SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.08285 · NeurIPS · 2022

FR: Folded Rationalization with a Unified Encoder

Jun Wang, Wei Liu, Haozhao Wang, Ruixuan Li, Chao Yue, Yuankai Zhang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 4 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/2209.08285.json · badge: /api/ran/2209.08285.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
jugechengzi/fr canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
kochsnow/distribution-matching-rationality unrelated (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
FunctionStatusWhere it lives
Embedding Ran
ran on a synthesized input · constructed an object; no result was computed
jugechengzi/fr/code/model.py
code served (permissive licence) · get_code("2d69b548b68473d8")
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 an instance of its own class, Embedding: the run constructed the object and did not call it, so no result was computed. 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
import numpy as np

torch.manual_seed(0)

# Set up parameters for the Embedding class
vocab_size = 100
embedding_dim = 4

# Create a pretrained embedding matrix (optional parameter)
pretrained_embedding = np.random.randn(vocab_size, embedding_dim).astype(np.float32)

ARGS = {
    "vocab_size": vocab_size,
    "embedding_dim": embedding_dim,
    "pretrained_embedding": pretrained_embedding,
}
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 Embedding — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Embedding 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
Rnn Ran
ran on a synthesized input · constructed an object; no result was computed
jugechengzi/fr/code/model.py
code served (permissive licence) · get_code("a15f3f880dc015cb")
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 an instance of its own class, Rnn: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'cell_type': 'LSTM',
    'embedding_dim': 4,
    'hidden_dim': 8,
    'num_layers': 2
}
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 Rnn — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Rnn 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
Embedding Not yet run
unverified (harvested, no recorded run)
kochsnow/distribution-matching-rationality/core/model.py
code served (permissive licence) · get_code("0ecca65553fc73fc")
How it ran

no invocation recorded.

GenEncShareModel Not yet run
unverified (harvested, no recorded run)
jugechengzi/fr/code/model.py
code served (permissive licence) · get_code("8f2c103a7213c94d")
How it ran

no invocation recorded.

RNN Not yet run
unverified (harvested, no recorded run)
kochsnow/distribution-matching-rationality/core/model.py
code served (permissive licence) · get_code("cea6a2e603a0cd85")
How it ran

no invocation recorded.

TargetRNN Not yet run
unverified (harvested, no recorded run)
kochsnow/distribution-matching-rationality/core/model.py
code served (permissive licence) · get_code("8e7154e1c58e042f")
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, 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 5 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
Embedding
brick of this paper's assembly: model
2 other papers
2 later · 2 only as an assembly brick
2410.06003 (2024-10)
Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
2505.02118 (2025-05)
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets

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

Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces. However, such a two-phase model may incur the degeneration problem where the predictor overfits to the noise generated by a not yet well-trained generator and in turn, leads the generator to converge to a sub-optimal model that tends to select senseless pieces. To tackle this challenge, we propose Folded Rationalization (FR) that folds the two phases of the rationale model into one from the perspective of text semantic extraction. The key idea of FR is to employ a unified encoder between the generator and predictor, based on which FR can facilitate a better predictor by access to valuable information blocked by the generator in the traditional two-phase model and thus bring a better generator. Empirically, we show that FR improves the F1 score by up to 10.3% as compared to state-of-the-art methods. Our codes are available at https://github.com/jugechengzi/FR.

For agents

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

get_harvested_code_for_paper("2209.08285")
get_code_for_paper("2209.08285")
have("2209.08285")

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

curl https://syntology.ai/api/ran/2209.08285.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.08285.svg)](https://syntology.ai/paper/2209.08285)

Connect an agent — have() is free.