SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.00483 · 2020

Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2011.00483.json · badge: /api/ran/2011.00483.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
vitouphy/usl_dialogue_metric canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
apply_word_drop Ran
ran on a synthesized input
vitouphy/usl_dialogue_metric/usl_score/data_utils.py
code served (permissive licence) · get_code("41a79d03a37cc6b8")
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 random

def apply_word_drop(tokens):
    drop_threshold = random.random() / 2
    arr = []
    for token in tokens:
        val = random.random()
        if val < drop_threshold:
            continue
        arr.append(token)
    if len(arr) == 0 or len(arr) == len(tokens):
        return apply_word_drop(tokens)
    return ' '.join(arr)

random.seed(42)

tokens = ["hello", "world", "this", "is", "a", "test", "sentence"]

ARGS = {
    "tokens": tokens
}
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
apply_word_order Ran
ran on a synthesized input
vitouphy/usl_dialogue_metric/usl_score/data_utils.py
code served (permissive licence) · get_code("6dff05995d96e41f")
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 random

def apply_word_order(tokens):
    random.shuffle(tokens)
    return ' '.join(tokens)

# The function takes a list of tokens (strings) and shuffles them
# then joins them into a space-separated string
ARGS = {
    'tokens': ['hello', 'world', 'from', 'python']
}
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
calc_minmax Ran
ran on a synthesized input
vitouphy/usl_dialogue_metric/usl_score/normalize.py
code served (permissive licence) · get_code("776969e513361b74")
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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def predict(self, x):
        # Returns a dict with keys mapping to scalar values
        with torch.no_grad():
            output = self.linear(x)
        return {
            'score_a': output[0].item(),
            'score_b': output[1].item(),
            'score_c': output[2].item()
        }

model = MockModel()

# Create X_data as a list of small tensors
X_data = [
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4)
]

ARGS = {
    'model': model,
    'X_data': X_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — 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
composite_one_instance Ran
ran on a synthesized input
vitouphy/usl_dialogue_metric/usl_score/models/composite.py
code served (permissive licence) · get_code("2efc8ad4fb7aac77")
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)

# Construct arguments for composite_one_instance
# The function takes u, s, l (numeric values or tensors) and optional method and coef parameters
# It performs arithmetic operations on these values

u = torch.tensor([[0.5, 0.6, 0.7, 0.8], [0.1, 0.2, 0.3, 0.4]], dtype=torch.float32)
s = torch.tensor([[0.2, 0.3, 0.4, 0.5], [0.6, 0.7, 0.8, 0.9]], dtype=torch.float32)
l = torch.tensor([[0.9, 0.8, 0.7, 0.6], [0.5, 0.4, 0.3, 0.2]], dtype=torch.float32)

ARGS = {
    'u': u,
    's': s,
    'l': l,
    'method': 'HS',
    'coef': [0.33, 0.33, 0.34]
}
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
read_dataset Ran
ran on a synthesized input
vitouphy/usl_dialogue_metric/usl_score/data_utils.py
code served (permissive licence) · get_code("f76a87f857f7b328")
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. 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 tempfile
import os

# Create a temporary file with test data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("This is a single sentence\n")
temp_file.write("First sentence\tSecond sentence\n")
temp_file.write("Another single sentence\n")
temp_file.write("Context sentence\tResponse sentence\n")
temp_file.close()

ARGS = {
    'path': temp_file.name
}

# Note: The temporary file will exist for the duration of the test
# In production code, you'd want to clean up with:
# os.unlink(temp_file.name)
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 list — a list 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
composite Not yet run
unverified (harvested, no recorded run)
vitouphy/usl_dialogue_metric/usl_score/models/composite.py
code served (permissive licence) · get_code("8e7771cd0a0658c0")
How it ran

no invocation recorded.

distinct Not yet run
unverified (harvested, no recorded run)
vitouphy/usl_dialogue_metric/usl_score/models/distinct.py
code served (permissive licence) · get_code("a2a250c29b16791f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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 2026-11-21.

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 automatic evaluation metrics have been proposed to score the overall quality of a response in open-domain dialogue. Generally, the overall quality is comprised of various aspects, such as relevancy, specificity, and empathy, and the importance of each aspect differs according to the task. For instance, specificity is mandatory in a food-ordering dialogue task, whereas fluency is preferred in a language-teaching dialogue system. However, existing metrics are not designed to cope with such flexibility. For example, BLEU score fundamentally relies only on word overlapping, whereas BERTScore relies on semantic similarity between reference and candidate response. Thus, they are not guaranteed to capture the required aspects, i.e., specificity. To design a metric that is flexible to a task, we first propose making these qualities manageable by grouping them into three groups: understandability, sensibleness, and likability, where likability is a combination of qualities that are essential for a task. We also propose a simple method to composite metrics of each aspect to obtain a single metric called USL-H, which stands for Understandability, Sensibleness, and Likability in Hierarchy. We demonstrated that USL-H score achieves good correlations with human judgment and maintains its configurability towards different aspects and metrics.

For agents

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

get_harvested_code_for_paper("2011.00483")
get_code_for_paper("2011.00483")
have("2011.00483")

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

curl https://syntology.ai/api/ran/2011.00483.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.00483.svg)](https://syntology.ai/paper/2011.00483)

Connect an agent — have() is free.