Papers › A Consistent and Efficient Evaluation Strategy for Attribution Methods

A Consistent and Efficient Evaluation Strategy for Attribution Methods

1 Feb 2022arXiv:2202.00449archive 2025-07-28

Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, Enkelejda Kasneci

With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies. To assess the attribution quality across different attribution techniques, the most popular among these evaluation strategies in the image domain use pixel perturbations. However, recent advances discovered that different evaluation strategies produce conflicting rankings of attribution methods and can be prohibitively expensive to compute. In this work, we present an information-theoretic analysis of evaluation strategies based on pixel perturbations. Our findings reveal that the results are strongly affected by information leakage through the shape of the removed pixels as opposed to their actual values. Using our theoretical insights, we propose a novel evaluation framework termed Remove and Debias (ROAD) which offers two contributions: First, it mitigates the impact of the confounders, which entails higher consistency among evaluation strategies. Second, ROAD does not require the computationally expensive retraining step and saves up to 99% in computational costs compared to the state-of-the-art. We release our source code at https://github.com/tleemann/road_evaluation.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 10 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tleemann/road_evaluation officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 10 ran (0 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 10 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
8ran
6unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tleemann/road_evaluation. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

tleemann/road_evaluation official repository 16 samples, 10 ran (0 instrument-failed) · 6 unverified
ChannelMeanImputer road/road.py ran MIT (permissive) · 8d39eb0a1bab6a0a · report fixture: returned ChannelMeanImputer · level recorded 2026-09-22
ConvBlock_ResNet road/road.py ran fingerprinted MIT (permissive) · a5a2de6a98b65ad1 · report fixture: returned ConvBlock_ResNet · level recorded 2026-09-22
GNet_ResNet road/road.py ran fingerprinted MIT (permissive) · 5e433e65a3f46c52 · report fixture: returned GNet_ResNet · level recorded 2026-09-22
ImputedDataset road/road.py ran MIT (permissive) · a75a12951c70b941 · report fixture: returned ImputedDataset · level recorded 2026-09-22
ImputedDatasetMasksOnly road/road.py ran MIT (permissive) · 11860240064c7dd0 · report fixture: returned ImputedDatasetMasksOnly · level recorded 2026-09-22
ImputingDataLoaderWrapper road/road.py ran MIT (permissive) · 47503ad265daf120 · report fixture: returned ImputingDataLoaderWrapper · level recorded 2026-09-22
NoisyLinearImputer road/road.py ran fingerprinted MIT (permissive) · 629765eba65036f5 · report fixture: returned NoisyLinearImputer · level recorded 2026-09-22
ZeroImputer road/road.py ran MIT (permissive) · 428d991a1dcea84e · report fixture: signature img:Tensor/3/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-24
normalize_map in 6 papers road/road.py ran · honoured contract fingerprinted MIT (permissive) · b0613e306198627a · report fixture: signature s:ndarray/2/float · returned ndarray · level recorded 2026-09-22
rescale_channel road/road.py ran · violated contract fingerprinted MIT (permissive) · 1d09d53a4f0a9512 · report fixture: signature exp:ndarray/3/float · returned ndarray · level recorded 2026-09-22
BaseImputer road/road.py unverified MIT (permissive) · a9eaec23fad20830 · report
GAINImputer road/road.py unverified MIT (permissive) · c676b8a8d65d31fe · report
SelfAttention in 66 papers road/road.py unverified MIT (permissive) · b28b45f46cb768f9 · report
_from_str road/road.py unverified MIT (permissive) · dd12bbba39b07ee5 · report
road_eval road/road.py unverified MIT (permissive) · 44de25a587d6939c · report
run_road road/road.py unverified MIT (permissive) · 5c9f538fc7ee4d08 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Remove and Debias (ROAD) (graph method: Remove and Debias (ROAD)). 16 bricks; individually on a fixture: 10 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. run_road entry · level 0 · unverified · 5c9f538fc7ee4d08
  2. GAINImputer helper · level 0 · unverified · c676b8a8d65d31fe
  3. ImputedDataset data_transform · level 1 · ran · a75a12951c70b941
  4. ImputedDatasetMasksOnly data_transform · level 1 · ran · 11860240064c7dd0
  5. ImputingDataLoaderWrapper helper · level 1 · ran · 47503ad265daf120
  6. NoisyLinearImputer helper · level 1 · ran · 629765eba65036f5
  7. _from_str helper · level 0 · unverified · dd12bbba39b07ee5
  8. road_eval metric · level 0 · unverified · 44de25a587d6939c
  9. BaseImputer helper · level 0 · unverified · a9eaec23fad20830
  10. GNet_ResNet helper · level 1 · ran · 5e433e65a3f46c52
  11. ChannelMeanImputer helper · level 1 · ran · 8d39eb0a1bab6a0a
  12. rescale_channel helper · level 1 · ran · violated contract · 1d09d53a4f0a9512
  13. ZeroImputer helper · level 1 · ran · 428d991a1dcea84e
  14. ConvBlock_ResNet helper · level 1 · ran · a5a2de6a98b65ad1
  15. SelfAttention helper · level 0 · unverified · b28b45f46cb768f9
  16. normalize_map helper · level 1 · ran · honoured contract · b0613e306198627a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2202.00449") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections