Papers › This Probably Looks Exactly Like That: An Invertible Prototypical Network

This Probably Looks Exactly Like That: An Invertible Prototypical Network

16 Jul 2024arXiv:2407.12200archive 2025-07-28

Zachariah Carmichael, Timothy Redgrave, Daniel Gonzalez Cedre, Walter J. Scheirer

We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural network, represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations, but a human-machine semantic gap continues to haunt current approaches. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. From this, we posit that invertibly learning prototypes as distributions over the latent space provides more robust, expressive, and interpretable modeling. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models. ProtoFlow (1) sets a new state-of-the-art in joint generative and predictive modeling and (2) achieves predictive performance comparable to existing prototypical neural networks while enabling richer interpretation.

PaperPDFCodeCode Syntology ran

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: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 13 ran (7 with no instrument failure; 6 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.

craymichael/protoflow officialmentioned in paperpytorchGPL-2.0Syntology: 16 samples, 13 ran (6 instrument-failed) · 3 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: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
1ran; the contract check could not run
6ran
3unverified

Licence: 16 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 craymichael/protoflow. “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.

craymichael/protoflow official repository 16 samples, 13 ran (6 instrument-failed) · 3 unverified
calculate_matmul protoflow/gmm.py ran; the contract check could not run (RAISES) GPL-2.0 (copyleft) · pointer only · 7252b82bcb3357b6 · report fixture: signature mat_a:Tensor/4/float, mat_b:Tensor/4/float · returned Tensor · level recorded 2026-09-24
compute_softdtw in 9 papers protoflow/kmeans/soft_dtw_cuda.py ran GPL-2.0 (copyleft) · pointer only · 168a9cabc7a9663b · report fixture: signature D:ndarray/3/float, gamma:float/0/float, bandwidth:int/0/int · returned ndarray · level recorded 2026-09-24
compute_softdtw_backward in 9 papers protoflow/kmeans/soft_dtw_cuda.py ran GPL-2.0 (copyleft) · pointer only · ab0a02fe3f0bce01 · report fixture: signature D_:ndarray/3/float, R:ndarray/3/float, gamma:float/0/float, bandwidth:int/0/int · returned ndarray · level recorded 2026-09-24
consistency_loss in 19 papers protoflow/training.py ran GPL-2.0 (copyleft) · pointer only · c582f1abfdf87bbf · report fixture: signature all_log_probs:Tensor/2/float, z:Tensor/2/float, sldj:Tensor/1/float, x_shape:Tensor/4/float, y:Tensor/1/int, k:int/0/int · returned Tensor · level recorded 2026-09-24
convert_legacy_config protoflow/utils.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · 7294ea39eb1f484b · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-24
dict_to_namespace in 9 papers protoflow/utils.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · 32ba9344b7753cf9 · report fixture: signature d:dict/0/? · returned Namespace · level recorded 2026-09-24
elbo_bpd protoflow/metrics.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · e89baae0a1437b16 · report fixture: signature log_prob:Tensor/4/float, x_shape:Size/1/int · returned Tensor · level recorded 2026-09-24
elbo_nats denseflow/utils/loss.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · d232e453e386a533 · report fixture: signature model:callable/0/?, x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
linear_rampup in 33 papers protoflow/training.py ran · honoured contract fingerprinted GPL-2.0 (copyleft) · pointer only · 4eae3eb7fc10b826 · report fixture: signature final_value:float/0/float, epoch:int/0/int, num_epochs:int/0/int, start_epoch:int/0/int · returned float · level recorded 2026-09-24
loglik_bpd denseflow/utils/loss.py ran GPL-2.0 (copyleft) · pointer only · 9f24b4c6cbb5e19f · report fixture: signature model:callable/0/?, x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
loglik_nats denseflow/utils/loss.py ran GPL-2.0 (copyleft) · pointer only · 9bff0117086fa0a0 · report fixture: signature model:callable/0/?, x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
timed_run protoflow/kmeans/soft_dtw_cuda.py ran GPL-2.0 (copyleft) · pointer only · 89a318a54beb022e · report fixture: signature a:Tensor/3/float, b:Tensor/3/float, sdtw:callable/0/? · returned tuple · level recorded 2026-09-25
z_log_prob protoflow/training.py ran · our draft was wrong fingerprinted GPL-2.0 (copyleft) · pointer only · b9bb230c9c9c7a26 · report fixture: signature all_log_probs:Tensor/2/float, y:Tensor/1/int · returned Tensor · level recorded 2026-09-24
calculate_matmul_n_times protoflow/gmm.py unverified GPL-2.0 (copyleft) · pointer only · 3669431e2653a3ed · report
get_dataset in 285 papers protoflow/datasets.py unverified GPL-2.0 (copyleft) · pointer only · a30a1acd1c8065d4 · report
write_shm_meta protoflow/datasets.py unverified GPL-2.0 (copyleft) · pointer only · d8c19986ae830c3f · 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