SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.03310 · ICML · 2021

Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model

Zi Wang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 0 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2106.03310.json · badge: /api/ran/2106.03310.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
zwang84/zsdb3kd canonical (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
FunctionStatusWhere it lives
UntargetedMBD Ran
ran on a synthesized input · constructed an object; no result was computed
zwang84/zsdb3kd/untargeted_mbd.py
pointer only (licence: NONE) · get_code("be0d69cbc109c6ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwang84/zsdb3kd 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_target_train_loader Not yet run
unverified (harvested, no recorded run)
zwang84/zsdb3kd/get_soft_labels.py
pointer only (licence: NONE) · get_code("3db04229e79c579e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwang84/zsdb3kd 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.

get_train_loader Not yet run
unverified (harvested, no recorded run)
zwang84/zsdb3kd/get_soft_labels.py
pointer only (licence: NONE) · get_code("a5817c4ad22df324")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwang84/zsdb3kd 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.

shuffle_data Not yet run
unverified (harvested, no recorded run)
zwang84/zsdb3kd/train_model_kd.py
pointer only (licence: NONE) · get_code("d60c92fc9f2f5916")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwang84/zsdb3kd 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
get_target_train_loader 1 other paper
1 later
Ma_Aligning_Logits_Generatively_for_Principled_Black-Box_Knowledge_Distillation_CVPR_2024_paper (2024 (year only))
Aligning Logits Generatively for Principled Black-Box Knowledge Distillation

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Knowledge distillation (KD) is a successful approach for deep neural network acceleration, with which a compact network (student) is trained by mimicking the softmax output of a pre-trained high-capacity network (teacher). In tradition, KD usually relies on access to the training samples and the parameters of the white-box teacher to acquire the transferred knowledge. However, these prerequisites are not always realistic due to storage costs or privacy issues in real-world applications. Here we propose the concept of decisionbased black-box (DB3) knowledge distillation, with which the student is trained by distilling the knowledge from a black-box teacher (parameters are not accessible) that only returns classes rather than softmax outputs. We start with the scenario when the training set is accessible. We represent a sample's robustness against other classes by computing its distances to the teacher's decision boundaries and use it to construct the soft label for each training sample. After that, the student can be trained via standard KD. We then extend this approach to a more challenging scenario in which even accessing the training data is not feasible. We propose to generate pseudo samples distinguished by the teacher's decision boundaries to the largest extent and construct soft labels for them, which are used as the transfer set. We evaluate our approaches on various benchmark networks and datasets and experiment results demonstrate their effectiveness. Codes are available at: https://github.com/zwang84/zsdb3kd.

For agents

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

get_harvested_code_for_paper("2106.03310")
get_code_for_paper("2106.03310")
have("2106.03310")

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

curl https://syntology.ai/api/ran/2106.03310.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.03310.svg)](https://syntology.ai/paper/2106.03310)

Connect an agent — have() is free.