SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02215 · 2026

Scientific Theory of a Black-Box: A Life Cycle-Scale XAI Framework Based on Constructive Empiricism

Christian Bauckhage, Vanessa Toborek, Sebastian Müller, Tamás Horváth, Eike Stadtländer, Brendan Balcerak, Jackson Institiute, Bonn

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 2 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/2602.02215.json · badge: /api/ran/2602.02215.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
semueller/stobb_cobot canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
get_observation_base Ran
ran; our contract draft was wrong, not the code
semueller/stobb_cobot/interfaces.py
pointer only (licence: NONE) · get_code("c143b4dc224b6c1b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_support_labels Ran
ran; our contract draft was wrong, not the code
semueller/stobb_cobot/interfaces.py
pointer only (licence: NONE) · get_code("ec41f5c0e545eb27")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_csv Ran
ran, honoured the contract we drafted
semueller/stobb_cobot/show_example.py
pointer only (licence: NONE) · get_code("d403a53e43a72df5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_pkl Ran
ran; our contract draft was wrong, not the code
semueller/stobb_cobot/show_example.py
pointer only (licence: NONE) · get_code("249e1c82fd0a206b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_ff Ran
ran; our contract draft was wrong, not the code
semueller/stobb_cobot/lxg/models.py
pointer only (licence: NONE) · get_code("09f32aad82ceb1ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rect_contains Ran
ran; our contract draft was wrong, not the code
semueller/stobb_cobot/interfaces.py
pointer only (licence: NONE) · get_code("62506f5a23645283")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

train_nn Ran
ran; our contract draft was wrong, not the code
semueller/stobb_cobot/lxg/util.py
pointer only (licence: NONE) · get_code("bbe9ed448fc931fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_abalone Not yet run
unverified (harvested, no recorded run)
semueller/stobb_cobot/lxg/util.py
pointer only (licence: NONE) · get_code("a6a7cb1a78fbefe6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

integrated_gradients Not yet run
unverified (harvested, no recorded run)
semueller/stobb_cobot/lxg/attribution.py
pointer only (licence: NONE) · get_code("667758f31b1b6656")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, semueller/stobb_cobot when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Explainable AI (XAI) offers a growing number of algorithms that aim to answer specific questions about black-box models. What is missing is a principled way to consolidate explanatory information about a fixed black-box model into a persistent, auditable artefact, that accompanies the black-box throughout its life cycle. We address this gap by introducing the notion of a scientific theory of a black box (SToBB). Grounded in Constructive Empiricism, a SToBB fulfils three obligations: (i) empirical adequacy with respect to all available observations of black-box behaviour, (ii) adaptability via explicit update commitments that restore adequacy when new observations arrive, and (iii) auditability through transparent documentation of assumptions, construction choices, and update behaviour. We operationalise these obligations as a general framework that specifies an extensible observation base, a traceable hypothesis class, algorithmic components for construction and revision, and documentation sufficient for third-party assessment. Explanations for concrete stakeholder needs are then obtained by querying the maintained record through interfaces, rather than by producing isolated method outputs. As a proof of concept, we instantiate a complete SToBB for a neural-network classifier on a tabular task and introduce the Constructive Box Theoriser (CoBoT) algorithm, an online procedure that constructs and maintains an empirically adequate rule-based surrogate as observations accumulate. Together, these contributions position SToBBs as a life cycle-scale, inspectable point of reference that supports consistent, reusable analyses and systematic external scrutiny.

For agents

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

get_harvested_code_for_paper("2602.02215")
get_code_for_paper("2602.02215")
have("2602.02215")

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

curl https://syntology.ai/api/ran/2602.02215.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.02215.svg)](https://syntology.ai/paper/2602.02215)

Connect an agent — have() is free.