SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.01569 · 2023

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have no contract verdict; 0 failures of our instrument; 0 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/2305.01569.json · badge: /api/ran/2305.01569.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
yuvalkirstain/pickscore canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
instantiate_dummy_lr_scheduler Ran
ran on a synthesized input
yuvalkirstain/pickscore/trainer/lr_schedulers/constant_with_warmup.py
code served (permissive licence) · get_code("889813052606c2ee")
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 LambdaLR. 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
import torch.nn as nn
from torch.optim import Adam
from dataclasses import dataclass
from transformers import get_constant_schedule_with_warmup

torch.manual_seed(0)

@dataclass
class ConstantWithWarmupLRSchedulerConfig:
    lr: float = 0.001
    lr_warmup_steps: int = 500
    total_num_steps: int = 5000

# Create a minimal model
class DummyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = DummyModel()
optimizer = Adam(model.parameters(), lr=0.001)
cfg = ConstantWithWarmupLRSchedulerConfig()

ARGS = {
    'cfg': cfg,
    'optimizer': optimizer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
omegaconf, torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
instantiate_with_cfg Ran
ran on a synthesized input
yuvalkirstain/pickscore/trainer/configs/configs.py
code served (permissive licence) · get_code("8083a7b336edee87")
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
from omegaconf import DictConfig, OmegaConf

torch.manual_seed(0)

# Create a simple target function that accepts a DictConfig and kwargs
def simple_target(cfg, **kwargs):
    """A simple target function that will be instantiated"""
    return {
        "cfg": cfg,
        "kwargs": kwargs
    }

# Register the function so it can be located
import sys
from types import ModuleType

# Create a mock module to hold our target
mock_module = ModuleType("mock_target_module")
mock_module.simple_target = simple_target
sys.modules["mock_target_module"] = mock_module

# Create a DictConfig with _target_ pointing to our function
cfg = OmegaConf.create({
    "_target_": "mock_target_module.simple_target",
    "param1": "value1",
    "param2": 42
})

# Define kwargs to pass to instantiate_with_cfg
extra_kwargs = {
    "extra_param": "extra_value",
    "extra_num": 100
}

ARGS = {
    "cfg": cfg,
    "kwargs": extra_kwargs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
omegaconf, 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
simple_collate Ran
ran on a synthesized input
yuvalkirstain/pickscore/trainer/datasetss/clip_hf_dataset.py
code served (permissive licence) · get_code("ef1c92590a58880a")
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 (4, 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

torch.manual_seed(0)

# The function expects:
# - batch: a list of items, where each item is a dict-like object
# - column_name: a string key to access tensors in each item

# Create sample batch items as dicts containing tensors
batch = [
    {"data": torch.randn(2, 4)},
    {"data": torch.randn(2, 4)},
]

column_name = "data"

ARGS = {
    "batch": batch,
    "column_name": column_name,
}
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 (4, 4) — shape (4, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate images and specify their preferences. Using this web app we build Pick-a-Pic, a large, open dataset of text-to-image prompts and real users' preferences over generated images. We leverage this dataset to train a CLIP-based scoring function, PickScore, which exhibits superhuman performance on the task of predicting human preferences. Then, we test PickScore's ability to perform model evaluation and observe that it correlates better with human rankings than other automatic evaluation metrics. Therefore, we recommend using PickScore for evaluating future text-to-image generation models, and using Pick-a-Pic prompts as a more relevant dataset than MS-COCO. Finally, we demonstrate how PickScore can enhance existing text-to-image models via ranking.

For agents

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

get_harvested_code_for_paper("2305.01569")
get_code_for_paper("2305.01569")
have("2305.01569")

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

curl https://syntology.ai/api/ran/2305.01569.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.01569.svg)](https://syntology.ai/paper/2305.01569)

Connect an agent — have() is free.