SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.20134 · NeurIPS · 2025

Revisiting Logit Distributions for Reliable Out-of-Distribution Detection

Xilin Chen, Shiguang Shan, Ruibing Hou, Hong Chang, Jiachen Liang, Minyang Hu

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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; 4 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/2510.20134.json · badge: /api/ran/2510.20134.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
GIT-LJc/LogitGap canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
basic_clean Ran
ran; our contract draft was wrong, not the code
GIT-LJc/LogitGap/clip/simple_tokenizer.py
pointer only (licence: NONE); 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: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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_loss Ran
ran on a synthesized input
GIT-LJc/LogitGap/utils/id_like_loss.py
pointer only (licence: NONE) · get_code("39f12edcbfe6882e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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
GIT-LJc/LogitGap/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("d919ae32e5e4e616")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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.

select_in_out Ran
ran; our contract draft was wrong, not the code
GIT-LJc/LogitGap/trainers/id_like.py
pointer only (licence: NONE) · get_code("6a21d81fd81655e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
GIT-LJc/LogitGap/clip/simple_tokenizer.py
pointer only (licence: NONE); 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: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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)
GIT-LJc/LogitGap/clip/model.py
pointer only (licence: NONE) · get_code("aa56b568a90f8516")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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_coop_loss Not yet run
unverified (harvested, no recorded run)
GIT-LJc/LogitGap/trainers/coop.py
pointer only (licence: NONE) · get_code("139138f4e901e78d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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.

load Not yet run
unverified (harvested, no recorded run)
GIT-LJc/LogitGap/clip/clip.py
pointer only (licence: NONE) · get_code("88d0e8acec4aead0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GIT-LJc/LogitGap 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 3 the same month, 4 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
get_pairs 258 other papers
222 dated earlier, 2 the same month, 22 later, 11 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
203 dated earlier, 2 the same month, 15 later, 10 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
203 dated earlier, 2 the same month, 2 later, 10 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
build_model 9 other papers
8 dated earlier, 1 later
2305.18010 (2023-05)
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
2311.15243 (2023-11)
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
2401.15657 (2024-01)
Data-Free Generalized Zero-Shot Learning
and 6 more not named here
load 8 other papers
8 dated earlier
2311.15243 (2023-11)
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
2401.15657 (2024-01)
Data-Free Generalized Zero-Shot Learning
2403.12952 (2024-03)
Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models
and 5 more not named here
get_loss 1 other paper
1 dated earlier
2311.15243 (2023-11)
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
select_in_out 1 other paper
1 dated earlier
2311.15243 (2023-11)
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

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

Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications. While post-hoc methods are favored for their efficiency and ease of deployment, existing approaches often underexploit the rich information embedded in the model's logits space. In this paper, we propose LogitGap, a novel post-hoc OOD detection method that explicitly exploits the relationship between the maximum logit and the remaining logits to enhance the separability between in-distribution (ID) and OOD samples. To further improve its effectiveness, we refine LogitGap by focusing on a more compact and informative subset of the logit space. Specifically, we introduce a training-free strategy that automatically identifies the most informative logits for scoring. We provide both theoretical analysis and empirical evidence to validate the effectiveness of our approach. Extensive experiments on both vision-language and vision-only models demonstrate that LogitGap consistently achieves state-of-the-art performance across diverse OOD detection scenarios and benchmarks. Code is available at https://github.com/GIT-LJc/LogitGap.

For agents

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

get_harvested_code_for_paper("2510.20134")
get_code_for_paper("2510.20134")
have("2510.20134")

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

curl https://syntology.ai/api/ran/2510.20134.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.20134.svg)](https://syntology.ai/paper/2510.20134)

Connect an agent — have() is free.