Papers › Interpretable machine learning: definitions, methods, and applications

Interpretable machine learning: definitions, methods, and applications

14 Jan 2019arXiv:1901.04592archive 2025-07-28

W. James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, Bin Yu

Official code for using / reproducing ACD (ICLR 2019) from the paper "Hierarchical interpretations for neural network predictions" https://arxiv.org/abs/1806.05337

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="1901.04592")

Code

Syntology Ran 2 of 27 code samples harvested from 1 repository linked to this paper; 25 have no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: community (archive-listed): 27 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

csinva/imodels officialmentioned on GitHubMIT report
csinva/hierarchical-dnn-interpretations mentioned on GitHubpytorchMIT report
csinva/local-vae mentioned on GitHubpytorch report
csinva/transformation-importance 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

27 samples harvested; 2 ran; 2 honoured the contract we drafted; 25 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.

2ran · honoured contract
25unverified

Licence: 0 of the 27 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 csinva/hierarchical-dnn-interpretations. “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.

calc_pad csinva/hierarchical-dnn-interpretations/acd/util/conv2dnp.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 54e4782533ba8866 · report
calc_size csinva/hierarchical-dnn-interpretations/acd/util/conv2dnp.py community (archive-listed) ran · honoured contract MIT (permissive) · 4100b072ce597ce6 · report
agglomerate csinva/hierarchical-dnn-interpretations/acd/agglomeration/agg_1d.py community (archive-listed) unverified MIT (permissive) · 33d9d5e45e5d68c0 · report
agglomerate csinva/hierarchical-dnn-interpretations/acd/agglomeration/agg_2d.py community (archive-listed) unverified MIT (permissive) · 7eae009e30183429 · report
cd csinva/hierarchical-dnn-interpretations/acd/scores/cd.py community (archive-listed) unverified MIT (permissive) · be288b6f3d3d398a · report
cd_generic csinva/hierarchical-dnn-interpretations/acd/scores/cd.py community (archive-listed) unverified MIT (permissive) · 8becf4c93688ea33 · report
cd_propagate_mnist csinva/hierarchical-dnn-interpretations/acd/scores/cd_architecture_specific.py community (archive-listed) unverified MIT (permissive) · 7930da855e30bb01 · report
cd_propagate_resnet csinva/hierarchical-dnn-interpretations/acd/scores/cd_architecture_specific.py community (archive-listed) unverified MIT (permissive) · 5120f7225c37624b · report
cd_text csinva/hierarchical-dnn-interpretations/acd/scores/cd.py community (archive-listed) unverified MIT (permissive) · d5f59990e6fe26e2 · report
cd_track_vgg csinva/hierarchical-dnn-interpretations/acd/scores/cd_architecture_specific.py community (archive-listed) unverified MIT (permissive) · 9f35efb88f5d2085 · report
collapse_tree csinva/hierarchical-dnn-interpretations/acd/agglomeration/agg_1d.py community (archive-listed) unverified MIT (permissive) · 3094108dbe03f52e · report
discrete_cmap csinva/hierarchical-dnn-interpretations/visualization/viz_2d.py community (archive-listed) unverified MIT (permissive) · 0fbfcd3ecb36c8bf · report
extract_sliding_windows_gradw csinva/hierarchical-dnn-interpretations/acd/util/conv2dnp.py community (archive-listed) unverified MIT (permissive) · 9c3f257866bb5fb0 · report
get_im_and_label csinva/hierarchical-dnn-interpretations/dsets/imagenet/dset.py community (archive-listed) unverified MIT (permissive) · f4beec75da6f8e0d · report
gradient_times_input_scores csinva/hierarchical-dnn-interpretations/acd/scores/score_funcs.py community (archive-listed) unverified MIT (permissive) · 557ddf3dd7b26d8b · report
ig_scores_1d csinva/hierarchical-dnn-interpretations/acd/scores/score_funcs.py community (archive-listed) unverified MIT (permissive) · b5ed9dfff1bbb2d1 · report
ig_scores_2d csinva/hierarchical-dnn-interpretations/acd/scores/score_funcs.py community (archive-listed) unverified MIT (permissive) · d589fb3829819544 · report
load_data csinva/hierarchical-dnn-interpretations/dsets/imagenet/dset.py community (archive-listed) unverified MIT (permissive) · 46f245f91c8c2e4a · report
pred_ims csinva/hierarchical-dnn-interpretations/dsets/imagenet/dset.py community (archive-listed) unverified MIT (permissive) · 170ff6204f66b748 · report
propagate_batchnorm2d csinva/hierarchical-dnn-interpretations/acd/scores/cd_propagate.py community (archive-listed) unverified MIT (permissive) · 2c90ac9573576d86 · report
propagate_conv_linear csinva/hierarchical-dnn-interpretations/acd/scores/cd_propagate.py community (archive-listed) unverified MIT (permissive) · 9e337dcd6fa467df · report
propagate_pooling csinva/hierarchical-dnn-interpretations/acd/scores/cd_propagate.py community (archive-listed) unverified MIT (permissive) · 1b19ddbd7737cc58 · report
refine_scores csinva/hierarchical-dnn-interpretations/acd/agglomeration/agg_2d.py community (archive-listed) unverified MIT (permissive) · 35f2273c5de00174 · report
threshold_scores csinva/hierarchical-dnn-interpretations/acd/agglomeration/agg_1d.py community (archive-listed) unverified MIT (permissive) · 6b39e8b9e90c1d43 · report
threshold_scores csinva/hierarchical-dnn-interpretations/acd/agglomeration/agg_2d.py community (archive-listed) unverified MIT (permissive) · 2ae7daa6e619d55a · report
visualize_batch_preds csinva/hierarchical-dnn-interpretations/visualization/viz_2d.py community (archive-listed) unverified MIT (permissive) · e02745f340467d1d · report
word_heatmap csinva/hierarchical-dnn-interpretations/visualization/viz_1d.py community (archive-listed) unverified MIT (permissive) · afaa71c3c23899ba · report

Tasks

BIG-bench Machine LearningFeature ImportanceInterpretable Machine Learning

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