SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.07024 · NeurIPS · 2022

Self-explaining deep models with logic rule reasoning

Xing Xie, Xiaoyuan Yi, Seungeon Lee, Xiting Wang, † Social, Computing Group, Sungwon Han, Meeyoung Cha

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 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/2210.07024.json · badge: /api/ran/2210.07024.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
archon159/selor marked official in Papers with Code
Papers with Code archive
2 ran · 2 no recorded run
FunctionStatusWhere it lives
AtomSelector Ran
ran on a synthesized input · constructed an object; no result was computed
archon159/selor/selor_utils/net.py
code served (permissive licence) · get_code("d1aa7d5f0c4921b9")
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, AtomSelector: 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
from torch import nn

torch.manual_seed(0)

# Parameters for AtomSelector
num_atoms = 5
antecedent_len = 2
hidden_dim = 4

# Create a small atom_embedding tensor
# Shape: (num_atoms, hidden_dim) - used in torch.mm(prob, self.atom_embedding.detach())
atom_embedding = torch.randn(num_atoms, hidden_dim)

ARGS = {
    "num_atoms": num_atoms,
    "antecedent_len": antecedent_len,
    "hidden_dim": hidden_dim,
    "atom_embedding": atom_embedding,
}
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 AtomSelector — 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 AtomSelector 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
BaseModel Ran
ran on a synthesized input · constructed an object; no result was computed
archon159/selor/selor_utils/net.py
code served (permissive licence) · get_code("6ec61531758d0ded")
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, BaseModel: 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
from torch import nn
import transformers

torch.manual_seed(0)

# Create a minimal transformer model for testing
class MinimalTransformer(nn.Module):
    def __init__(self):
        super().__init__()
        self.embedding = nn.Embedding(100, 768)
        self.transformer_layer = nn.TransformerEncoderLayer(d_model=768, nhead=8, batch_first=True)
    
    def forward(self, input_ids, attention_mask):
        x = self.embedding(input_ids)
        out = self.transformer_layer(x)
        return {'last_hidden_state': out}

# Create minimal transformer model instance
tf_model = MinimalTransformer()

# Define ARGS dict with all parameters for BaseModel
ARGS = {
    'dataset': 'yelp',
    'base': 'bert',
    'input_dim': 512,
    'hidden_dim': 768,
    'num_classes': 2,
    'tf_model': tf_model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BaseModel — 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 BaseModel 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
AntecedentGenerator Not yet run
unverified (harvested, no recorded run)
archon159/selor/selor_utils/net.py
code served (permissive licence) · get_code("cbcbd0551f8ad9c9")
How it ran

no invocation recorded.

check_kwargs Not yet run
unverified (harvested, no recorded run)
archon159/selor/selor_utils/net.py
code served (permissive licence) · get_code("2240b43d073c5f4b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

We present SELOR, a framework for integrating self-explaining capabilities into a given deep model to achieve both high prediction performance and human precision. By "human precision", we refer to the degree to which humans agree with the reasons models provide for their predictions. Human precision affects user trust and allows users to collaborate closely with the model. We demonstrate that logic rule explanations naturally satisfy human precision with the expressive power required for good predictive performance. We then illustrate how to enable a deep model to predict and explain with logic rules. Our method does not require predefined logic rule sets or human annotations and can be learned efficiently and easily with widely-used deep learning modules in a differentiable way. Extensive experiments show that our method gives explanations closer to human decision logic than other methods while maintaining the performance of deep learning models.

For agents

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

get_harvested_code_for_paper("2210.07024")
get_code_for_paper("2210.07024")
have("2210.07024")

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

curl https://syntology.ai/api/ran/2210.07024.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.07024.svg)](https://syntology.ai/paper/2210.07024)

Connect an agent — have() is free.