SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.08958 · ICML · 2024

PINNfluence: Interpreting PINNs through Influence Functions

Sebastian Lapuschkin, Aleksander Krasowski, Jonas Naujoks, Moritz Weckbecker, Galip Yolcu, Thomas Wiegand, Wojciech Samek, René Klausen

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 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/2409.08958.json · badge: /api/ran/2409.08958.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
aleks-krasowski/PINNfluence canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
aleks-krasowski/pinnfluence canonical (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
FunctionStatusWhere it lives
get_X_y_true Ran
ran; our contract draft was wrong, not the code
aleks-krasowski/PINNfluence/pinnfluence/utils/io.py
pointer only (licence: NOASSERTION) · get_code("25f8c12140a911b1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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_correlation Ran
ran; our contract draft was wrong, not the code
aleks-krasowski/PINNfluence/pinnfluence/utils/indicators.py
pointer only (licence: NOASSERTION) · get_code("c836d29fb6089248")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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_influence_scores Ran
ran; our contract draft was wrong, not the code
aleks-krasowski/PINNfluence/pinnfluence/utils/io.py
pointer only (licence: NOASSERTION) · get_code("89b31071ec219bf8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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_min_max_from_geom Ran
ran, honoured the contract we drafted
aleks-krasowski/PINNfluence/pinnfluence/utils/common.py
pointer only (licence: NOASSERTION) · get_code("9ab50b7dc3a5e730")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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_checkpoint Ran
ran; our contract draft was wrong, not the code
aleks-krasowski/PINNfluence/pinnfluence/problem_factory.py
pointer only (licence: NONE); the stored copy get_code serves, from aleks-krasowski/pinnfluence_resampling, is pointer only (licence: NOASSERTION) · get_code("4d40d73cd634b67e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aleks-krasowski/PINNfluence 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.

scale_x Ran
ran, honoured the contract we drafted
aleks-krasowski/PINNfluence/pinnfluence/utils/common.py
pointer only (licence: NOASSERTION) · get_code("b1197215b3d24dfc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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.

scaled_rbf_kernel Ran
ran; our contract draft was wrong, not the code
aleks-krasowski/PINNfluence/pinnfluence/utils/common.py
pointer only (licence: NOASSERTION) · get_code("8a57fd63b314245f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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.

compute_single_influence Not yet run
unverified (harvested, no recorded run)
aleks-krasowski/pinnfluence/pinnfluence/precalculate_influences.py
pointer only (licence: NOASSERTION) · get_code("8870d93ffbd07c19")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/pinnfluence (NOASSERTION). 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.

instantiate_IF Not yet run
unverified (harvested, no recorded run)
aleks-krasowski/PINNfluence/pinnfluence/utils/influence.py
pointer only (licence: NOASSERTION) · get_code("4fa37e957e571a35")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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.

instantiate_grad_dot Not yet run
unverified (harvested, no recorded run)
aleks-krasowski/PINNfluence/pinnfluence/utils/influence.py
pointer only (licence: NOASSERTION) · get_code("f89d12e5d7483405")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/PINNfluence (NOASSERTION). 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.

parse_loss_term Not yet run
unverified (harvested, no recorded run)
aleks-krasowski/pinnfluence/pinnfluence/precalculate_influences.py
pointer only (licence: NOASSERTION) · get_code("b6160bd12c82c84a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, aleks-krasowski/pinnfluence (NOASSERTION). 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 10 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
load_checkpoint 1 other paper
1 later
2506.16443 (2025-06)
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks

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

Physics-informed neural networks (PINNs) have emerged as a powerful deep learning approach for solving partial differential equations (PDEs) in the physical sciences, yet their behavior remains largely opaque and is typically understood through failure mode analyses rather than explicit interpretability. To address this issue, we introduce PINNFLUENCE, a training data attribution framework for interpreting PINNs based on influence functions. By extending influence functions to composite physics-informed training objectives, we enable fine-grained attribution between predictions, loss components, and training data points. Through benchmark experiments across various PDEs, we demonstrate that influence patterns provide granular diagnostics that distinguish structural characteristics across well-trained and poorly-trained PINNs. PINN-FLUENCE thus opens a new avenue for understanding and improving the reliability of PINNs through the lens of their data.

For agents

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

get_harvested_code_for_paper("2409.08958")
get_code_for_paper("2409.08958")
have("2409.08958")

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

curl https://syntology.ai/api/ran/2409.08958.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.08958.svg)](https://syntology.ai/paper/2409.08958)

Connect an agent — have() is free.