Papers › Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
Andrew Slavin Ross, Michael C. Hughes, Finale Doshi-Velez
Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on explanations for black-box models has produced tools (e.g. LIME) to show the implicit rules behind predictions, which can help us identify when models are right for the wrong reasons. However, these methods do not scale to explaining entire datasets and cannot correct the problems they reveal. We introduce a method for efficiently explaining and regularizing differentiable models by examining and selectively penalizing their input gradients, which provide a normal to the decision boundary. We apply these penalties both based on expert annotation and in an unsupervised fashion that encourages diverse models with qualitatively different decision boundaries for the same classification problem. On multiple datasets, we show our approach generates faithful explanations and models that generalize much better when conditions differ between training and test.
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):
get_harvested_code_for_paper(arxiv_id="1703.03717")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1703.03717", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1703.03717")
Code
Syntology 14 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.
By repository: official repository: 14 samples from 1 repository, 12 ran (12 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 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.
Licence: 0 of the 14 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 dtak/rrr. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
9817b40445c2c460 · report
fixture: signature p:float/0/float · returned bool · level recorded 2026-09-24 5eccb66a8fd6a7ad · report
fixture: signature row:tuple/1/str · returned list · level recorded 2026-09-25 17b25464218ca9f7 · report
fixture: signature row:list/1/list · returned bool · level recorded 2026-09-25 986bd42d6c370e36 · report
fixture: signature image:ndarray/2/int, digit:int/0/int, randomize:bool/0/bool, mult:int/0/int, all_digits:range/0/? · returned tuple · level recorded 2026-09-25 79b825acdeeb1e5d · report
fixture: signature test_size:float/0/float · returned tuple · level recorded 2026-09-25 35ae7d4c0d9d0a3f · report
fixture: signature model:callable/0/?, X:Tensor/2/float, cutoff:float/0/float · returned Tensor · level recorded 2026-09-25 202c34477ef03008 · report
fixture: signature l:list/1/int · returned list · level recorded 2026-09-25 781a2d98cab6f688 · report
fixture: signature rows:list/1/tuple · returned float · level recorded 2026-09-25 census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket rrr/multilayer_perceptron.py ran MIT (permissive) ·
fff341b836aa49d0 · report
fixture: signature y:ndarray/1/int · returned ndarray · level recorded 2026-09-25 census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket rrr/tensorflow_perceptron.py ran MIT (permissive) ·
d144728084cadb8c · report
fixture: signature y:ndarray/1/int · returned ndarray · level recorded 2026-09-25 census: 8 implementations from 11 papers, 4 distinct outputs across 2 buckets, one shared input per bucket rrr/multilayer_perceptron.py ran fingerprinted MIT (permissive) ·
fd6644bff4456444 · report
fixture: signature inputs:ndarray/2/float · returned ndarray · level recorded 2026-09-25 ff31ad55c2bc4916 · report
fixture: signature pred:str/0/str, pos:list/1/tuple, neg:list/1/tuple, maxwlen:int/0/int, maxwords:int/0/int, scale:NoneType/0/? · returned str · level recorded 2026-09-25 c106f94602bc64a0 · report
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