SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.00920 · ICLR · 2021

DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues

Vidhisha Balachandran, Rishabh Joshi, Shikhar Vashishth, Alan Black, Yulia Tsvetkov

arXiv · PDF · Open in the Atlas

Code that ran

9 of 17 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; 1 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 1 failure of our instrument; 8 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/2106.00920.json · badge: /api/ran/2106.00920.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
rishabhjoshi/DialoGraph_ICLR21 canonical (classifier label)
classifier basis: census
7 ran · 7 no recorded run
boru-roylu/theta community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
HierarchicalBertModel Ran
ran on a synthesized input
boru-roylu/theta/src/hierarchical_models.py
pointer only (licence: NONE) · get_code("06c5c41854483ea6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, boru-roylu/theta when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

checkFile Ran
ran, violated the contract we drafted
rishabhjoshi/DialoGraph_ICLR21/src/bot/helper.py
code served (permissive licence) · get_code("ee37607aa9b149ad")
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, shape () 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 tempfile
import pathlib

# Create a temporary file for testing
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".txt")
temp_file.write(b"test content")
temp_file.close()
temp_filename = temp_file.name

ARGS = {
    "filename": temp_filename
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
count_parameters Ran
ran, honoured the contract we drafted
rishabhjoshi/DialoGraph_ICLR21/src/bot/helper.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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) and returned int, ndim 0, dtype family int, shape () 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 torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () 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
getAmounts Ran
ran on a synthesized input
rishabhjoshi/DialoGraph_ICLR21/src/utils.py
code served (permissive licence) · get_code("36717219876c7415")
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 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

torch.manual_seed(0)

# Construct a valid datapoint for getAmounts
datapoint = {
    'outcome': {
        'buyer_start_amt': 100,
        'seller_suggested_amt': 150,
        'accepted_amt': 125
    },
    'scenario': {
        'kbs': [
            {
                'personal': {
                    'Role': 'buyer',
                    'Target': 90
                }
            },
            {
                'personal': {
                    'Role': 'seller',
                    'Target': 160
                }
            }
        ]
    }
}

ARGS = {
    'datapoint': datapoint
}
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, ndim 1, dtype family int — 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
getRatio Ran
ran on a synthesized input
rishabhjoshi/DialoGraph_ICLR21/src/utils.py
code served (permissive licence) · get_code("eb87901e8a97565b")
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 float, ndim 0, dtype family float, shape () 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)

# Construct a valid datapoint dictionary that satisfies the function's requirements
datapoint = {
    'outcome': {
        'buyer_start_amt': 100,
        'seller_suggested_amt': 200,
        'accepted_amt': 150
    },
    'scenario': {
        'kbs': [
            {
                'personal': {
                    'Role': 'buyer',
                    'Target': 100
                }
            },
            {
                'personal': {
                    'Role': 'seller',
                    'Target': 200
                }
            }
        ]
    }
}

ARGS = {
    'datapoint': datapoint
}
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 float, ndim 0, dtype family float, shape () — shape () 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
get_cmd Ran
ran on a synthesized input
rishabhjoshi/DialoGraph_ICLR21/src/bot/tuning_client.py
code served (permissive licence) · get_code("430fd103ade21c84")
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 queue

class MockQueue:
    """Mock queue object that provides dequeServer method"""
    def __init__(self, config_to_return):
        self.config = config_to_return
        self.call_count = 0
    
    def dequeServer(self):
        # Return config on first call, -1 on subsequent calls
        if self.call_count == 0:
            self.call_count += 1
            return self.config
        return -1

# Create a sample config dictionary
sample_config = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 10,
    'if_self_loops': True,
    'hidden_dim': 64,
    'model': 'gcn'
}

# Create the mock queue with the config
mock_q = MockQueue(sample_config)

ARGS = {
    'q': mock_q
}
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
get_conv Ran
ran on a synthesized input
rishabhjoshi/DialoGraph_ICLR21/src/utils.py
code served (permissive licence) · get_code("11dc2e1c87bdd148")
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 2, 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.

# Setup code for get_conv function

ARGS = {
    "data": {
        "events": [
            {
                "action": "message",
                "agent": 0,
                "data": "Hello, I'm interested in this item"
            },
            {
                "action": "message",
                "agent": 1,
                "data": "Sure, what's your offer?"
            },
            {
                "action": "message",
                "agent": 0,
                "data": "I propose 50 dollars",
                "strategies": ["buyer_propose"]
            },
            {
                "action": "message",
                "agent": 1,
                "data": "That's too low, I want 80"
            },
            {
                "action": "message",
                "agent": 0,
                "data": "Okay, 75 then"
            }
        ]
    },
    "split": False
}
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, ndim 2, dtype family float — 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
make_hierarchical Ran
ran; our contract draft was wrong, not the code
boru-roylu/theta/src/hierarchical_models.py
pointer only (licence: NONE) · get_code("84722522f6fc6c6b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, boru-roylu/theta when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

str_proc Ran
ran on a synthesized input
rishabhjoshi/DialoGraph_ICLR21/src/bot/helper.py
code served (permissive licence) · get_code("e26ca61a522b8c9a")
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 torch

torch.manual_seed(0)

ARGS = {
    'x': "  HELLO WORLD  "
}
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 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
HierarchicalBertModelForConversationClassification Not yet run
unverified (harvested, no recorded run)
boru-roylu/theta/src/hierarchical_models.py
pointer only (licence: NONE) · get_code("b7afae1868526099")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, boru-roylu/theta when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

attention Not yet run
unverified (harvested, no recorded run)
rishabhjoshi/DialoGraph_ICLR21/src/bot/transformer_model.py
code served (permissive licence) · get_code("f6ec93136ba6135d")
How it ran

no invocation recorded.

beam_decode Not yet run
unverified (harvested, no recorded run)
rishabhjoshi/DialoGraph_ICLR21/src/bot/bot_models.py
code served (permissive licence) · get_code("ab1062b85c090c41")
How it ran

no invocation recorded.

clones Not yet run
unverified (harvested, no recorded run)
rishabhjoshi/DialoGraph_ICLR21/src/bot/transformer_model.py
code served (permissive licence) · get_code("c12dbc36536a1028")
How it ran

no invocation recorded.

get_attention Not yet run
unverified (harvested, no recorded run)
rishabhjoshi/DialoGraph_ICLR21/src/bot/higru_model.py
code served (permissive licence) · get_code("14f91d3ae965322d")
How it ran

no invocation recorded.

get_attn_pad_mask Not yet run
unverified (harvested, no recorded run)
rishabhjoshi/DialoGraph_ICLR21/src/bot/higru_model.py
code served (permissive licence) · get_code("4ca85dff48190064")
How it ran

no invocation recorded.

greedy_decode Not yet run
unverified (harvested, no recorded run)
rishabhjoshi/DialoGraph_ICLR21/src/bot/bot_models.py
code served (permissive licence) · get_code("8e2d784cf34c95cd")
How it ran

no invocation recorded.

subsequent_mask Not yet run
unverified (harvested, no recorded run)
rishabhjoshi/DialoGraph_ICLR21/src/bot/transformer_model.py
code served (permissive licence) · get_code("ad20149c986f9560")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 4 later) and 11 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
count_parameters 180 other papers
36 dated earlier, 7 the same month, 137 later · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
clones 79 other papers
30 dated earlier, 1 the same month, 47 later, 1 same year, order not determinable · 11 only as an assembly brick
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1706.03762 (2017-06)
Attention Is All You Need
and 76 more not named here
attention 27 other papers
14 dated earlier, 13 later
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
and 24 more not named here
subsequent_mask 21 other papers
11 dated earlier, 9 later, 1 same year, order not determinable
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1707.07998 (2017-07)
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
and 18 more not named here
checkFile 1 other paper
1 dated earlier
1812.04361 (2018-12)
RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information
get_attention 1 other paper
1 dated earlier
2009.10815 (2020-09)
Keeping Up Appearances: Computational Modeling of Face Acts in Persuasion Oriented Discussions

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

To successfully negotiate a deal, it is not enough to communicate fluently: pragmatic planning of persuasive negotiation strategies is essential. While modern dialogue agents excel at generating fluent sentences, they still lack pragmatic grounding and cannot reason strategically. We present DIALOGRAPH, a negotiation system that incorporates pragmatic strategies in a negotiation dialogue using graph neural networks. DIALOGRAPH explicitly incorporates dependencies between sequences of strategies to enable improved and interpretable prediction of next optimal strategies, given the dialogue context. Our graph-based method outperforms prior state-of-the-art negotiation models both in the accuracy of strategy/dialogue act prediction and in the quality of downstream dialogue response generation. We qualitatively show further benefits of learned strategy-graphs in providing explicit associations between effective negotiation strategies over the course of the dialogue, leading to interpretable and strategic dialogues. 1

For agents

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

get_harvested_code_for_paper("2106.00920")
get_code_for_paper("2106.00920")
have("2106.00920")

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

curl https://syntology.ai/api/ran/2106.00920.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.00920.svg)](https://syntology.ai/paper/2106.00920)

Connect an agent — have() is free.