Papers › A Unified Approach to Interpreting Model Predictions

A Unified Approach to Interpreting Model Predictions

22 May 2017NeurIPS 2017 12arXiv:1705.07874archive 2025-07-28

Scott Lundberg, Su-In Lee

Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle to interpret, such as ensemble or deep learning models, creating a tension between accuracy and interpretability. In response, various methods have recently been proposed to help users interpret the predictions of complex models, but it is often unclear how these methods are related and when one method is preferable over another. To address this problem, we present a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature an importance value for a particular prediction. Its novel components include: (1) the identification of a new class of additive feature importance measures, and (2) theoretical results showing there is a unique solution in this class with a set of desirable properties. The new class unifies six existing methods, notable because several recent methods in the class lack the proposed desirable properties. Based on insights from this unification, we present new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.

PaperPDFConference PDFCodeCode 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 8 code samples harvested from 3 repositories linked to this paper: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 8 samples from 3 repositories, 3 ran (3 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 3 samples that ran have no recorded date.

17 repositories listed; official and paper-mentioned ones first.

slundberg/shap mentioned in papertfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GPUTreeShap: Massively Parallel Exact Calculation of SHAP Scores for Tree Ensembles (arXiv:2010.13972; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
GISH123/Cathay-Holdings-CIP-Projects-for-Interpretable-Machine-Learning mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
LaurentLava/SHAP mentioned on GitHubSyntology: not harvested report
MachineLearningJournalClub/LearningNLP mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
OpenXAIProject/SHAP-Tutorial mentioned on GitHubSyntology: not harvested report
TooTouch/WhiteBox-Part2 mentioned on GitHubtfSyntology: not harvested report
bgreenwell/fastshap mentioned on GitHubSyntology: not harvested report
iancovert/shapley-regression mentioned on GitHubSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
linkedin/fasttreeshap mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Consistent Individualized Feature Attribution for Tree Ensembles (arXiv:1802.03888; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
liuyanguu/SHAPforxgboost mentioned on GitHubNOASSERTIONSyntology: not harvested report
matteo-rizzo/explainable-fruit-ripeness-classification mentioned on GitHubpytorchSyntology: not harvested report
ojimenezn/ml-interpretability mentioned on GitHubSyntology: not harvested report
poloclub/webshap mentioned on GitHubtfMITSyntology: not harvested report
suinleelab/vit-shapley mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
yramon/ShapCounterfactual mentioned on GitHubtfSyntology: not harvested report
pytorch/captum pytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Understanding and Improving Feature Learning for Out-of-Distribution Generalization (arXiv:2304.11327; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

8 samples harvested: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 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
1ran
5unverified

Licence: 6 of the 8 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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”. “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.

GISH123/Cathay-Holdings-CIP-Projects-for-Interpretable-Machine-Learning community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ShapNN Interpretable Machine Learning/Data Shapley/Data Shapley cores(forked from github Data Shapley)/DShap.py ran no licence file found · pointer only · 8a5c823af20228ab · report fixture: returned ShapNN · level recorded 2026-09-22
DShap Interpretable Machine Learning/Data Shapley/Data Shapley cores(forked from github Data Shapley)/DShap.py unverified no licence file found · pointer only · 4ad3529c6a0d35d4 · report
iancovert/shapley-regression community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
calculate_result in 6 papers shapreg/shapley.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · violated contract fingerprinted licence of this copy not recorded · 3514bf75f7ea90b7 · report fixture: signature A:ndarray/2/float, b:ndarray/1/float, total:float/0/float · returned ndarray · level recorded, date not recorded
default_min_variance_samples shapreg/shapley.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · ddb5cac385e0f2fb · report fixture: signature game:SimpleGame/0/? · returned int · level recorded, date not recorded
ShapleyRegression shapreg/shapley.py unverified MIT (permissive) · 1bae926aa4169f77 · report
default_variance_batches shapreg/shapley.py unverified MIT (permissive) · a0ec30609289d2f1 · report
suinleelab/vit-shapley community (archive-listed) 2 samples, 0 ran · 2 unverified
ExplainerViT src/vit_shapley/models/explainer.py unverified no licence file found · pointer only · d229caa00dd35ea5 · report
_reset_weights src/vit_shapley/models/explainer.py unverified no licence file found · pointer only · 324da4ba58dcc892 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for SHAP (SHapley Additive exPlanations) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for SHAP (SHapley Additive exPlanations) (graph method: SHAP (SHapley Additive exPlanations)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. DShap entry · level 0 · unverified · 4ad3529c6a0d35d4
  2. ShapNN helper · level 1 · ran · 8a5c823af20228ab

harvested Assembly for SHAP (SHapley Additive exPlanations) (graph method: SHAP (SHapley Additive exPlanations)). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ExplainerViT entry · level 0 · unverified · d229caa00dd35ea5
  2. _reset_weights helper · level 0 · unverified · 324da4ba58dcc892

harvested Assembly for SHAP (SHapley Additive exPlanations) (graph method: SHAP (SHapley Additive exPlanations)). 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ShapleyRegression entry · level 0 · unverified · 1bae926aa4169f77
  2. calculate_result model · level 1 · ran · violated contract · 3514bf75f7ea90b7
  3. default_min_variance_samples helper · level 1 · ran · honoured contract · ddb5cac385e0f2fb
  4. default_variance_batches helper · level 0 · unverified · a0ec30609289d2f1

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="1705.07874") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Feature ImportanceImage AttributionInterpretability Techniques for Deep LearningInterpretable Machine Learningmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Attribution CUB-200-2011 Kernel SHAP Deletion AUC score (ResNet-101) 0.1016 #6 of 8 Archive leaderboard report
Image Attribution CUB-200-2011 Kernel SHAP Insertion AUC score (ResNet-101) 0.6763 #6 of 8 Archive leaderboard report
Image Attribution CelebA Kernel SHAP Deletion AUC score (ArcFace ResNet-101) 0.1409 #4 of 8 Archive leaderboard report
Image Attribution CelebA Kernel SHAP Insertion AUC score (ArcFace ResNet-101) 0.5246 #4 of 8 Archive leaderboard report
Image Attribution VGGFace2 Kernel SHAP Deletion AUC score (ArcFace ResNet-101) 0.2034 #5 of 8 Archive leaderboard report
Image Attribution VGGFace2 Kernel SHAP Insertion AUC score (ArcFace ResNet-101) 0.6132 #5 of 8 Archive leaderboard report
Interpretability Techniques for Deep Learning CelebA Kernel SHAP Insertion AUC score 0.5246 #3 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SHAP

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