SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.06559 · 2017

Active One-shot Learning

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 failure of our instrument; 0 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/1702.06559.json · badge: /api/ran/1702.06559.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
markpwoodward/active_osl canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
episode Ran
ran; our contract draft was wrong, not the code
markpwoodward/active_osl/model.py
code served (permissive licence) · get_code("33aea1a29953d87a")
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
import torch.nn as nn

torch.manual_seed(0)

# Define a minimal Simulator class
class Simulator:
    def __init__(self, batch_size, num_actions, observation_dim):
        self.batch_size = batch_size
        self.num_actions = num_actions
        self.observation_dim = observation_dim
        self.step_count = 0
    
    def get_observation(self):
        """Returns observation tensor of shape (batch_size, observation_dim)"""
        return torch.randn(self.batch_size, self.observation_dim)
    
    def do_step(self, actions):
        """Takes actions and advances simulation"""
        self.step_count += 1

# Define a minimal Agent class
class Agent(nn.Module):
    def __init__(self, observation_dim, num_actions, batch_size):
        super().__init__()
        self.observation_dim = observation_dim
        self.num_actions = num_actions
        self.batch_size = batch_size
        self.fc = nn.Linear(observation_dim, num_actions)
    
    def next_action(self, observation):
        """
        Args:
            observation: tensor of shape (batch_size, observation_dim)
        
        Returns:
            (a_t, q_t)
            a_t: tensor of shape (batch_size, num_actions) with int32 actions
            q_t: tensor of shape (batch_size, num_actions) with float32 q-values
        """
        # Compute q-values
        q_t = self.fc(observation)  # (batch_size, num_actions)
        
        # Choose actions (argmax per sample)
        a_t = torch.argmax(q_t, dim=1, keepdim=True).int()  # (batch_size, 1)
        # Expand to (batch_size, num_actions) for consistency
        a_t = a_t.expand(self.batch_size, self.num_actions).int()
        
        return a_t, q_t

# Define params as a simple class
class Params:
    def __init__(self, time_steps):
        self.time_steps = time_steps

# Construct arguments
batch_size = 2
num_actions = 3
observation_dim = 4
time_steps = 5

sim = Simulator(batch_size=batch_size, num_actions=num_actions, observation_dim=observation_dim)
agent = Agent(observation_dim=observation_dim, num_actions=num_actions, batch_size=batch_size)
params = Params(time_steps=time_steps)

ARGS = {
    "sim": sim,
    "agent": agent,
    "params": params
}
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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Recent advances in one-shot learning have produced models that can learn from a handful of labeled examples, for passive classification and regression tasks. This paper combines reinforcement learning with one-shot learning, allowing the model to decide, during classification, which examples are worth labeling. We introduce a classification task in which a stream of images are presented and, on each time step, a decision must be made to either predict a label or pay to receive the correct label. We present a recurrent neural network based action-value function, and demonstrate its ability to learn how and when to request labels. Through the choice of reward function, the model can achieve a higher prediction accuracy than a similar model on a purely supervised task, or trade prediction accuracy for fewer label requests.

For agents

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

get_harvested_code_for_paper("1702.06559")
get_code_for_paper("1702.06559")
have("1702.06559")

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

curl https://syntology.ai/api/ran/1702.06559.json

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

[![Syntology run record](https://syntology.ai/api/ran/1702.06559.svg)](https://syntology.ai/paper/1702.06559)

Connect an agent — have() is free.