SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.07566 · 2021

VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

arXiv · PDF · Open in the Atlas

Code that ran

6 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, 1 violated it and 2 have no contract verdict; 3 failures of our instrument; 3 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/2112.07566.json · badge: /api/ran/2112.07566.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
heidelberg-nlp/valse canonical (classifier label)
classifier basis not recorded on the link
6 ran · 3 no recorded run
FunctionStatusWhere it lives
do_nms Ran
ran; our contract draft was wrong, not the code
heidelberg-nlp/valse/modeling_frcnn.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("e21bb85b8e1b4836")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

is_remote_url Ran
ran, violated the contract we drafted
heidelberg-nlp/valse/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("899d1e2736236351")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

load_labels Ran
ran; our contract draft was wrong, not the code
heidelberg-nlp/valse/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("8a78a755bda274a5")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

norm_box Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
heidelberg-nlp/valse/modeling_frcnn.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("cfa4887da544c990")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

pad_list_tensors Ran
ran on a synthesized input
heidelberg-nlp/valse/modeling_frcnn.py
code served (permissive licence) · get_code("c06bd30b6fcc7498")
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, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (3, 5, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import numpy as np

torch.manual_seed(0)

# Create sample tensors with different numbers of detections
tensor1 = torch.randn(3, 4)  # 3 detections, 4 features
tensor2 = torch.randn(2, 4)  # 2 detections, 4 features
tensor3 = torch.randn(1, 4)  # 1 detection, 4 features

list_tensors = [tensor1, tensor2, tensor3]
preds_per_image = [3, 2, 1]

ARGS = {
    'list_tensors': list_tensors,
    'preds_per_image': preds_per_image,
    'max_detections': 5,
    'return_tensors': 'pt',
    'padding': 'max_detections',
    'pad_value': 0,
    'location': 'cpu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 5, 4) — shape (3, 5, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
read_foil_dataset Ran
ran on a synthesized input
heidelberg-nlp/valse/read_foil_dataset.py
code served (permissive licence) · get_code("0ea1a5e4fb771a67")
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, through the batch API) and returned dict. 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 json
import tempfile
import os

# Create a temporary JSON file with the FOIL dataset structure
foil_data = {
    "annotations": [
        {
            "foil": True,
            "caption": "A dog jumping over a red ball",
            "foil_word": "red",
            "target_word": "blue",
            "image_id": 123456,
            "foil_id": "foil_001"
        },
        {
            "foil": True,
            "caption": "A cat sitting on a wooden chair",
            "foil_word": "wooden",
            "target_word": "plastic",
            "image_id": 789012,
            "foil_id": "foil_002"
        },
        {
            "foil": False,
            "caption": "A bird flying in the sky",
            "foil_word": "sky",
            "target_word": "cloud",
            "image_id": 345678,
            "foil_id": "foil_003"
        }
    ]
}

# Create a temporary file
temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False)
json.dump(foil_data, temp_file)
temp_file.close()

ARGS = {
    "foils_path": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
compute_ppl Not yet run
unverified (harvested, no recorded run)
heidelberg-nlp/valse/unimodal_valse_eval.py
code served (permissive licence) · get_code("3b772f0bbcecca2c")
How it ran

no invocation recorded.

load_checkpoint Not yet run
unverified (harvested, no recorded run)
heidelberg-nlp/valse/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("bd3a3f4bd8750da2")
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 vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

read_foils Not yet run
unverified (harvested, no recorded run)
heidelberg-nlp/valse/read_foil_dataset.py
code served (permissive licence) · get_code("dc379b20add70eab")
How it ran

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 (1 with at least one paper dated earlier, 0 the same month, 5 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
is_remote_url 14 other papers
5 dated earlier, 9 later
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
and 11 more not named here
do_nms 11 other papers
11 later
2203.02013 (2022-03)
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations
2204.03162 (2022-04)
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
2205.00363 (2022-05)
Visual Spatial Reasoning
and 8 more not named here
norm_box 4 other papers
4 later
2206.06522 (2022-06)
LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
2305.11692 (2023-05)
Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
2307.05182 (2023-07)
CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
and 1 more not named here
load_checkpoint 3 other papers
3 later
2203.02013 (2022-03)
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations
2205.00363 (2022-05)
Visual Spatial Reasoning
2605.27311 (2026-05)
CHARTOGRAPHER: Counterfactual Chart Generation for Evaluating Vision-Language Models
load_labels 3 other papers
3 later
2203.02013 (2022-03)
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations
2205.00363 (2022-05)
Visual Spatial Reasoning
2605.27311 (2026-05)
CHARTOGRAPHER: Counterfactual Chart Generation for Evaluating Vision-Language Models

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

We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic phenomena. VALSE offers a suite of six tests covering various linguistic constructs. Solving these requires models to ground linguistic phenomena in the visual modality, allowing more fine-grained evaluations than hitherto possible. We build VALSE using methods that support the construction of valid foils, and report results from evaluating five widely-used V&L models. Our experiments suggest that current models have considerable difficulty addressing most phenomena. Hence, we expect VALSE to serve as an important benchmark to measure future progress of pretrained V&L models from a linguistic perspective, complementing the canonical task-centred V&L evaluations.

For agents

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

get_harvested_code_for_paper("2112.07566")
get_code_for_paper("2112.07566")
have("2112.07566")

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

curl https://syntology.ai/api/ran/2112.07566.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.07566.svg)](https://syntology.ai/paper/2112.07566)

Connect an agent — have() is free.