SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.12914 · 2022

Open-vocabulary Attribute Detection

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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, 1 violated it and 5 have no contract verdict; 1 failure of our instrument; 2 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/2211.12914.json · badge: /api/ran/2211.12914.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
OVAD-Benchmark/ovad-bechmark-code canonical (classifier label)
classifier basis not recorded on the link
8 ran · 2 no recorded run
FunctionStatusWhere it lives
check_dir Ran
ran on a synthesized input
OVAD-Benchmark/ovad-bechmark-code/ovamc/misc.py
code served (permissive licence) · get_code("22996a79db8b6912")
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 str. 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 os
import tempfile

def check_dir(path):
    os.makedirs(path, exist_ok=True)
    return path

# Create a temporary directory path to use
temp_base = tempfile.gettempdir()
test_dir = os.path.join(temp_base, "test_check_dir_12345")

ARGS = {
    "path": test_dir
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
encode_albef Ran
ran on a synthesized input
OVAD-Benchmark/ovad-bechmark-code/ovamc/ova_albef.py
code served (permissive licence) · get_code("6acf85a66164e260")
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 2, dtype family float, shape (2, 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Build a minimal tokenizer stand-in
class MinimalTokenizer:
    def __call__(self, sentences, padding=None, truncation=None, max_length=None, return_tensors=None):
        batch_size = len(sentences)
        seq_len = 10
        
        input_ids = torch.randint(0, 1000, (batch_size, seq_len))
        attention_mask = torch.ones(batch_size, seq_len)
        
        class TokenizerOutput:
            def __init__(self, input_ids, attention_mask):
                self.input_ids = input_ids
                self.attention_mask = attention_mask
            
            def to(self, device):
                return TokenizerOutput(
                    self.input_ids.to(device),
                    self.attention_mask.to(device)
                )
        
        return TokenizerOutput(input_ids, attention_mask)

# Build a minimal text encoder with bert attribute
class MinimalTextEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.bert = MinimalBert()
    
    def forward(self, input_ids, attention_mask, return_dict=True, mode=None):
        # Dummy output
        batch_size = input_ids.shape[0]
        seq_len = input_ids.shape[1]
        hidden_dim = 8
        
        class TextOutput:
            def __init__(self, last_hidden_state):
                self.last_hidden_state = last_hidden_state
        
        last_hidden_state = torch.randn(batch_size, seq_len, hidden_dim)
        return TextOutput(last_hidden_state)

class MinimalBert(nn.Module):
    def __init__(self):
        super().__init__()
    
    def forward(self, input_ids, attention_mask, return_dict=True, mode=None):
        batch_size = input_ids.shape[0]
        seq_len = input_ids.shape[1]
        hidden_dim = 8
        
        class TextOutput:
            def __init__(self, last_hidden_state):
                self.last_hidden_state = last_hidden_state
        
        last_hidden_state = torch.randn(batch_size, seq_len, hidden_dim)
        return TextOutput(last_hidden_state)

# Build a minimal model with text_encoder and text_proj
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.text_encoder = MinimalTextEncoder()
        self.text_proj = nn.Linear(8, 4)
    
    def forward(self, *args, **kwargs):
        pass

# Test with simple text list
text_list_simple = ["hello world", "foo bar"]

# Test with nested list (synonyms)
text_list_nested = [["cat", "feline"], ["dog", "canine"]]

model = MinimalModel()
tokenizer = MinimalTokenizer()
device = 'cpu'

ARGS = {
    'text_list': text_list_simple,
    'model': model,
    'tokenizer': tokenizer,
    'device': device,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
encode_blip Ran
ran on a synthesized input
OVAD-Benchmark/ovad-bechmark-code/ovamc/ova_blip.py
code served (permissive licence) · get_code("4a39c00197a61d3b")
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 2, dtype family float, shape (2, 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Stand-in tokenizer class
class SimpleTokenizer:
    def __call__(self, sentences, padding=None, truncation=None, max_length=None, return_tensors=None):
        batch_size = len(sentences)
        # Return a mock tokenizer output with input_ids and attention_mask
        class TokenizerOutput:
            def __init__(self, batch_size):
                self.input_ids = torch.randint(0, 100, (batch_size, 30))
                self.attention_mask = torch.ones(batch_size, 30)
            
            def to(self, device):
                self.input_ids = self.input_ids.to(device)
                self.attention_mask = self.attention_mask.to(device)
                return self
        
        return TokenizerOutput(batch_size)

# Stand-in text encoder class
class SimpleTextEncoder(nn.Module):
    def __init__(self, hidden_dim=4):
        super().__init__()
        self.hidden_dim = hidden_dim
    
    def forward(self, input_ids, attention_mask=None, return_dict=True, mode=None):
        batch_size = input_ids.shape[0]
        # Return mock last_hidden_state with shape (batch_size, seq_len, hidden_dim)
        class EncoderOutput:
            def __init__(self, batch_size, hidden_dim):
                self.last_hidden_state = torch.randn(batch_size, 30, hidden_dim)
        
        return EncoderOutput(batch_size, self.hidden_dim)

# Stand-in model class
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.tokenizer = SimpleTokenizer()
        self.text_encoder = SimpleTextEncoder(hidden_dim=4)
        self.text_proj = nn.Linear(4, 4)
    
    def forward(self, x):
        return x

# Create test data
device = 'cpu'
model = SimpleModel()

# Test case 1: list of strings
text_list_strings = ["hello world", "foo bar"]

# Test case 2: list of lists (synonyms)
text_list_synonyms = [["hello", "hi"], ["world", "earth", "globe"]]

# Use the list of strings for this setup
text_list = text_list_strings

ARGS = {
    'text_list': text_list,
    'model': model,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
get_fed_loss_inds Ran
ran; our contract draft was wrong, not the code
OVAD-Benchmark/ovad-bechmark-code/ovadb/modeling/utils.py
code served (permissive licence) · get_code("bb583e07209fe58b")
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 1, dtype family int, shape (5,) 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

torch.manual_seed(0)

# gt_classes: a tensor of class indices
gt_classes = torch.tensor([0, 1, 2, 1, 0], dtype=torch.long)

# num_sample_cats: number of categories to sample
num_sample_cats = 5

# C: number of classes (total number of categories)
C = 8

# weight: optional weight tensor for classes, should have length C
weight = torch.ones(C, dtype=torch.float32)

ARGS = {
    "gt_classes": gt_classes,
    "num_sample_cats": num_sample_cats,
    "C": C,
    "weight": weight,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int, shape (5,) — shape (5,) 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
get_logger Ran
ran on a synthesized input
OVAD-Benchmark/ovad-bechmark-code/ovamc/misc.py
code served (permissive licence) · get_code("811f379c87ce6257")
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 Logger. 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 os
import logging
import datetime
import tempfile

# Create a temporary directory for logging
logdir = tempfile.mkdtemp()

# Define arguments for get_logger
ARGS = {
    'logdir': logdir,
    'name': 'test_logger',
    'evaluate': False
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
load_class_freq Ran
ran, honoured the contract we drafted
OVAD-Benchmark/ovad-bechmark-code/ovadb/modeling/utils.py
code served (permissive licence) · get_code("1f6e4c3da7b82979")
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 1, dtype family float, shape (3,) 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 json
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory and a mock LVIS metadata file
temp_dir = tempfile.mkdtemp()
metadata_path = os.path.join(temp_dir, 'lvis_v1_train_cat_info.json')

# Create mock category info with id and image_count
cat_info_data = [
    {'id': 1, 'image_count': 100},
    {'id': 2, 'image_count': 250},
    {'id': 3, 'image_count': 50},
]

with open(metadata_path, 'w') as f:
    json.dump(cat_info_data, f)

ARGS = {
    'path': metadata_path,
    'freq_weight': 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (3,) — shape (3,) 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
match_name_keywords Ran
ran, violated the contract we drafted
OVAD-Benchmark/ovad-bechmark-code/ovadb/custom_solver.py
code served (permissive licence) · get_code("c15434906f804d7f")
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 bool, ndim 0, dtype family float, shape () 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

torch.manual_seed(0)

# The function match_name_keywords checks if any string in name_keywords
# is contained in the string n. It takes:
# - n: a string to search in
# - name_keywords: an iterable of strings to search for

n = "layer.weight.bias"
name_keywords = ["weight", "bias", "norm"]

ARGS = {
    "n": n,
    "name_keywords": name_keywords,
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
stats Ran
ran on a synthesized input
OVAD-Benchmark/ovad-bechmark-code/ovadb/modeling/logged_module.py
code served (permissive licence) · get_code("9f35411381d5ccbc")
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 torch

torch.manual_seed(0)

# The function takes a single parameter: tensor
# It calls: .cpu(), .detach(), .numpy(), .device.index, .shape, .min(), .max(), .mean(), .std()
# All of these are standard torch.Tensor methods

# Create a small tensor on CPU with distinct dimensions
tensor = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    'tensor': tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — 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
accuracy Not yet run
unverified (harvested, no recorded run)
OVAD-Benchmark/ovad-bechmark-code/ovamc/misc.py
code served (permissive licence) · get_code("aafcff3ad1ccef6e")
How it ran

no invocation recorded.

encode_blip Not yet run
unverified (harvested, no recorded run)
OVAD-Benchmark/ovad-bechmark-code/ovamc/ova_blip2.py
code served (permissive licence) · get_code("b33aa70e7bb612ec")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 6 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
accuracy 22 other papers
2 dated earlier, 20 later
2207.05333 (2022-07)
IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training
2208.05592 (2022-08)
Patching open-vocabulary models by interpolating weights
2305.12827 (2023-05)
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
and 19 more not named here
match_name_keywords 13 other papers
4 dated earlier, 9 later
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2111.04076 (2021-11)
Direct Multi-view Multi-person 3D Pose Estimation
2206.11134 (2022-06)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
and 10 more not named here
get_fed_loss_inds 10 other papers
3 dated earlier, 7 later
2206.11134 (2022-06)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
2207.03482 (2022-07)
Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
2207.13080 (2022-07)
DETRs with Hybrid Matching
and 7 more not named here
load_class_freq 7 other papers
2 dated earlier, 5 later
2206.11134 (2022-06)
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
2207.13080 (2022-07)
DETRs with Hybrid Matching
2303.14679 (2023-03)
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
and 4 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

Vision-language modeling has enabled open-vocabulary tasks where predictions can be queried using any text prompt in a zero-shot manner. Existing open-vocabulary tasks focus on object classes, whereas research on object attributes is limited due to the lack of a reliable attribute-focused evaluation benchmark. This paper introduces the Open-Vocabulary Attribute Detection (OVAD) task and the corresponding OVAD benchmark. The objective of the novel task and benchmark is to probe object-level attribute information learned by vision-language models. To this end, we created a clean and densely annotated test set covering 117 attribute classes on the 80 object classes of MS COCO. It includes positive and negative annotations, which enables open-vocabulary evaluation. Overall, the benchmark consists of 1.4 million annotations. For reference, we provide a first baseline method for open-vocabulary attribute detection. Moreover, we demonstrate the benchmark's value by studying the attribute detection performance of several foundation models. Project page https://ovad-benchmark.github.io

For agents

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

get_harvested_code_for_paper("2211.12914")
get_code_for_paper("2211.12914")
have("2211.12914")

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

curl https://syntology.ai/api/ran/2211.12914.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.12914.svg)](https://syntology.ai/paper/2211.12914)

Connect an agent — have() is free.