SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.00059 · 2019

GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 2 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/1908.00059.json · badge: /api/ran/1908.00059.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
hugochan/GraphFlow canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
find_span_with_gt Ran
ran; our contract draft was wrong, not the code
hugochan/GraphFlow/src/coqa_scripts/preprocess.py
code served (permissive licence) · get_code("52f882a8e42aa045")
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 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 re
import string
from collections import Counter

def normalize_answer(s):
    """Lower text and remove punctuation, storys and extra whitespace."""

    def remove_articles(text):
        regex = re.compile('\\b(a|an|the)\\b', re.UNICODE)
        return re.sub(regex, ' ', text)

    def white_space_fix(text):
        return ' '.join(text.split())

    def remove_punc(text):
        exclude = set(string.punctuation)
        return ''.join((ch for ch in text if ch not in exclude))

    def lower(text):
        return text.lower()
    return white_space_fix(remove_articles(remove_punc(lower(s))))

def find_span_with_gt(context, offsets, ground_truth):
    best_f1 = 0.0
    best_span = (len(offsets) - 1, len(offsets) - 1)
    gt = normalize_answer(ground_truth).split()
    ls = [i for i in range(len(offsets)) if context[offsets[i][0]:offsets[i][1]].lower() in gt]
    for i in range(len(ls)):
        for j in range(i, len(ls)):
            pred = normalize_answer(context[offsets[ls[i]][0]:offsets[ls[j]][1]]).split()
            common = Counter(pred) & Counter(gt)
            num_same = sum(common.values())
            if num_same > 0:
                precision = 1.0 * num_same / len(pred)
                recall = 1.0 * num_same / len(gt)
                f1 = 2 * precision * recall / (precision + recall)
                if f1 > best_f1:
                    best_f1 = f1
                    best_span = (ls[i], ls[j])
    return best_span

# Setup code
context = "the quick brown fox jumps over the lazy dog and the cat"
offsets = [
    (0, 3),      # "the"
    (4, 9),      # "quick"
    (10, 15),    # "brown"
    (16, 19),    # "fox"
    (20, 25),    # "jumps"
    (26, 30),    # "over"
    (31, 34),    # "the"
    (35, 39),    # "lazy"
    (40, 43),    # "dog"
    (44, 47),    # "and"
    (48, 51),    # "the"
    (52, 55),    # "cat"
]
ground_truth = "the quick brown fox"

ARGS = {
    "context": context,
    "offsets": offsets,
    "ground_truth": ground_truth,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 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
normalize_answer Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from stanfordnlp/coqa-baselines
pointer only · get_code("a2fdbbe11e2cf910")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

extract_sent_dep_order_tree Not yet run
unverified (harvested, no recorded run)
hugochan/GraphFlow/src/annotate_graphs.py
code served (permissive licence) · get_code("b35b1a8b07c2f04e")
How it ran

no invocation recorded.

extract_sent_dep_tree Not yet run
unverified (harvested, no recorded run)
hugochan/GraphFlow/src/annotate_graphs.py
code served (permissive licence) · get_code("198b12358dd1545e")
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 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 the same month, 1 later) and 2 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
normalize_answer 37 other papers
3 dated earlier, 1 the same month, 33 later · 1 only as an assembly brick
1808.07042 (2018-08)
CoQA: A Conversational Question Answering Challenge
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1902.01718 (2019-02)
End-to-End Open-Domain Question Answering with BERTserini
and 34 more not named here
extract_sent_dep_tree 1 other paper
1 the same month
1908.04942 (2019-08)
Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation

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

Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture conversation history and thus have trouble handling questions involving coreference or ellipsis. Moreover, when reasoning over passage text, most of them simply treat it as a word sequence without exploring rich semantic relationships among words. In this paper, we first propose a simple yet effective graph structure learning technique to dynamically construct a question and conversation history aware context graph at each conversation turn. Then we propose a novel Recurrent Graph Neural Network, and based on that, we introduce a flow mechanism to model the temporal dependencies in a sequence of context graphs. The proposed GraphFlow model can effectively capture conversational flow in a dialog, and shows competitive performance compared to existing state-of-the-art methods on CoQA, QuAC and DoQA benchmarks. In addition, visualization experiments show that our proposed model can offer good interpretability for the reasoning process.

For agents

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

get_harvested_code_for_paper("1908.00059")
get_code_for_paper("1908.00059")
have("1908.00059")

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

curl https://syntology.ai/api/ran/1908.00059.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.00059.svg)](https://syntology.ai/paper/1908.00059)

Connect an agent — have() is free.