SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.06007 · 2026

PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue

Jinho Choi, Hyunbae Jeon

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 1 has no contract verdict; 3 failures of our instrument; 2 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/2605.06007.json · badge: /api/ran/2605.06007.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
HarryJeon24/PersonaStudyKit canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
hash_password Ran
ran; our contract draft was wrong, not the code
HarryJeon24/PersonaStudyKit/bot_core.py
code served (permissive licence) · get_code("9001d3560a788a36")
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 str. 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 hashlib

# Construct valid arguments for hash_password
password = "my_secure_password_123"

ARGS = {
    "password": password
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
load_credentials Ran
ran; our contract draft was wrong, not the code
HarryJeon24/PersonaStudyKit/bot_core.py
code served (permissive licence) · get_code("46635c89c2cded17")
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 dict. 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 os
import re
import json
import tempfile
from unittest.mock import MagicMock
from queue import Queue

# Create a temporary directory and a mock credentials file for testing
temp_dir = tempfile.mkdtemp()
credentials_file = os.path.join(temp_dir, 'user_credentials.json')

# Write a sample credentials file
sample_credentials = {
    'username': 'testuser',
    'password': 'testpass',
    'api_key': 'test_api_key_123'
}

with open(credentials_file, 'w', encoding='utf-8') as f:
    json.dump(sample_credentials, f)

# Set up the global ui_queue for gui_print to work
ui_queue = None

ARGS = {
    'filename': credentials_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
colorama — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
register_user Ran
ran; our contract draft was wrong, not the code
HarryJeon24/PersonaStudyKit/bot_core.py
code served (permissive licence) · get_code("5015d1109f873c1c")
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 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 os
import re
import json
import hashlib
from colorama import Fore, init
import tempfile
import shutil

# Initialize colorama
init(autoreset=True)

# Set up a temporary directory for the test
test_dir = tempfile.mkdtemp()
original_dir = os.getcwd()
os.chdir(test_dir)

# Define ARGS for the register_user function
ARGS = {
    'username': 'testuser',
    'password': 'testpassword123'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
colorama — 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 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
user_exists Ran
ran on a synthesized input
HarryJeon24/PersonaStudyKit/db.py
code served (permissive licence) · get_code("e589691c9126ccaa")
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 bool, ndim 0, 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 os
import sqlite3
import tempfile

# Set up environment for sqlite backend (default)
os.environ['DB_BACKEND'] = 'sqlite'

# Create a temporary database file
temp_db = tempfile.NamedTemporaryFile(delete=False, suffix='.db')
db_path = temp_db.name
temp_db.close()

os.environ['DB_NAME'] = db_path

# Initialize the database with a users table and sample data
conn = sqlite3.connect(db_path)
c = conn.cursor()
c.execute('''CREATE TABLE users 
             (username TEXT PRIMARY KEY, password TEXT, role TEXT, linked_researcher TEXT)''')
c.execute("INSERT INTO users VALUES (?, ?, ?, ?)", 
          ('testuser', 'hashedpassword123', 'admin', 'researcher1'))
conn.commit()
conn.close()

# Define ARGS for user_exists function
ARGS = {
    'username': 'testuser'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
google — 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 — no output shape is stated: observe_signature.py could not observe it (call:OperationalError)
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_configs Not yet run
unverified (harvested, no recorded run)
HarryJeon24/PersonaStudyKit/db.py
code served (permissive licence) · get_code("fdbed1fde2ca90df")
How it ran

no invocation recorded.

get_user Not yet run
unverified (harvested, no recorded run)
HarryJeon24/PersonaStudyKit/db.py
code served (permissive licence) · get_code("85f8d137aa6545e6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

As spoken dialogue systems expand beyond traditional assistant roles to encompass diverse personas-such as authoritative instructors, uncooperative merchants, or distracted workers-they require distinct, human-like turn-taking behaviors to maintain psychological immersion. However, current full-duplex systems often default to a rigid, overly accommodating "always-yield" policy during overlapping speech, which severely undermines character consistency for non-submissive roles. Evaluating alternative, persona-specific turntaking strategies through empirical user studies is challenging because building real-time full-duplex test environments requires substantial engineering overhead. To address this, we present PersonaKit (PK), an opensource, low-latency web platform for the rapid prototyping and evaluation of conversational agents. Using intuitive JSON configurations, researchers can define personas, specify probabilistic interruption-handling behaviors (e.g., yield, hold, bridge, or override), and automatically deploy comparative A/B surveys. Through an in-the-wild evaluation with 8 distinct personas, we demonstrate that PersonaKit provides an extensible, end-to-end framework for studying complex sociolinguistic behaviors in next-generation spoken agents.

For agents

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

get_harvested_code_for_paper("2605.06007")
get_code_for_paper("2605.06007")
have("2605.06007")

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

curl https://syntology.ai/api/ran/2605.06007.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.06007.svg)](https://syntology.ai/paper/2605.06007)

Connect an agent — have() is free.