Papers › Probabilistic Concept Bottleneck Models

Probabilistic Concept Bottleneck Models

2 Jun 2023arXiv:2306.01574archive 2025-07-28

Eunji Kim, Dahuin Jung, Sangha Park, Siwon Kim, Sungroh Yoon

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the predicted concepts. CBM provides explanations with high-level concepts derived from concept predictions; thus, reliable concept predictions are important for trustworthiness. In this study, we address the ambiguity issue that can harm reliability. While the existence of a concept can often be ambiguous in the data, CBM predicts concepts deterministically without considering this ambiguity. To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM). By leveraging probabilistic concept embeddings, ProbCBM models uncertainty in concept prediction and provides explanations based on the concept and its corresponding uncertainty. This uncertainty enhances the reliability of the explanations. Furthermore, as class uncertainty is derived from concept uncertainty in ProbCBM, we can explain class uncertainty by means of concept uncertainty. Code is publicly available at https://github.com/ejkim47/prob-cbm.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.01574")

Code

Syntology Ran 10 of 17 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 5 ran; community (archive-listed): 7 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ejkim47/prob-cbm officialmentioned in papermentioned on GitHubpytorch report
samuelebortolotti/bears mentioned on GitHubpytorch 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

17 samples harvested; 10 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · our draft was wrong
1ran · fixture could not drive it
5ran
7unverified

Licence: 0 of the 17 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

ConceptConvModelBase ejkim47/prob-cbm/models/build_model_resnset.py official repository ran MIT (permissive) · fda0a150408ff903 · report
MC_dropout ejkim47/prob-cbm/models/build_model_resnset.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 83e14008bc124e87 · report
MultiHeadSelfAttention ejkim47/prob-cbm/models/build_model_resnset.py official repository ran MIT (permissive) · 428e1e15fdf0919e · report
batchwise_cdist ejkim47/prob-cbm/models/build_model_resnset.py official repository ran · our draft was wrong MIT (permissive) · eebc0b804e5a37cc · report
sample_gaussian_tensors ejkim47/prob-cbm/models/build_model_resnset.py official repository ran · our draft was wrong MIT (permissive) · 30eff244f638904e · report
PIENet ejkim47/prob-cbm/models/build_model_resnset.py official repository unverified MIT (permissive) · 71f4f03fffd0371c · report
ProbCBM ejkim47/prob-cbm/models/build_model_resnset.py official repository unverified MIT (permissive) · bdfbdaf595fd9bfa · report
ProbConceptModel ejkim47/prob-cbm/models/build_model_resnset.py official repository unverified MIT (permissive) · f31a10567b4272c6 · report
UncertaintyModuleImage ejkim47/prob-cbm/models/build_model_resnset.py official repository unverified MIT (permissive) · 41583f26fa5b9bf1 · report
weights_init ejkim47/prob-cbm/models/build_model_resnset.py official repository unverified MIT (permissive) · 974828b96c76f1ec · report
ADDMNIST_DPL samuelebortolotti/bears/XOR_MNIST/models/mnistpcbmdpl.py community (archive-listed) ran Apache-2.0 (permissive) · 87513c7b4b584213 · report
DeepProblogModel samuelebortolotti/bears/XOR_MNIST/models/mnistpcbmdpl.py community (archive-listed) ran Apache-2.0 (permissive) · 3ad96c3821cdf701 · report
get_device samuelebortolotti/bears/XOR_MNIST/models/mnistpcbmdpl.py community (archive-listed) ran Apache-2.0 (permissive) · fc09d4849f2de596 · report
kl_divergence samuelebortolotti/bears/XOR_MNIST/models/mnistpcbmdpl.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 7f0ddf1b30b1a8ac · report
sample_gaussian_tensors samuelebortolotti/bears/XOR_MNIST/models/mnistpcbmdpl.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cfa1916be4f5e83e · report
MnistDPL samuelebortolotti/bears/XOR_MNIST/models/mnistpcbmdpl.py community (archive-listed) unverified Apache-2.0 (permissive) · e7d420ab3ab8ebd1 · report
MnistPcbmDPL samuelebortolotti/bears/XOR_MNIST/models/mnistpcbmdpl.py community (archive-listed) unverified Apache-2.0 (permissive) · 542d2057f4601708 · report

Tasks

Prediction

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