SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.06987 · 2021

Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2105.06987.json · badge: /api/ran/2105.06987.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
KaosEngineer/structured-uncertainty extension (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
get_sentence_wer Ran
ran, honoured the contract we drafted
KaosEngineer/structured-uncertainty/examples/structured_uncertainty/assessment/compute_cross_metrics.py
pointer only (licence: NONE) · get_code("2b7c186c9b54effb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KaosEngineer/structured-uncertainty 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.

load_text Ran
ran; our contract draft was wrong, not the code
KaosEngineer/structured-uncertainty/examples/structured_uncertainty/assessment/compute_cross_metrics.py
pointer only (licence: NONE) · get_code("5b36af4674a8d16d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KaosEngineer/structured-uncertainty 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.

load_uncertainties Ran
ran; our contract draft was wrong, not the code
KaosEngineer/structured-uncertainty/examples/structured_uncertainty/assessment/ood_detection.py
pointer only (licence: NONE) · get_code("5cb5b04d985b725c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KaosEngineer/structured-uncertainty 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.

load_uncertainties_calibrate Ran
ran; our contract draft was wrong, not the code
KaosEngineer/structured-uncertainty/examples/structured_uncertainty/assessment/ood_detection.py
pointer only (licence: NONE) · get_code("84515154843f0ccf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KaosEngineer/structured-uncertainty 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.

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Ensembles of machine learning models yield improved system performance as well as robust and interpretable uncertainty estimates; however, their inference costs may often be prohibitively high. \emph{Ensemble Distribution Distillation} is an approach that allows a single model to efficiently capture both the predictive performance and uncertainty estimates of an ensemble. For classification, this is achieved by training a Dirichlet distribution over the ensemble members' output distributions via the maximum likelihood criterion. Although theoretically principled, this criterion exhibits poor convergence when applied to large-scale tasks where the number of classes is very high. In our work, we analyze this effect and show that the Dirichlet log-likelihood criterion classes with low probability induce larger gradients than high-probability classes. This forces the model to focus on the distribution of the ensemble tail-class probabilities. We propose a new training objective that minimizes the reverse KL-divergence to a \emph{Proxy-Dirichlet} target derived from the ensemble. This loss resolves the gradient issues of Ensemble Distribution Distillation, as we demonstrate both theoretically and empirically on the ImageNet and WMT17 En-De datasets containing 1000 and 40,000 classes, respectively.

For agents

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

get_harvested_code_for_paper("2105.06987")
get_code_for_paper("2105.06987")
have("2105.06987")

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

curl https://syntology.ai/api/ran/2105.06987.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.06987.svg)](https://syntology.ai/paper/2105.06987)

Connect an agent — have() is free.