SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.04347 · 2020

Confidence sequences for sampling without replacement

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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 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/2006.04347.json · badge: /api/ran/2006.04347.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
wannabesmith/confseq_wor canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
gostevehoward/confseq canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
check_approx_equal Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gostevehoward/confseq/demo/ate_demo.py
code served (permissive licence) · get_code("1b969d6c5e72286a")
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) and returned bool, 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 numpy as np
import pandas as pd
import torch

# Analyze the function to understand what it needs:
# - name: string
# - actual: numpy array or pandas Series with .max() method and indexing
# - expected: numpy array or pandas Series with .max() method and indexing
# - tolerance: float (default 0.0001)

# The function calls:
# - np.abs() on (expected - actual)
# - .max() on the result
# - .to_numpy() on abs_errors (so it expects a pandas Series)
# - .nonzero()[0] on a boolean array
# - indexing with error_indexes on expected and actual

# Create test data as pandas Series
torch.manual_seed(0)

# Create small pandas Series with some differences within and outside tolerance
expected_data = pd.Series([1.0, 2.0, 3.0, 4.0, 5.0])
actual_data = pd.Series([1.00005, 2.0001, 3.05, 4.0, 5.0])

ARGS = {
    'name': 'test_values',
    'actual': actual_data,
    'expected': expected_data,
    'tolerance': 0.0001
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, pandas, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
ci_from_martingale_2D Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wannabesmith/confseq_wor/cswor/cswor.py
code served (permissive licence) · get_code("bb767a7250f18b7e")
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) 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 numpy as np

# Construct arguments for ci_from_martingale_2D
mu_hat = 2.5  # real number estimate of the mean

N = 100  # total population size (integer)

# Martingale vector: array of positive reals
# Create a vector where some values are < 1/alpha (0.05) and some are >= 1/alpha
mart_vec = np.array([0.01, 0.02, 0.5, 5.0, 20.0, 50.0])

# Possible null candidates (e.g., number of green balls in urn)
possible_m = np.array([0, 1, 2, 3, 4, 5])

# Confidence level
alpha = 0.05

# Search step parameter
search_step = 1

ARGS = {
    "mu_hat": mu_hat,
    "N": N,
    "mart_vec": mart_vec,
    "possible_m": possible_m,
    "alpha": alpha,
    "search_step": search_step
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — 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
form_predictions Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gostevehoward/confseq/demo/ate_demo.py
code served (permissive licence) · get_code("bb009376bd6e9abd")
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) and returned ndarray, ndim 1, dtype family float, shape (4,) 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 numpy as np

# Analyze the function:
# - outcomes: used in multiplication with selector, needs to be array-like
# - selector: used in multiplication with outcomes and cumsum, needs to be array-like
# - default_prediction: scalar value used to set lagged_means[0]

# Create small numpy arrays for outcomes and selector
outcomes = np.array([0.5, 0.7, 0.3, 0.9])
selector = np.array([1.0, 1.0, 0.0, 1.0])
default_prediction = 0.1

ARGS = {
    "outcomes": outcomes,
    "selector": selector,
    "default_prediction": default_prediction
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
logical_cs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wannabesmith/confseq_wor/cswor/cswor.py
code served (permissive licence) · get_code("f090dcf28fc2257c")
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) and returned tuple, ndim 2, 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 numpy as np

# Create sample data: array-like of reals between 0 and 1
x = np.array([0.2, 0.5, 0.8, 0.3, 0.6])

# Population size
N = 10

ARGS = {
    "x": x,
    "N": N
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — 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
DMHG_martingale Not yet run
unverified (harvested, no recorded run)
wannabesmith/confseq_wor/cswor/cswor.py
code served (permissive licence) · get_code("6f64efb3ca6b5e5e")
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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
check_approx_equal 3 other papers
2 dated earlier, 1 later
1810.08240 (2018-10)
Time-uniform, nonparametric, nonasymptotic confidence sequences
1906.09712 (2019-06)
Sequential estimation of quantiles with applications to A/B-testing and best-arm identification
2010.09686 (2020-10)
Estimating means of bounded random variables by betting
form_predictions 3 other papers
2 dated earlier, 1 later
1810.08240 (2018-10)
Time-uniform, nonparametric, nonasymptotic confidence sequences
1906.09712 (2019-06)
Sequential estimation of quantiles with applications to A/B-testing and best-arm identification
2010.09686 (2020-10)
Estimating means of bounded random variables by betting

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

Many practical tasks involve sampling sequentially without replacement (WoR) from a finite population of size $N$, in an attempt to estimate some parameter $θ^\star$. Accurately quantifying uncertainty throughout this process is a nontrivial task, but is necessary because it often determines when we stop collecting samples and confidently report a result. We present a suite of tools for designing confidence sequences (CS) for $θ^\star$. A CS is a sequence of confidence sets $(C_n)_{n=1}^N$, that shrink in size, and all contain $θ^\star$ simultaneously with high probability. We present a generic approach to constructing a frequentist CS using Bayesian tools, based on the fact that the ratio of a prior to the posterior at the ground truth is a martingale. We then present Hoeffding- and empirical-Bernstein-type time-uniform CSs and fixed-time confidence intervals for sampling WoR, which improve on previous bounds in the literature and explicitly quantify the benefit of WoR sampling.

For agents

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

get_harvested_code_for_paper("2006.04347")
get_code_for_paper("2006.04347")
have("2006.04347")

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

curl https://syntology.ai/api/ran/2006.04347.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.04347.svg)](https://syntology.ai/paper/2006.04347)

Connect an agent — have() is free.