SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.12200 · ECCV · 2024

This Probably Looks Exactly Like That: An Invertible Prototypical Network

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

arXiv · PDF · Open in the Atlas

Code that ran

13 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 12 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.12200.json · badge: /api/ran/2407.12200.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
craymichael/ProtoFlow canonical (classifier label)
classifier basis: census
13 ran · 3 no recorded run
FunctionStatusWhere it lives
calculate_matmul Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
craymichael/ProtoFlow/protoflow/gmm.py
pointer only (licence: GPL-2.0) · get_code("7252b82bcb3357b6")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_softdtw Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
craymichael/ProtoFlow/protoflow/kmeans/soft_dtw_cuda.py
pointer only (licence: GPL-2.0) · get_code("168a9cabc7a9663b")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_softdtw_backward Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
craymichael/ProtoFlow/protoflow/kmeans/soft_dtw_cuda.py
pointer only (licence: GPL-2.0) · get_code("ab0a02fe3f0bce01")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

consistency_loss Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/protoflow/training.py
pointer only (licence: GPL-2.0) · get_code("c582f1abfdf87bbf")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_legacy_config Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/protoflow/utils.py
pointer only (licence: GPL-2.0) · get_code("7294ea39eb1f484b")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dict_to_namespace Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/protoflow/utils.py
pointer only (licence: GPL-2.0) · get_code("32ba9344b7753cf9")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

elbo_bpd Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/protoflow/metrics.py
pointer only (licence: GPL-2.0) · get_code("e89baae0a1437b16")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

elbo_nats Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/denseflow/utils/loss.py
pointer only (licence: GPL-2.0) · get_code("d232e453e386a533")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

linear_rampup Ran
ran, honoured the contract we drafted
craymichael/ProtoFlow/protoflow/training.py
pointer only (licence: GPL-2.0) · get_code("4eae3eb7fc10b826")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

loglik_bpd Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/denseflow/utils/loss.py
pointer only (licence: GPL-2.0) · get_code("9f24b4c6cbb5e19f")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

loglik_nats Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/denseflow/utils/loss.py
pointer only (licence: GPL-2.0) · get_code("9bff0117086fa0a0")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

timed_run Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/protoflow/kmeans/soft_dtw_cuda.py
pointer only (licence: GPL-2.0) · get_code("89a318a54beb022e")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

z_log_prob Ran
ran; our contract draft was wrong, not the code
craymichael/ProtoFlow/protoflow/training.py
pointer only (licence: GPL-2.0) · get_code("b9bb230c9c9c7a26")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_matmul_n_times Not yet run
unverified (harvested, no recorded run)
craymichael/ProtoFlow/protoflow/gmm.py
pointer only (licence: GPL-2.0) · get_code("3669431e2653a3ed")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
craymichael/ProtoFlow/protoflow/datasets.py
pointer only (licence: GPL-2.0) · get_code("a30a1acd1c8065d4")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

write_shm_meta Not yet run
unverified (harvested, no recorded run)
craymichael/ProtoFlow/protoflow/datasets.py
pointer only (licence: GPL-2.0) · get_code("d8c19986ae830c3f")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, craymichael/ProtoFlow, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 2 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
elbo_nats 3 other papers
3 dated earlier
2007.02731 (2020-07)
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
2106.06245 (2021-06)
Model Selection for Bayesian Autoencoders
2305.04111 (2023-05)
Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling
loglik_nats 3 other papers
3 dated earlier
2007.02731 (2020-07)
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
2106.06245 (2021-06)
Model Selection for Bayesian Autoencoders
2305.04111 (2023-05)
Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling
timed_run 3 other papers
2 dated earlier, 1 later
2306.02693 (2023-06)
CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels
2404.02394 (2024-04)
Cohort-Individual Cooperative Learning for Multimodal Cancer Survival Analysis
2412.09501 (2024-12)
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
calculate_matmul 2 other papers
1 dated earlier, 1 later
2401.10191 (2024-01)
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
2606.25347 (2026-06)
Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
compute_softdtw 2 other papers
2 dated earlier
2306.02693 (2023-06)
CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels
2404.02394 (2024-04)
Cohort-Individual Cooperative Learning for Multimodal Cancer Survival Analysis
compute_softdtw_backward 2 other papers
2 dated earlier
2306.02693 (2023-06)
CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels
2404.02394 (2024-04)
Cohort-Individual Cooperative Learning for Multimodal Cancer Survival Analysis
linear_rampup 2 other papers
2 dated earlier
1912.13025 (2019-12)
Semi-Supervised Learning with Normalizing Flows
2006.08545 (2020-06)
Why Normalizing Flows Fail to Detect Out-of-Distribution Data
loglik_bpd 2 other papers
2 dated earlier
2007.02731 (2020-07)
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
2106.06245 (2021-06)
Model Selection for Bayesian Autoencoders

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.12200")
get_code_for_paper("2407.12200")
have("2407.12200")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.12200.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.12200.svg)](https://syntology.ai/paper/2407.12200)

Connect an agent — have() is free.