SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.03753 · EMNLP · 2024

WILDVIS: Open Source Visualizer for Million-Scale Chat Logs in the Wild

Yejin Choi, Yuntian Deng, Xiang Ren, Jack Hessel, Wenting Zhao, Claire Cardie

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2409.03753.json · badge: /api/ran/2409.03753.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
da03/WildVisualizer canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
reservoir_sampling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
da03/WildVisualizer/embed_conversations_firstturn.py
code served (permissive licence) · get_code("1255aa2206e59096")
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 random
import tqdm

torch.manual_seed(0)

# Create a simple iterable - a list of integers
iterable = list(range(100))

# Define k as the sample size
k = 10

# Construct the ARGS dictionary
ARGS = {
    "iterable": iterable,
    "k": k
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — 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
reservoir_sampling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
da03/WildVisualizer/embed_conversations_firstturn_trytsne.py
code served (permissive licence) · get_code("49951f0611c8f5da")
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 random
import tqdm

torch.manual_seed(0)

# The function takes an iterable and k (number of samples to keep)
# It iterates through the iterable with tqdm progress bar
# and performs reservoir sampling

iterable = list(range(100))  # A simple iterable of integers
k = 10  # Number of samples to keep

ARGS = {
    "iterable": iterable,
    "k": k,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — 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
retrieve Ran
ran; our contract draft was wrong, not the code
da03/WildVisualizer/embed_conversations.py
code served (permissive licence) · get_code("514fccf5f99c7a9d")
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 sqlite3
import json
import tempfile
import os

# Create a temporary database with test data
temp_dir = tempfile.mkdtemp()
db_path = os.path.join(temp_dir, "test_cache.db")

# Set up database with cache table
conn = sqlite3.connect(db_path)
c = conn.cursor()
c.execute('''CREATE TABLE cache
             (key TEXT PRIMARY KEY, prompt TEXT, embedding TEXT)''')

# Insert test data
test_embedding = [0.1, 0.2, 0.3, 0.4]
c.execute('INSERT INTO cache VALUES (?, ?, ?)',
          ('test_key', 'test prompt', json.dumps(test_embedding)))
conn.commit()
conn.close()

ARGS = {
    'db_name': db_path,
    'key': 'test_key'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
get_language_distribution Not yet run
unverified (harvested, no recorded run)
da03/WildVisualizer/find_models.py
code served (permissive licence) · get_code("6befdf14c737d065")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 3 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 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.

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

The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions. However, the sheer volume of this data makes manually examining individual conversations impractical. To overcome this challenge, we introduce WILDVIS, an interactive tool that enables fast, versatile, and large-scale conversation analysis. WILDVIS provides search and visualization capabilities in the text and embedding spaces based on a list of criteria. To manage million-scale datasets, we implemented optimizations including search index construction, embedding precomputation and compression, and caching to ensure responsive user interactions within seconds. We demonstrate WILDVIS' utility through three case studies: facilitating chatbot misuse research, visualizing and comparing topic distributions across datasets, and characterizing user-specific conversation patterns. WILDVIS is open-source and designed to be extendable, supporting additional datasets and customized search and visualization functionalities.

For agents

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

get_harvested_code_for_paper("2409.03753")
get_code_for_paper("2409.03753")
have("2409.03753")

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

curl https://syntology.ai/api/ran/2409.03753.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.03753.svg)](https://syntology.ai/paper/2409.03753)

Connect an agent — have() is free.