SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.00495 · 2022

Searching for Structure in Unfalsifiable Claims

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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 5 have no contract verdict; 1 failure of our instrument; 2 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/2209.00495.json · badge: /api/ran/2209.00495.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
captaine/searching-for-structure-in-unfalsifiable-claims canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
Hbeta_torch Ran
ran on a synthesized input
captaine/searching-for-structure-in-unfalsifiable-claims/snack/embedding/utils/binary_search.py
code served (permissive licence) · get_code("fdc87b840503cdc1")
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)

# Construct a small distance matrix D
# This should be a 2D tensor of pairwise distances
D = torch.tensor([
    [0.0, 1.5, 2.3, 0.8],
    [1.5, 0.0, 1.2, 2.1]
], dtype=torch.float32)

ARGS = {
    "D": D,
    "beta": 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 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
cauchy_kernel Ran
ran on a synthesized input
captaine/searching-for-structure-in-unfalsifiable-claims/snack/embedding/utils/kernels.py
code served (permissive licence) · get_code("47493b1d2bf867f4")
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 2, dtype family float, shape (2, 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 torch
import numpy as np

torch.manual_seed(0)

# The function cauchy_kernel takes:
# 1. distance_squared: a tensor or numeric value representing squared distances
# 2. degree: an int parameter (default=1)

# Create a small distance_squared tensor
# Using distance_squared function as shown: (x_i - x_j) ** 2
x_i = torch.randn(2, 4)
x_j = torch.randn(2, 4)
distance_squared_value = (x_i - x_j) ** 2

ARGS = {
    "distance_squared": distance_squared_value,
    "degree": 1
}
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 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
euclidean_distance_squared Ran
ran on a synthesized input
captaine/searching-for-structure-in-unfalsifiable-claims/snack/embedding/utils/kernels.py
code served (permissive licence) · get_code("fcc98d7b55b4639b")
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 2, dtype family float, shape (2, 2) 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

torch.manual_seed(0)

# The function euclidean_distance_squared takes a single parameter Y
# It expects Y to be a 2D tensor (matrix)
# The function performs:
# 1. sum_Y = torch.sum(Y * Y, 1) - sum of squares along dimension 1
# 2. num = -2.0 * torch.mm(Y, Y.t()) - matrix multiplication with transpose
# 3. Returns a distance matrix

# Create a small 2D tensor with shape (2, 4) - batch size 2, dimension 4
Y = torch.randn(2, 4)

ARGS = {
    "Y": Y
}
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 2, dtype family float, shape (2, 2) — shape (2, 2) 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
prevent_values_being_too_low Ran
ran on a synthesized input
captaine/searching-for-structure-in-unfalsifiable-claims/snack/embedding/tsne.py
code served (permissive licence) · get_code("f70435d0297727ae")
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 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Q should be a tensor that can be compared with tolerance
# The function uses torch.max(Q, tolerance) which broadcasts and compares element-wise
Q = torch.tensor([[1e-13, 2e-13, 3e-13, 4e-13],
                   [5e-13, 6e-13, 7e-13, 8e-13]], dtype=torch.float32)

tolerance = torch.tensor([1e-12], dtype=torch.float32)

ARGS = {
    "Q": Q,
    "tolerance": tolerance
}
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 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
unscaled_student_t_prop_density Ran
ran on a synthesized input
captaine/searching-for-structure-in-unfalsifiable-claims/snack/embedding/utils/kernels.py
code served (permissive licence) · get_code("a24518b184de4639")
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 2, dtype family float, shape (2, 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 torch
import numpy as np

torch.manual_seed(0)

# The function takes three parameters:
# - distance: likely a tensor or array of distances
# - distibution_dim: int, defaults to 1
# - degree: int, defaults to 3

# Construct a small distance tensor
distance = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                         [0.5, 1.5, 2.5, 3.5]])

# Define the arguments dictionary
ARGS = {
    "distance": distance,
    "distibution_dim": 2,
    "degree": 5
}
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 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
x2p_torch Ran
ran; our contract draft was wrong, not the code
captaine/searching-for-structure-in-unfalsifiable-claims/snack/embedding/utils/binary_search.py
code served (permissive licence) · get_code("2a0e73fbd575f66c")
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 2, dtype family float, shape (2, 2) 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

torch.manual_seed(0)

# Create a small input tensor X with shape (n_samples, n_features)
# Using distinct sizes: 2 samples, 4 features
X = torch.randn(2, 4)

# Define parameters for x2p_torch
tol = 1e-05
perplexity = 30.0

ARGS = {
    "X": X,
    "tol": tol,
    "perplexity": perplexity,
}
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 2, dtype family float, shape (2, 2) — shape (2, 2) 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
pca_torch Not yet run
unverified (harvested, no recorded run)
captaine/searching-for-structure-in-unfalsifiable-claims/snack/embedding/utils/dimensionality_reduction.py
code served (permissive licence) · get_code("e67350daa5b9bd57")
How it ran

no invocation recorded.

post_hoc_metric_given_embedding_and_triplets Not yet run
unverified (harvested, no recorded run)
captaine/searching-for-structure-in-unfalsifiable-claims/snack/datamodule/metrics.py
code served (permissive licence) · get_code("86df641625006594")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 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
pca_torch 1 other paper
1 dated earlier
2207.05500 (2022-07)
Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection
post_hoc_metric_given_embedding_and_triplets 1 other paper
1 later
2308.16900 (2023-08)
Learning to Taste : A Multimodal Wine Dataset
x2p_torch 1 other paper
1 dated earlier
2207.05500 (2022-07)
Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection

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

Social media platforms give rise to an abundance of posts and comments on every topic imaginable. Many of these posts express opinions on various aspects of society, but their unfalsifiable nature makes them ill-suited to fact-checking pipelines. In this work, we aim to distill such posts into a small set of narratives that capture the essential claims related to a given topic. Understanding and visualizing these narratives can facilitate more informed debates on social media. As a first step towards systematically identifying the underlying narratives on social media, we introduce PAPYER, a fine-grained dataset of online comments related to hygiene in public restrooms, which contains a multitude of unfalsifiable claims. We present a human-in-the-loop pipeline that uses a combination of machine and human kernels to discover the prevailing narratives and show that this pipeline outperforms recent large transformer models and state-of-the-art unsupervised topic models.

For agents

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

get_harvested_code_for_paper("2209.00495")
get_code_for_paper("2209.00495")
have("2209.00495")

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

curl https://syntology.ai/api/ran/2209.00495.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.00495.svg)](https://syntology.ai/paper/2209.00495)

Connect an agent — have() is free.