SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.15349 · 2020

DynaSent: A Dynamic Benchmark for Sentiment Analysis

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2012.15349.json · badge: /api/ran/2012.15349.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
cgpotts/dynasent canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
get_dist_of_majority_dists Ran
ran, honoured the contract we drafted
cgpotts/dynasent/dynasent_utils.py
code served (permissive licence) · get_code("3b74331a5d2b400f")
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 Series. 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 pandas as pd

# Construct a minimal split argument
# The function iterates over split, accessing d['gold_label'] and d['label_distribution']
# label_distribution is a dict where values are iterables (we use lists)
# The function sorts by (len(v), k) and takes the max count

split = [
    {
        'gold_label': True,
        'label_distribution': {
            'label_a': ['item1', 'item2', 'item3'],
            'label_b': ['item1', 'item2'],
            'label_c': ['item1']
        }
    },
    {
        'gold_label': True,
        'label_distribution': {
            'label_x': ['a', 'b'],
            'label_y': ['a', 'b', 'c', 'd']
        }
    },
    {
        'gold_label': False,
        'label_distribution': {
            'label_p': ['x', 'y', 'z']
        }
    },
    {
        'gold_label': True,
        'label_distribution': {
            'label_m': ['p', 'q', 'r'],
            'label_n': ['p']
        }
    }
]

ARGS = {
    'split': split
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Series — a Series output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Series output the recorded ndim 1 and dtype family int 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
sample_examples Ran
ran; our contract draft was wrong, not the code
cgpotts/dynasent/dynasent_utils.py
code served (permissive licence) · get_code("6206bbdc84ac4981")
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 DataFrame. 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 pandas as pd
import numpy as np

# Create sample data for the split parameter
split_data = [
    {
        'sentence': 'This is a great movie.',
        'gold_label': 'positive',
        'model_prediction': 'positive',
        'label_distribution': {'entailment': [1, 2], 'neutral': [3], 'contradiction': [4, 5, 6]}
    },
    {
        'sentence': 'I did not like this film.',
        'gold_label': 'negative',
        'model_prediction': 'negative',
        'label_distribution': {'contradiction': [1, 2, 3], 'neutral': [4], 'entailment': [5]}
    },
    {
        'sentence': 'The weather is nice today.',
        'gold_label': 'neutral',
        'model_prediction': 'neutral',
        'label_distribution': {'neutral': [1, 2, 3, 4], 'entailment': [5], 'contradiction': [6]}
    },
    {
        'sentence': 'This product is amazing.',
        'gold_label': 'positive',
        'model_prediction': 'positive',
        'label_distribution': {'entailment': [1, 2, 3], 'neutral': [4, 5], 'contradiction': [6]}
    },
    {
        'sentence': 'I hate waiting in lines.',
        'gold_label': 'negative',
        'model_prediction': 'negative',
        'label_distribution': {'contradiction': [1, 2], 'neutral': [3, 4], 'entailment': [5, 6]}
    },
    {
        'sentence': 'The sky is blue.',
        'gold_label': 'neutral',
        'model_prediction': 'neutral',
        'label_distribution': {'neutral': [1, 2], 'entailment': [3, 4, 5], 'contradiction': [6]}
    },
    {
        'sentence': 'This is wonderful.',
        'gold_label': 'positive',
        'model_prediction': 'positive',
        'label_distribution': {'entailment': [1, 2, 3, 4], 'neutral': [5], 'contradiction': [6]}
    },
    {
        'sentence': 'I am very disappointed.',
        'gold_label': 'negative',
        'model_prediction': 'negative',
        'label_distribution': {'contradiction': [1, 2, 3], 'neutral': [4, 5], 'entailment': [6]}
    },
    {
        'sentence': 'The food was okay.',
        'gold_label': 'neutral',
        'model_prediction': 'neutral',
        'label_distribution': {'neutral': [1, 2, 3], 'entailment': [4], 'contradiction': [5, 6]}
    },
    {
        'sentence': 'Absolutely fantastic experience.',
        'gold_label': 'positive',
        'model_prediction': 'positive',
        'label_distribution': {'entailment': [1, 2], 'neutral': [3, 4], 'contradiction': [5]}
    },
    {
        'sentence': 'Terrible and awful.',
        'gold_label': 'negative',
        'model_prediction': 'negative',
        'label_distribution': {'contradiction': [1, 2, 3, 4], 'neutral': [5], 'entailment': [6]}
    },
    {
        'sentence': 'It is what it is.',
        'gold_label': 'neutral',
        'model_prediction': 'neutral',
        'label_distribution': {'neutral': [1, 2, 3, 4, 5], 'entailment': [6], 'contradiction': []}
    }
]

ARGS = {
    'split': split_data,
    'model_colname': 'model_prediction',
    'n': 10,
    'random_state': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
sample_short_examples Not yet run
unverified (harvested, no recorded run)
cgpotts/dynasent/dynasent_utils.py
code served (permissive licence) · get_code("40f680f0fd399a9b")
How it ran

no invocation recorded.

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

We introduce DynaSent ('Dynamic Sentiment'), a new English-language benchmark task for ternary (positive/negative/neutral) sentiment analysis. DynaSent combines naturally occurring sentences with sentences created using the open-source Dynabench Platform, which facilities human-and-model-in-the-loop dataset creation. DynaSent has a total of 121,634 sentences, each validated by five crowdworkers, and its development and test splits are designed to produce chance performance for even the best models we have been able to develop; when future models solve this task, we will use them to create DynaSent version 2, continuing the dynamic evolution of this benchmark. Here, we report on the dataset creation effort, focusing on the steps we took to increase quality and reduce artifacts. We also present evidence that DynaSent's Neutral category is more coherent than the comparable category in other benchmarks, and we motivate training models from scratch for each round over successive fine-tuning.

For agents

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

get_harvested_code_for_paper("2012.15349")
get_code_for_paper("2012.15349")
have("2012.15349")

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

curl https://syntology.ai/api/ran/2012.15349.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.15349.svg)](https://syntology.ai/paper/2012.15349)

Connect an agent — have() is free.