SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.17075 · ACL · 2023

CREST: A Joint Framework for Rationalization and Counterfactual Text Generation

André Martins, Marcos Treviso, Alexis Ross, Nuno Guerreiro

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 1 has no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2305.17075.json · badge: /api/ran/2305.17075.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
deep-spin/crest canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
build_optimizer Ran
ran on a synthesized input
deep-spin/crest/rationalizers/builders.py
code served (permissive licence) · get_code("0ccd640711c998a9")
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 Adam. 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

torch.manual_seed(0)

# Create a simple model with parameters
model = nn.Linear(4, 3)

# Define hyperparameters dictionary for Adam optimizer
h_params = {
    'optimizer': 'adam',
    'lr': 0.001,
    'betas': (0.9, 0.999),
    'weight_decay': 1e-5,
    'amsgrad': False,
    'rho': 0.9,
    'momentum': 0.9,
    'dampening': 0,
    'nesterov': False,
    'lambd': 0.0001,
    'alpha': 0.75,
    't0': 1000000.0,
    'centered': False
}

ARGS = {
    'model_parameters': model.parameters(),
    'h_params': h_params
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 0 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
build_optimizer 1 other paper
1 dated earlier
2109.04552 (2021-09)
SPECTRA: Sparse Structured Text Rationalization

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

Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these methods can be integrated to combine their complementary advantages. We overcome this limitation by introducing CREST (ContRastive Edits with Sparse raTionalization), a joint framework for selective rationalization and counterfactual text generation, and show that this framework leads to improvements in counterfactual quality, model robustness, and interpretability. First, CREST generates valid counterfactuals that are more natural than those produced by previous methods, and subsequently can be used for data augmentation at scale, reducing the need for human-generated examples. Second, we introduce a new loss function that leverages CREST counterfactuals to regularize selective rationales and show that this regularization improves both model robustness and rationale quality, compared to methods that do not leverage CREST counterfactuals. Our results demonstrate that CREST successfully bridges the gap between selective rationales and counterfactual examples, addressing the limitations of existing methods and providing a more comprehensive view of a model's predictions.

For agents

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

get_harvested_code_for_paper("2305.17075")
get_code_for_paper("2305.17075")
have("2305.17075")

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

curl https://syntology.ai/api/ran/2305.17075.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.17075.svg)](https://syntology.ai/paper/2305.17075)

Connect an agent — have() is free.