SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.13346 · NAACL · 2021

Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics

Vidhisha Balachandran, Yulia Tsvetkov, Artidoro Pagnoni

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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2104.13346.json · badge: /api/ran/2104.13346.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
artidoro/frank canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
human_metric_correlation Ran
ran, honoured the contract we drafted
artidoro/frank/evaluation/evaluate.py
code served (permissive licence) · get_code("2ec3c56451c218fd")
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 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 a small sample dataframe with human judgements and metrics
np.random.seed(0)

n_samples = 10

data_df = pd.DataFrame({
    'human_score': np.random.randn(n_samples),
    'metric_1': np.random.randn(n_samples),
    'metric_2': np.random.randn(n_samples),
    'confound_var': np.random.choice(['A', 'B', 'C'], n_samples)
})

ARGS = {
    'data_df': data_df,
    'human_col': 'human_score',
    'metrics_cols': ['metric_1', 'metric_2'],
    'partial_correlation': True,
    'partial_correlation_variable': 'confound_var'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, scipy, sklearn — 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
parse_args Ran
ran; our contract draft was wrong, not the code
artidoro/frank/evaluation/evaluate.py
code served (permissive licence) · get_code("727187d8199941aa")
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 argparse

ARGS = {
    'args': [
        '--mode', 'hm-correlation',
        '--human_eval_path', 'data/human_annotations.json',
        '--baseline_metrics_outputs', 'data/baseline_factuality_metrics_outputs.json',
        '--baseline_metrics', 'Bleu', 'Meteor', 'Rouge 1',
        '--ablations', 'Flip_Semantic_Frame_Errors', 'Flip_Discourse_Errors',
        '--human', 'Factuality',
        '--partial_correlation_variable', 'model_name',
        '--dataset', 'cnndm',
        '--model_name', 'bart', 'pgn',
        '--split', 'valid'
    ]
}
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
williams_test Ran
ran, honoured the contract we drafted
artidoro/frank/evaluation/evaluate.py
code served (permissive licence) · get_code("00f000efebe2b132")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np
from scipy import stats
import sys

# Set seed for reproducibility
np.random.seed(0)

# Create valid arguments for williams_test
# The function tests whether correlation r12 equals r13
# Requirements: r12 > r13, n > 3, and correlations should be between -1 and 1

r12 = 0.75  # correlation between x1, x2 (larger value)
r13 = 0.65  # correlation between x1, x3 (smaller value, r12 > r13 required)
r23 = 0.50  # correlation between x2, x3
n = 50      # sample size (must be > 3)

ARGS = {
    "r12": r12,
    "r13": r13,
    "r23": r23,
    "n": n,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
williams_test 1 other paper
1 later
2310.05657 (2023-10)
A Closer Look into Automatic Evaluation Using Large 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

Modern summarization models generate highly fluent but often factually unreliable outputs. This motivated a surge of metrics attempting to measure the factuality of automatically generated summaries. Due to the lack of common benchmarks, these metrics cannot be compared. Moreover, all these methods treat factuality as a binary concept and fail to provide deeper insights on the kinds of inconsistencies made by different systems. To address these limitations, we devise a typology of factual errors and use it to collect human annotations of generated summaries from state-of-the-art summarization systems for the CNN/DM and XSum datasets. Through these annotations we identify the proportion of different categories of factual errors in various summarization models and benchmark factuality metrics, showing their correlation with human judgement as well as their specific strengths and weaknesses. 1

For agents

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

get_harvested_code_for_paper("2104.13346")
get_code_for_paper("2104.13346")
have("2104.13346")

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

curl https://syntology.ai/api/ran/2104.13346.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.13346.svg)](https://syntology.ai/paper/2104.13346)

Connect an agent — have() is free.