SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.06292 · 2019

ProtoAttend: Attention-Based Prototypical Learning

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 1 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/1902.06292.json · badge: /api/ran/1902.06292.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
ZJUHSY/2020- canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
aced125/sparsemax community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
si-qi/protoattend community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
flatten_all_but_nth_dim Ran
ran; our contract draft was wrong, not the code
aced125/sparsemax/sparsemax/utils.py
code served (permissive licence) · get_code("32ac3d67805b2251")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

class Context:
    def __init__(self, dim):
        self.dim = dim
        self.original_size = None

ctx = Context(dim=1)
x = torch.randn(2, 3, 4, 5)

ARGS = {
    "ctx": ctx,
    "x": x,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
relational_attention Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZJUHSY/2020-/model.py
pointer only (licence: NONE) · get_code("ce92cc99dd76380b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZJUHSY/2020- when it was checked. 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.

unflatten_all_but_nth_dim Ran
ran; our contract draft was wrong, not the code
aced125/sparsemax/sparsemax/utils.py
code served (permissive licence) · get_code("bdec64ff3f52a1cc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

class Context:
    def __init__(self):
        self.original_size = (3, 2, 4, 5)
        self.dim = 1

ctx = Context()
x = torch.randn(2, 3, 4, 5)

ARGS = {
    "ctx": ctx,
    "x": x,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
resnet_layer Not yet run
unverified (harvested, no recorded run)
si-qi/protoattend/model.py
code served (permissive licence) · get_code("ae96c336f5bbf25c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
flatten_all_but_nth_dim 3 other papers
3 later · 2 only as an assembly brick
2309.12673 (2023-09)
On Sparse Modern Hopfield Model
2404.03827 (2024-04)
Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
2404.03828 (2024-04)
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
unflatten_all_but_nth_dim 3 other papers
3 later · 2 only as an assembly brick
2309.12673 (2023-09)
On Sparse Modern Hopfield Model
2404.03827 (2024-04)
Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
2404.03828 (2024-04)
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

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 propose a novel inherently interpretable machine learning method that bases decisions on few relevant examples that we call prototypes. Our method, ProtoAttend, can be integrated into a wide range of neural network architectures including pre-trained models. It utilizes an attention mechanism that relates the encoded representations to samples in order to determine prototypes. The resulting model outperforms state of the art in three high impact problems without sacrificing accuracy of the original model: (1) it enables high-quality interpretability that outputs samples most relevant to the decision-making (i.e. a sample-based interpretability method); (2) it achieves state of the art confidence estimation by quantifying the mismatch across prototype labels; and (3) it obtains state of the art in distribution mismatch detection. All this can be achieved with minimal additional test time and a practically viable training time computational cost.

For agents

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

get_harvested_code_for_paper("1902.06292")
get_code_for_paper("1902.06292")
have("1902.06292")

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

curl https://syntology.ai/api/ran/1902.06292.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.06292.svg)](https://syntology.ai/paper/1902.06292)

Connect an agent — have() is free.