SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.03007 · ICML · 2023

Nonparametric Iterative Machine Teaching

Ivor Tsang, James Kwok, Chen Zhang, Weiyang Liu, Xiaofeng Cao

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2306.03007.json · badge: /api/ran/2306.03007.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
chen2hang/GraNT_NonparametricTeaching community
Papers with Code archive
3 ran · 1 no recorded run
chen2hang/INT_NonparametricTeaching community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
_get_global_sub_topk_idxs Ran
ran; our contract draft was wrong, not the code
chen2hang/GraNT_NonparametricTeaching/sampler.py
code served (permissive licence) · get_code("1f5ebbb5b70774a2")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# Create a small tensor of differences with shape (batch_size,)
# This represents differences for one batch
one_batch_diffs = torch.randn(10)

# Number of top-k elements to sample
sampling_cnt = 3

# Batch counter (which batch number this is)
cnt = 2

# Size of each batch
batch_size = 10

ARGS = {
    "one_batch_diffs": one_batch_diffs,
    "sampling_cnt": sampling_cnt,
    "cnt": cnt,
    "batch_size": batch_size,
}
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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
_get_one_batch_diffs Ran
ran; our contract draft was wrong, not the code
chen2hang/GraNT_NonparametricTeaching/sampler.py
code served (permissive licence) · get_code("23b4c6d9b1d57e61")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# Construct arguments for _get_one_batch_diffs
num_graphs = 2
batch_size = 6
num_classes = 10
output_dim = 10

# batch: tensor indicating which graph each node belongs to
# For 2 graphs with 6 nodes total, let's say graph 0 has 3 nodes, graph 1 has 3 nodes
batch = torch.tensor([0, 0, 0, 1, 1, 1])

# output: model predictions for each node (batch_size x num_classes)
output = torch.randn(6, num_classes)

# target_y: ground truth labels for each node (batch_size,)
target_y = torch.randint(0, num_classes, (6,))

# need_one_hot: whether to convert target_y to one-hot encoding
need_one_hot = True

ARGS = {
    "num_graphs": num_graphs,
    "batch": batch,
    "output": output,
    "target_y": target_y,
    "need_one_hot": need_one_hot,
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
_get_sampling_per_batch Ran
ran, honoured the contract we drafted
chen2hang/GraNT_NonparametricTeaching/sampler.py
code served (permissive licence) · get_code("1b3101b4b8539f64")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

# The function _get_sampling_per_batch takes three integer parameters
# and performs batch-wise sampling allocation with error correction.
# Let's construct valid arguments:

total_len = 100  # Total length of dataset
batch_size = 32  # Size of each batch
sampling_nums = 50  # Total number of samples to allocate across batches

ARGS = {
    "total_len": total_len,
    "batch_size": batch_size,
    "sampling_nums": sampling_nums
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
incremental Ran
ran, honoured the contract we drafted
chen2hang/INT_NonparametricTeaching/src/strategy.py
code served (permissive licence) · get_code("8c05b484d4a196b5")
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, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

torch.manual_seed(0)

ARGS = {
    "step": 10,
    "max_steps": 100,
    "min_interval": 1,
    "max_interval": 50,
    "n_increments": 5,
    "startup_ratio": 0.25
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
grant_sampler Not yet run
unverified (harvested, no recorded run)
chen2hang/GraNT_NonparametricTeaching/sampler.py
code served (permissive licence) · get_code("e7ab729ff77f165f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
incremental
brick of this paper's assembly: entry
1 other paper
1 later · 1 only as an assembly brick
2405.10531 (2024-05)
Nonparametric Teaching of Implicit Neural Representations

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 this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast convergence to a target model. However, existing IMT algorithms are solely based on parameterized families of target models. They mainly focus on convergence in the parameter space, resulting in difficulty when the target models are defined to be functions without dependency on parameters. To address such a limitation, we study a more general task -Nonparametric Iterative Machine Teaching (NIMT), which aims to teach nonparametric target models to learners in an iterative fashion. Unlike parametric IMT that merely operates in the parameter space, we cast NIMT as a functional optimization problem in the function space. To solve it, we propose both random and greedy functional teaching algorithms. We obtain the iterative teaching dimension (ITD) of the random teaching algorithm under proper assumptions, which serves as a uniform upper bound of ITD in NIMT. Further, the greedy teaching algorithm has a significantly lower ITD, which reaches a tighter upper bound of ITD in NIMT. Finally, we verify the correctness of our theoretical findings with extensive experiments in nonparametric scenarios. Our source code is available at https://github.com/ chen2hang/NonparametricTeaching.

For agents

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

get_harvested_code_for_paper("2306.03007")
get_code_for_paper("2306.03007")
have("2306.03007")

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

curl https://syntology.ai/api/ran/2306.03007.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.03007.svg)](https://syntology.ai/paper/2306.03007)

Connect an agent — have() is free.