SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.07470 · 2018

Contrastive Explanations with Local Foil Trees

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have no contract verdict; 0 failures of our instrument; 0 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/1806.07470.json · badge: /api/ran/1806.07470.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
MarcelRobeer/ContrastiveExplanation community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
cache Ran
ran on a synthesized input
MarcelRobeer/ContrastiveExplanation/contrastive_explanation/utils.py
code served (permissive licence) · get_code("5fc1f2be9d33baf3")
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 function. 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 functools
import torch

def cache(f):
    """Add cache to function."""
    cache = f.cache = {}

    @functools.wraps(f)
    def cached_f(*a, **kw):
        key = str(a) + str(kw)
        if key not in cache:
            cache[key] = f(*a, **kw)
        return cache[key]
    return cached_f

# Create a simple test function to decorate with cache
def sample_function(x, y=10):
    """A simple function to be cached."""
    return x + y

ARGS = {
    'f': sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
checkargs Ran
ran on a synthesized input
MarcelRobeer/ContrastiveExplanation/contrastive_explanation/utils.py
code served (permissive licence) · get_code("6b0adc80fa0255f6")
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 function. 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 inspect

torch.manual_seed(0)

def dummy_check_func(arg_name, actual_value, expected_spec):
    """A simple check function that validates argument values."""
    if expected_spec == "positive":
        if actual_value <= 0:
            raise ValueError(f"{arg_name} must be positive")
    elif expected_spec == "non_negative":
        if actual_value < 0:
            raise ValueError(f"{arg_name} must be non-negative")
    elif isinstance(expected_spec, (list, tuple)):
        if actual_value not in expected_spec:
            raise ValueError(f"{arg_name} must be one of {expected_spec}")

def sample_decorated_function(x, y=5, z="default"):
    """Sample function to decorate."""
    return x + y

# Create argchecks: list of tuples (arg_name, expected_value_spec)
argchecks = [
    ("x", "positive"),
    ("y", "non_negative"),
]

# Create checkfunc
checkfunc = dummy_check_func

ARGS = {
    "argchecks": argchecks,
    "checkfunc": checkfunc,
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
softmax Ran
ran on a synthesized input
MarcelRobeer/ContrastiveExplanation/contrastive_explanation/utils.py
code served (permissive licence) · get_code("5a872a566dbb586d")
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 ndarray, 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
import numpy as np

torch.manual_seed(0)

# The softmax function takes a single parameter 'a' which must support:
# - .sum(axis=0, keepdims=1) method
# - indexing with boolean mask [sums == 0]
# - division operator /
# This works with numpy arrays or torch tensors

a = np.array([[0.1, 0.2, 0.3, 0.4],
              [0.5, 0.6, 0.7, 0.8]], dtype=np.float32)

ARGS = {
    "a": a
}
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 ndarray, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Recent advances in interpretable Machine Learning (iML) and eXplainable AI (XAI) construct explanations based on the importance of features in classification tasks. However, in a high-dimensional feature space this approach may become unfeasible without restraining the set of important features. We propose to utilize the human tendency to ask questions like "Why this output (the fact) instead of that output (the foil)?" to reduce the number of features to those that play a main role in the asked contrast. Our proposed method utilizes locally trained one-versus-all decision trees to identify the disjoint set of rules that causes the tree to classify data points as the foil and not as the fact. In this study we illustrate this approach on three benchmark classification tasks.

For agents

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

get_harvested_code_for_paper("1806.07470")
get_code_for_paper("1806.07470")
have("1806.07470")

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

curl https://syntology.ai/api/ran/1806.07470.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.07470.svg)](https://syntology.ai/paper/1806.07470)

Connect an agent — have() is free.