SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.01357 · 2018

Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 3 have no contract verdict; 1 failure of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/1809.01357.json · badge: /api/ran/1809.01357.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
mhw32/rubric-sampling-public canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
mhw32/rubric-sampling-public/rubric_sampling/experiments/models.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). If your copy returns the same type, ndim and shape 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)

# The function swish takes a single parameter 'x' which is used with:
# - torch.sigmoid(x) - requires a tensor
# - x * ... - requires a tensor that supports multiplication
# So x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
p_program_elbo Ran
ran on a synthesized input
mhw32/rubric-sampling-public/rubric_sampling/experiments/loss.py
code served (permissive licence) · get_code("c3152b97d79c813a")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import torch.nn.functional as F

torch.manual_seed(0)

# Set up small tensors with distinct dimensions for clarity
batch_size = 2
seq_length = 5
vocab_size = 10
latent_dim = 4

# seq: (n, s) tensor of token indices
seq = torch.randint(0, vocab_size, (batch_size, seq_length))

# seq_logits: (n, s, v) tensor of logits over vocabulary
seq_logits = torch.randn(batch_size, seq_length, vocab_size)

# z: (n, latent_dim) latent variable sample
z = torch.randn(batch_size, latent_dim)

# z_mu: (n, latent_dim) mean of q(z|x)
z_mu = torch.randn(batch_size, latent_dim)

# z_logvar: (n, latent_dim) log-variance of q(z|x)
z_logvar = torch.randn(batch_size, latent_dim)

# annealing_factor: scalar for KL weighting
annealing_factor = 1.0

ARGS = {
    "seq": seq,
    "seq_logits": seq_logits,
    "z": z,
    "z_mu": z_mu,
    "z_logvar": z_logvar,
    "annealing_factor": annealing_factor,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
p_program_label_elbo Ran
ran on a synthesized input
mhw32/rubric-sampling-public/rubric_sampling/experiments/loss.py
code served (permissive licence) · get_code("6c1e981c6d209765")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import torch.nn.functional as F

torch.manual_seed(0)

# Tiny dimensions for batch, sequence length, vocabulary, label dimension, latent dimension
batch_size = 2
seq_len = 5
vocab_size = 10
label_dim = 3
latent_dim = 4

# seq: (batch_size, seq_len) - token indices
seq = torch.randint(0, vocab_size, (batch_size, seq_len))

# seq_logits: (batch_size, seq_len, vocab_size) - logits for each token position
seq_logits = torch.randn(batch_size, seq_len, vocab_size)

# label: (batch_size, label_dim) - binary labels
label = torch.randint(0, 2, (batch_size, label_dim)).float()

# label_out: (batch_size, label_dim) - Bernoulli parameters (probabilities)
label_out = torch.sigmoid(torch.randn(batch_size, label_dim))

# z: (batch_size, latent_dim) - sampled latent vector
z = torch.randn(batch_size, latent_dim)

# z_mu: (batch_size, latent_dim) - mean of q(z|x,y)
z_mu = torch.randn(batch_size, latent_dim)

# z_logvar: (batch_size, latent_dim) - log-variance of q(z|x,y)
z_logvar = torch.randn(batch_size, latent_dim)

ARGS = {
    "seq": seq,
    "seq_logits": seq_logits,
    "label": label,
    "label_out": label_out,
    "z": z,
    "z_mu": z_mu,
    "z_logvar": z_logvar,
    "annealing_factor": 1.0,
    "alpha_program": 1.0,
    "alpha_label": 1.0,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
p_program_label_melbo Ran
ran on a synthesized input
mhw32/rubric-sampling-public/rubric_sampling/experiments/loss.py
code served (permissive licence) · get_code("bb59142c78cc142e")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import torch.nn.functional as F

torch.manual_seed(0)

# Set up tensor dimensions
batch_size = 2
seq_len = 5
vocab_size = 10
latent_dim = 4
label_dim = 3

# Create tensors for the function arguments
seq = torch.randint(0, vocab_size, (batch_size, seq_len))
seq_logits_xy = torch.randn(batch_size, seq_len, vocab_size)
seq_logits_x = torch.randn(batch_size, seq_len, vocab_size)
seq_logits_y = torch.randn(batch_size, seq_len, vocab_size)

label = torch.randint(0, 2, (batch_size, label_dim)).float()

label_out_xy = torch.sigmoid(torch.randn(batch_size, label_dim))
label_out_x = torch.sigmoid(torch.randn(batch_size, label_dim))
label_out_y = torch.sigmoid(torch.randn(batch_size, label_dim))

z_xy = torch.randn(batch_size, latent_dim)
z_mu_xy = torch.randn(batch_size, latent_dim)
z_logvar_xy = torch.randn(batch_size, latent_dim)

z_x = torch.randn(batch_size, latent_dim)
z_mu_x = torch.randn(batch_size, latent_dim)
z_logvar_x = torch.randn(batch_size, latent_dim)

z_y = torch.randn(batch_size, latent_dim)
z_mu_y = torch.randn(batch_size, latent_dim)
z_logvar_y = torch.randn(batch_size, latent_dim)

length = torch.randint(3, seq_len + 1, (batch_size,))

ARGS = {
    'seq': seq,
    'length': length,
    'label': label,
    'seq_logits_xy': seq_logits_xy,
    'label_out_xy': label_out_xy,
    'z_xy': z_xy,
    'z_mu_xy': z_mu_xy,
    'z_logvar_xy': z_logvar_xy,
    'seq_logits_x': seq_logits_x,
    'label_out_x': label_out_x,
    'z_x': z_x,
    'z_mu_x': z_mu_x,
    'z_logvar_x': z_logvar_x,
    'seq_logits_y': seq_logits_y,
    'label_out_y': label_out_y,
    'z_y': z_y,
    'z_mu_y': z_mu_y,
    'z_logvar_y': z_logvar_y,
    'annealing_factor': 1.0,
    'alpha_program': 1.0,
    'alpha_label': 1.0,
    'lambda_program': 1.0,
    'lambda_label': 1.0,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
build_rank_map_from_count_map Not yet run
unverified (harvested, no recorded run)
mhw32/rubric-sampling-public/rubric_sampling/experiments/datasets.py
code served (permissive licence) · get_code("7ec7551b16cec75e")
How it ran

no invocation recorded.

build_zipf_map Not yet run
unverified (harvested, no recorded run)
mhw32/rubric-sampling-public/rubric_sampling/experiments/datasets.py
code served (permissive licence) · get_code("c704b64855b7e5f8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 5 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
swish 206 other papers
2 dated earlier, 204 later · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 203 more not named here

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

In modern computer science education, massive open online courses (MOOCs) log thousands of hours of data about how students solve coding challenges. Being so rich in data, these platforms have garnered the interest of the machine learning community, with many new algorithms attempting to autonomously provide feedback to help future students learn. But what about those first hundred thousand students? In most educational contexts (i.e. classrooms), assignments do not have enough historical data for supervised learning. In this paper, we introduce a human-in-the-loop "rubric sampling" approach to tackle the "zero shot" feedback challenge. We are able to provide autonomous feedback for the first students working on an introductory programming assignment with accuracy that substantially outperforms data-hungry algorithms and approaches human level fidelity. Rubric sampling requires minimal teacher effort, can associate feedback with specific parts of a student's solution and can articulate a student's misconceptions in the language of the instructor. Deep learning inference enables rubric sampling to further improve as more assignment specific student data is acquired. We demonstrate our results on a novel dataset from Code.org, the world's largest programming education platform.

For agents

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

get_harvested_code_for_paper("1809.01357")
get_code_for_paper("1809.01357")
have("1809.01357")

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

curl https://syntology.ai/api/ran/1809.01357.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.01357.svg)](https://syntology.ai/paper/1809.01357)

Connect an agent — have() is free.