SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.07818 · EMNLP · 2021

Certified Robustness to Programmable Transformations in LSTMs

Yuhao Zhang, Aws Albarghouthi, Loris Antoni

arXiv · PDF · Open in the Atlas

Code that ran

1 of 13 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 0 have no contract verdict; 1 failure of our instrument; 12 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/2102.07818.json · badge: /api/ran/2102.07818.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
foreverzyh/certified_lstms marked official in Papers with Code
Papers with Code archive
1 ran · 12 no recorded run
FunctionStatusWhere it lives
merge Ran
ran; our contract draft was wrong, not the code
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("13a8f8643f410f3e")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a small stand-in class that has a merge method
class MergeableObject:
    def __init__(self, value):
        self.value = value
    
    def merge(self, other):
        # Return a new MergeableObject with merged values
        return MergeableObject(self.value + other.value)

# Construct test arguments
X1 = (
    MergeableObject(torch.randn(2, 4)),
    MergeableObject(torch.randn(3, 5)),
)

X2 = (
    MergeableObject(torch.randn(2, 4)),
    MergeableObject(torch.randn(3, 5)),
)

ARGS = {
    "X1": X1,
    "X2": X2,
}
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 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
DiscreteChoiceTensorTrans Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("e55a6b4bee768aff")
How it ran

no invocation recorded.

DiscreteChoiceTensorWithUNK Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("fbd888025b89540a")
How it ran

no invocation recorded.

IntervalBoundedTensor Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("f44808aafab002f3")
How it ran

no invocation recorded.

LSTMDPGeneral Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("1880359f80ddceea")
How it ran

no invocation recorded.

Linear Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("fd80a7008b51f354")
How it ran

no invocation recorded.

NormBallTensor Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("9b303547a2021a85")
How it ran

no invocation recorded.

activation Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("5c7044eca4dc0224")
How it ran

no invocation recorded.

add Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("716e459ff7dd0927")
How it ran

no invocation recorded.

div Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("a566b05974471967")
How it ran

no invocation recorded.

mul Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("fb42c3a0a1c88cb9")
How it ran

no invocation recorded.

stack Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("4dbb73addd35ace4")
How it ran

no invocation recorded.

where Not yet run
unverified (harvested, no recorded run)
foreverzyh/certified_lstms/src/ibp.py
code served (permissive licence) · get_code("92963ee5c7b16174")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 11 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
add
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
1909.00986 (2019-09)
Certified Robustness to Adversarial Word Substitutions
2023.findings-acl.42 (2023 (year only))
Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions
mul
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
1909.00986 (2019-09)
Certified Robustness to Adversarial Word Substitutions
2023.findings-acl.42 (2023 (year only))
Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions

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

Deep neural networks for natural language processing are fragile in the face of adversarial examples-small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We present an approach to certifying the robustness of LSTMs (and extensions of LSTMs) and training models that can be efficiently certified. Our approach can certify robustness to intractably large perturbation spaces defined programmatically in a language of string transformations. Our evaluation shows that (1) our approach can train models that are more robust to combinations of string transformations than those produced using existing techniques; (2) our approach can show high certification accuracy of the resulting models.

For agents

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

get_harvested_code_for_paper("2102.07818")
get_code_for_paper("2102.07818")
have("2102.07818")

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

curl https://syntology.ai/api/ran/2102.07818.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.07818.svg)](https://syntology.ai/paper/2102.07818)

Connect an agent — have() is free.