SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.09680 · EMNLP · 2020

Profile Consistency Identification for Open-domain Dialogue Agents

Yan Wang, Ting Liu, Zhengyu Zhao, Haoyu Song, Xiaojiang Liu, Wei-Nan Zhang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 0 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/2009.09680.json · badge: /api/ran/2009.09680.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
songhaoyu/KvPI community
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
myModel Ran
ran on a synthesized input · constructed an object; no result was computed
songhaoyu/KvPI/kvbert.py
code served (permissive licence) · get_code("a9dab75126bb85a0")
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 an instance of its own class, myModel: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# Stand-in Vocab class
class Vocab:
    def __init__(self):
        self.padding_idx = 0
        self.token_to_idx_map = {
            '[CLS]': 1,
            '[SEP]': 2,
            'token1': 3,
            'token2': 4,
            'token3': 5,
        }
    
    def token2idx(self, tokens):
        return [self.token_to_idx_map.get(t, 3) for t in tokens]

# Stand-in BERT model
class BertModel(nn.Module):
    def __init__(self, embedding_size=4):
        super().__init__()
        self.embedding_size = embedding_size
        self.embed = nn.Embedding(10, embedding_size)
    
    def work(self, data, seg, typ):
        # Returns tuple where second element is pooled output
        batch_size = data.shape[1]
        output = self.embed(data).mean(dim=0)  # (batch_size, embedding_size)
        pooled = output.view(batch_size, self.embedding_size)
        return (output, pooled)

# Stand-in Tree model
class TreeModel(nn.Module):
    def __init__(self, input_size=4, hidden_dim=3):
        super().__init__()
        self.hidden_dim = hidden_dim
        self.fc = nn.Linear(input_size, hidden_dim)
    
    def forward(self, left_tree, left_input, right_tree, right_input):
        # Process trees and inputs, return (something, tree_output)
        tree_output = self.fc(left_input + right_input)
        return (None, tree_output)

# Create instances
vocab = Vocab()
bert_model = BertModel(embedding_size=4)
tree_model = TreeModel(input_size=4, hidden_dim=3)

# Arguments for myModel
ARGS = {
    'bert_model': bert_model,
    'num_class': 2,
    'num_category': 5,
    'embedding_size': 4,
    'batch_size': 2,
    'dropout': 0.1,
    'device': 0,
    'vocab': vocab,
    'tree_model': tree_model,
    'tree_hidden_dim': 3,
}
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 myModel — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a myModel 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
ListsToTensor Not yet run
unverified (harvested, no recorded run)
songhaoyu/KvPI/kvbert.py
code served (permissive licence) · get_code("e36d2e825b82a424")
How it ran

no invocation recorded.

batchify Not yet run
unverified (harvested, no recorded run)
songhaoyu/KvPI/kvbert.py
code served (permissive licence) · get_code("53b9359ddf7fc172")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 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

Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans. Existing studies on improving attribute consistency mainly explored how to incorporate attribute information in the responses, but few efforts have been made to identify the consistency relations between response and attribute profile. To facilitate the study of profile consistency identification, we create a large-scale human-annotated dataset with over 110K single-turn conversations and their key-value attribute profiles. Explicit relation between response and profile is manually labeled. We also propose a key-value structure information enriched BERT model to identify the profile consistency, and it gained improvements over strong baselines. Further evaluations on downstream tasks demonstrate that the profile consistency identification model is conducive for improving dialogue consistency. Gender Female Name Elena Current Location Beijing Constellation Aquarius Age Post-90s R1: I am glad you could come to Beijing. R3: I'll show you around Tsinghua University.

For agents

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

get_harvested_code_for_paper("2009.09680")
get_code_for_paper("2009.09680")
have("2009.09680")

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

curl https://syntology.ai/api/ran/2009.09680.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.09680.svg)](https://syntology.ai/paper/2009.09680)

Connect an agent — have() is free.