SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.02334 · ICML · 2023

Revisiting Discriminative vs. Generative Classifiers: Theory and Implications

Jun Zhu, Chongxuan Li, Guoqiang Wu, Yue Cao, Fan Bao, Chenyu Zheng

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 0 have no contract verdict; 3 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2302.02334.json · badge: /api/ran/2302.02334.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
ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers canonical (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
basic_clean Ran
ran; our contract draft was wrong, not the code
ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers/models/clip/simple_tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ltpwy/MSCI, and GitHub detected no licence in that repository 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_pairs Ran
ran; our contract draft was wrong, not the code
ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers/models/clip/simple_tokenizer.py
code served (permissive licence) · get_code("d919ae32e5e4e616")
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 set. 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 torch

torch.manual_seed(0)

# The function get_pairs takes a word parameter
# A word is represented as a tuple of symbols (variable-length strings)
# The function iterates through the word and creates pairs of consecutive symbols

word = ("hello", "world", "test")

ARGS = {
    "word": word
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
whitespace_clean Ran
ran; our contract draft was wrong, not the code
ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers/models/clip/simple_tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ltpwy/MSCI, and GitHub detected no licence in that repository 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.

build_model Not yet run
unverified (harvested, no recorded run)
ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers/models/clip/model.py
code served (permissive licence) · get_code("39e6b23b55f376ea")
How it ran

no invocation recorded.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers/models/moco/builder.py
code served (permissive licence) · get_code("73cecca9f3575f09")
How it ran

no invocation recorded.

load Not yet run
unverified (harvested, no recorded run)
ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers/models/clip/clip.py
pointer only (licence: MIT); the stored copy get_code serves, from mrflogs/ICLR24, is pointer only (licence: NONE) · get_code("f6f30e41636ae569")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mrflogs/ICLR24, and GitHub detected no licence in that repository 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 6 later) and 0 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_pairs 258 other papers
44 dated earlier, 1 the same month, 205 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
29 dated earlier, 1 the same month, 195 later, 5 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
basic_clean 218 other papers
29 dated earlier, 1 the same month, 182 later, 5 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 215 more not named here
concat_all_gather 138 other papers
67 dated earlier, 2 the same month, 68 later, 1 same year, order not determinable · 33 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 135 more not named here
build_model 53 other papers
4 dated earlier, 49 later
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2211.09552 (2022-11)
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
and 50 more not named here
load 23 other papers
3 dated earlier, 19 later, 1 undated
2208.05318 (2022-08)
Generative Action Description Prompts for Skeleton-based Action Recognition
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2212.04501 (2022-12)
Learning Video Representations from Large Language Models
and 20 more not named here

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

A large-scale deep model pre-trained on massive labeled or unlabeled data transfers well to downstream tasks. Linear evaluation freezes parameters in the pre-trained model and trains a linear classifier separately, which is efficient and attractive for transfer. However, little work has investigated the classifier in linear evaluation except for the default logistic regression. Inspired by the statistical efficiency of naïve Bayes, the paper revisits the classical topic on discriminative vs. generative classifiers (Ng & Jordan, 2001). Theoretically, the paper considers the surrogate loss instead of the zero-one loss in analyses and generalizes the classical results from binary cases to multiclass ones. We show that, under mild assumptions, multiclass naïve Bayes requires O(log n) samples to approach its asymptotic error while the corresponding multiclass logistic regression requires O(n) samples, where n is the feature dimension. To establish it, we present a multiclass H-consistency bound framework and an explicit bound for logistic loss, which are of independent interests. Simulation results on a mixture of Gaussian validate our theoretical findings. Experiments on various pre-trained deep vision models show that naïve Bayes consistently converges faster as the number of data increases. Besides, naïve Bayes shows promise in few-shot cases and we observe the "two regimes" phenomenon in pretrained supervised models. Our code is available at https://github.com/ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers.

For agents

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

get_harvested_code_for_paper("2302.02334")
get_code_for_paper("2302.02334")
have("2302.02334")

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

curl https://syntology.ai/api/ran/2302.02334.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.02334.svg)](https://syntology.ai/paper/2302.02334)

Connect an agent — have() is free.