SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1901.00850 · 2019

CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 1 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/1901.00850.json · badge: /api/ran/1901.00850.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
byahn2/clevr_ref canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
ruotianluo/iep-ref reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_all_relationships Ran
ran; our contract draft was wrong, not the code
byahn2/clevr_ref/image_generation/restore_render_images.py
pointer only (licence: NOASSERTION) · get_code("fba59b7f1bb4cc9e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, byahn2/clevr_ref (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.

find_filter_options Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
byahn2/clevr_ref/refexp_generation/generate_refexp.py
pointer only (licence: NOASSERTION) · get_code("9a69db254731308a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, byahn2/clevr_ref (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.

node_shallow_copy Ran
ran; our contract draft was wrong, not the code
byahn2/clevr_ref/refexp_generation/generate_refexp.py
pointer only (licence: NOASSERTION) · get_code("399457377d04215f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, byahn2/clevr_ref (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.

parse_int_list Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from facebookresearch/clevr-iep
pointer only; the stored copy get_code serves, from facebookresearch/clevr-iep, is pointer only (licence: NOASSERTION) · get_code("394f2802fb88d6da")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

run_our_model_batch Not yet run
unverified (harvested, no recorded run)
ruotianluo/iep-ref/scripts/run_model.py
pointer only (licence: NOASSERTION) · get_code("1383aead1bcf4276")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ruotianluo/iep-ref (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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
compute_all_relationships 3 other papers
1 dated earlier, 2 later
1811.03259 (2018-11)
Bias and Generalization in Deep Generative Models: An Empirical Study
2111.10265 (2021-11)
CLEVRTEX: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation
2310.17914 (2023-10)
3D-Aware Visual Question Answering about Parts, Poses and Occlusions
node_shallow_copy 2 other papers
2 later
2003.07258 (2020-03)
Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI
2112.11691 (2021-12)
Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation
parse_int_list 1 other paper
1 dated earlier
1705.03633 (2017-05)
Inferring and Executing Programs for Visual Reasoning

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

Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and current state-of-the-art models cannot be easily evaluated on their intermediate reasoning process. To address these issues and complement similar efforts in visual question answering, we build CLEVR-Ref+, a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators. In addition to evaluating several state-of-the-art models on CLEVR-Ref+, we also propose IEP-Ref, a module network approach that significantly outperforms other models on our dataset. In particular, we present two interesting and important findings using IEP-Ref: (1) the module trained to transform feature maps into segmentation masks can be attached to any intermediate module to reveal the entire reasoning process step-by-step; (2) even if all training data has at least one object referred, IEP-Ref can correctly predict no-foreground when presented with false-premise referring expressions. To the best of our knowledge, this is the first direct and quantitative proof that neural modules behave in the way they are intended.

For agents

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

get_harvested_code_for_paper("1901.00850")
get_code_for_paper("1901.00850")
have("1901.00850")

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

curl https://syntology.ai/api/ran/1901.00850.json

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

[![Syntology run record](https://syntology.ai/api/ran/1901.00850.svg)](https://syntology.ai/paper/1901.00850)

Connect an agent — have() is free.