SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.16211 · 2026

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Jinwoo Choi, Minho Shim, Dongyoon Wee, Taeoh Kim, Inwoong Lee, Geo Ahn

arXiv · PDF

Code that ran

7 of 9 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; 7 failures of our instrument; 2 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/2601.16211.json · badge: /api/ran/2601.16211.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
KHU-VLL/RCORE canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
cal_accs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KHU-VLL/RCORE/engine/evaluate_helper.py
pointer only (licence: NOASSERTION) · get_code("5b1a884852c840e2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, KHU-VLL/RCORE (NOASSERTION). 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.

cal_accs_with_component_logits Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KHU-VLL/RCORE/engine/evaluate_helper.py
pointer only (licence: NOASSERTION) · get_code("43d77d074ad9e997")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, KHU-VLL/RCORE (NOASSERTION). 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
KHU-VLL/RCORE/custom_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, KHU-VLL/RCORE 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_state_dict Ran
ran; our contract draft was wrong, not the code
KHU-VLL/RCORE/engine/train_comp_engine.py
pointer only (licence: NOASSERTION) · get_code("b5d43a2ad73d7b83")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, KHU-VLL/RCORE (NOASSERTION). 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.

hsic_loss Ran
ran; our contract draft was wrong, not the code
KHU-VLL/RCORE/utils/loss.py
pointer only (licence: NOASSERTION) · get_code("cf30627ae249d124")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, KHU-VLL/RCORE (NOASSERTION). 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.

loss_calu Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KHU-VLL/RCORE/utils/loss.py
pointer only (licence: NOASSERTION) · get_code("9157a56252b98f69")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, KHU-VLL/RCORE (NOASSERTION). 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
KHU-VLL/RCORE/custom_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, KHU-VLL/RCORE 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)
KHU-VLL/RCORE/custom_clip/model.py
pointer only (licence: NOASSERTION) · get_code("58149cc1cfb6b50c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, KHU-VLL/RCORE (NOASSERTION). 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)
KHU-VLL/RCORE/custom_clip/clip.py
pointer only (licence: NOASSERTION) · get_code("c22a78c25372b59f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, KHU-VLL/RCORE (NOASSERTION). 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 4 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
get_pairs 258 other papers
236 dated earlier, 5 the same month, 16 later, 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
216 dated earlier, 3 the same month, 11 later, 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
build_model 119 other papers
111 dated earlier, 2 the same month, 4 later, 2 undated
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2104.14294 (2021-04)
Emerging Properties in Self-Supervised Vision Transformers
and 116 more not named here
load 88 other papers
81 dated earlier, 2 the same month, 4 later, 1 undated
2203.05557 (2022-03)
Conditional Prompt Learning for Vision-Language Models
2206.01986 (2022-06)
Delving into the Openness of CLIP
2207.12819 (2022-07)
S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
and 85 more not named here
loss_calu 1 other paper
1 dated earlier
2211.10681 (2022-11)
Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning

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

Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key failure mode: models predict verbs via object-driven shortcuts (i.e., relying on the labeled object class) rather than temporal evidence. We argue that sparse compositional supervision and verb-object learning asymmetry can promote object-driven shortcut learning. Our analysis with proposed diagnostic metrics shows that existing methods overfit to training cooccurrence patterns and underuse temporal verb cues, resulting in weak generalization to unseen compositions. To address object-driven shortcuts, we propose Robust COmpositional REpresentations (RCORE) with two components. Co-occurrence Prior Regularization (CPR) adds explicit supervision for unseen compositions and regularizes the model against frequent co-occurrence priors by treating them as hard negatives. Temporal Order Regularization for Composition (TORC) enforces temporal-order sensitivity to learn temporally grounded verb representations. Across Sth-com and EK100-com, RCORE reduces shortcut diagnostics and consequently improves compositional generalization. The code is available at https://github.com/KHU-VLL/RCORE.

For agents

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

get_harvested_code_for_paper("2601.16211")
get_code_for_paper("2601.16211")
have("2601.16211")

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

curl https://syntology.ai/api/ran/2601.16211.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.16211.svg)](https://syntology.ai/paper/2601.16211)

Connect an agent — have() is free.