeier, Julian Lienen

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure 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/2106.11853.json · badge: /api/ran/2106.11853.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
julilien/CSSL canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
julilien/cssl canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_ece Ran
ran on a synthesized input
julilien/CSSL/cssl_utils.py
code served (permissive licence) · get_code("a0243f8f110dfcf2")
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; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

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

# Create small dummy data for testing calculate_ece
batch_size = 10
num_classes = 4

# predicted: probabilistic predictions (batch_size x num_classes)
# Should be probability-like values (between 0 and 1, summing to ~1 per row)
predicted = np.array([
    [0.7, 0.1, 0.1, 0.1],
    [0.2, 0.6, 0.1, 0.1],
    [0.1, 0.1, 0.7, 0.1],
    [0.1, 0.1, 0.1, 0.7],
    [0.6, 0.2, 0.1, 0.1],
    [0.3, 0.3, 0.2, 0.2],
    [0.1, 0.8, 0.05, 0.05],
    [0.25, 0.25, 0.25, 0.25],
    [0.5, 0.3, 0.1, 0.1],
    [0.1, 0.1, 0.1, 0.7],
], dtype=np.float32)

# labels: hard labels (classes) - integers from 0 to num_classes-1
labels = np.array([0, 1, 2, 3, 0, 1, 1, 2, 0, 3], dtype=np.int32)

# num_bins: number of bins for ECE discretization
num_bins = 15

ARGS = {
    "predicted": predicted,
    "labels": labels,
    "num_bins": num_bins,
}
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 — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
summary_dict Ran
ran; our contract draft was wrong, not the code
julilien/cssl/scripts/extract_ece.py
code served (permissive licence) · get_code("043a02598e0288df")
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) and returned dict. The image it ran in was not recorded. If your copy returns the same type 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

# The function takes 'accuracies' which is used with:
# - np.median(accuracies[-x:]) for x in [1, 10, 20, 50]
# This means it needs to be indexable and have at least 50 elements
# to avoid issues with the slicing

accuracies = np.array([0.85, 0.87, 0.86, 0.88, 0.89, 0.84, 0.90, 0.91, 0.85, 0.86,
                       0.87, 0.88, 0.89, 0.90, 0.91, 0.85, 0.86, 0.87, 0.88, 0.89,
                       0.90, 0.91, 0.85, 0.86, 0.87, 0.88, 0.89, 0.90, 0.91, 0.85,
                       0.86, 0.87, 0.88, 0.89, 0.90, 0.91, 0.85, 0.86, 0.87, 0.88,
                       0.89, 0.90, 0.91, 0.85, 0.86, 0.87, 0.88, 0.89, 0.90, 0.91])

ARGS = {
    'accuracies': accuracies
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 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
summary_dict 1 other paper
1 dated earlier
1911.09785 (2019-11)
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

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

Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency regularization, pseudo-labeling has shown promising performance in various domains, for example in computer vision. To account for the hypothetical nature of the pseudolabels, these are commonly provided in the form of probability distributions. Still, one may argue that even a probability distribution represents an excessive level of informedness, as it suggests that the learner precisely knows the ground-truth conditional probabilities. In our approach, we therefore allow the learner to label instances in the form of credal sets, that is, sets of (candidate) probability distributions. Thanks to this increased expressiveness, the learner is able to represent uncertainty and a lack of knowledge in a more flexible and more faithful manner. To learn from weakly labeled data of that kind, we leverage methods that have recently been proposed in the realm of so-called superset learning. In an exhaustive empirical evaluation, we compare our methodology to state-of-the-art self-supervision approaches, showing competitive to superior performance especially in low-label scenarios incorporating a high degree of uncertainty.

For agents

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

get_harvested_code_for_paper("2106.11853")
get_code_for_paper("2106.11853")
have("2106.11853")

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

curl https://syntology.ai/api/ran/2106.11853.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.11853.svg)](https://syntology.ai/paper/2106.11853)

Connect an agent — have() is free.