SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.02816 · EMNLP · 2022

PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training

Xiaoyong Du, Nan Tang, Preslav Nakov, Ju Fan, Zihui Gu, Xiaoman Zhao

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 3 have no contract verdict; 0 failures 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/2211.02816.json · badge: /api/ran/2211.02816.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
ruc-datalab/PASTA canonical (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
FunctionStatusWhere it lives
augment Ran
ran on a synthesized input
ruc-datalab/PASTA/src/utils/entitylink.py
code served (permissive licence) · get_code("5ee220eb85b02681")
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. 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 numpy as np

# The function 'augment' takes a single parameter 's' which is a list
# The function modifies this list in place and returns a tuple of (modified list, recover_dict)

# Test case 1: Simple list with 'first'
s1 = ['first', 'day']

# Test case 2: List with month and day number
s2 = ['january', '15', 'meeting']

# Test case 3: List with smoking-related terms
s3 = ['Smoking', 'status', 'Never', 'smoker']

# Test case 4: List with crowd/attendance
s4 = ['crowd', 'attendance', 'event']

# Test case 5: Empty list to test no augmentation
s5 = []

# Test case 6: List with abbreviated month
s6 = ['jan', '1', 'event']

# Test case 7: List with Active smoker
s7 = ['Active', 'smoker', 'person']

# Test case 8: List with Never smoker
s8 = ['Never', 'smoker', 'status']

# We'll use test case 2 as the primary one for ARGS
ARGS = {
    's': ['january', '15', 'meeting']
}
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 tuple — a tuple output has no array shape of its own; none is 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
is_ascii Ran
ran, violated the contract we drafted
ruc-datalab/PASTA/src/utils/entitylink.py
code served (permissive licence) · get_code("1b465b9239cb631c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 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.

ARGS = {
    "s": "Hello, World! This is an ASCII string with numbers 12345 and symbols @#$%"
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 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
linear_act Ran
ran on a synthesized input
ruc-datalab/PASTA/src/utils/pasta_mlm_model.py
code served (permissive licence) · get_code("3aff0fef02654e1a")
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

torch.manual_seed(0)

# linear_act simply returns its input x
# x should be a tensor
x = torch.randn(2, 4)

ARGS = {
    'x': x
}
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
replace_useless Ran
ran on a synthesized input
ruc-datalab/PASTA/src/utils/entitylink.py
code served (permissive licence) · get_code("53a8bf34ba711981")
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 torch

def replace_useless(s):
    s = s.replace(',', '')
    s = s.replace('.', '')
    s = s.replace('/', '')
    return s

ARGS = {
    's': 'hello,world.test/string'
}
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 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
gelu_new Not yet run
unverified (harvested, no recorded run)
ruc-datalab/PASTA/src/utils/pasta_mlm_model.py
code served (permissive licence) · get_code("283f4bd4ad4cc1ed")
How it ran

no invocation recorded.

gelu_python Not yet run
unverified (harvested, no recorded run)
ruc-datalab/PASTA/src/utils/pasta_mlm_model.py
code served (permissive licence) · get_code("f41cf0378a1399d0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 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
gelu_new 24 other papers
11 dated earlier, 12 later, 1 same year, order not determinable
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2104.08066 (2021-04)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
and 21 more not named here
is_ascii 9 other papers
7 dated earlier, 2 later
1911.08151 (2019-11)
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
2020.acl-main.53 (2020 (year only))
Efficient Dialogue State Tracking by Selectively Overwriting Memory
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
and 6 more not named here
gelu_python 3 other papers
1 dated earlier, 2 later
2202.00666 (2022-02)
Locally Typical Sampling
2306.08891 (2023-06)
Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation
2410.05748 (2024-10)
Label Confidence Weighted Learning for Target-level Sentence Simplification
linear_act 1 other paper
1 later
2306.08891 (2023-06)
Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

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

Fact verification has attracted a lot of research attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and disinformation online can sway one's opinion and affect one's actions. While fact-checking is a hard task in general, in many cases, false statements can be easily debunked based on analytics over tables with reliable information. Hence, table-based fact verification has recently emerged as an important and growing research area. Yet, progress has been limited due to the lack of datasets that can be used to pre-train language models (LMs) to be aware of common table operations, such as aggregating a column or comparing tuples. To bridge this gap, in this paper we introduce PASTA, a novel state-of-the-art framework for table-based fact verification via pre-training with synthesized sentence-table cloze questions. In particular, we design six types of common sentence-table cloze tasks, including Filter, Aggregation, Superlative, Comparative, Ordinal, and Unique, based on which we synthesize a large corpus consisting of 1.2 million sentence-table pairs from WikiTables. PASTA uses a recent pre-trained LM, DeBERTaV3, and further pretrains it on our corpus. Our experimental results show that PASTA achieves new state-ofthe-art performance on two table-based fact verification benchmarks: TabFact and SEM-TAB-FACTS. In particular, on the complex set of TabFact, which contains multiple operations, PASTA largely outperforms the previous state of the art by 4.7 points (85.6% vs. 80.9%), and the gap between PASTA and human performance on the small TabFact test set is narrowed to just 1.5 points (90.6% vs. 92.1%).

For agents

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

get_harvested_code_for_paper("2211.02816")
get_code_for_paper("2211.02816")
have("2211.02816")

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

curl https://syntology.ai/api/ran/2211.02816.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.02816.svg)](https://syntology.ai/paper/2211.02816)

Connect an agent — have() is free.