SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.09338 · NeurIPS · 2022

Deep Bidirectional Language-Knowledge Graph Pretraining

Hongyu Ren, Jure Leskovec, Percy Liang, Christopher Manning, Michihiro Yasunaga, Antoine Bosselut, Xikun Zhang

arXiv · PDF · Open in the Atlas

Code that ran

9 of 18 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, 0 violated it and 4 have no contract verdict; 4 failures of our instrument; 9 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/2210.09338.json · badge: /api/ran/2210.09338.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
michiyasunaga/dragon canonical (classifier label)
classifier basis not recorded on the link
9 ran · 9 no recorded run
FunctionStatusWhere it lives
clean_json_line Ran
ran on a synthesized input
michiyasunaga/dragon/preprocess_utils/convert_csqa.py
code served (permissive licence) · get_code("b256ca817b4ee5e6")
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 numpy as np

def clean_json_line(json_line):

    def clean_text(text):
        return ' '.join(text.strip().split())
    json_line['question']['stem'] = clean_text(json_line['question']['stem'])
    for c_idx, choice in enumerate(json_line['question']['choices']):
        json_line['question']['choices'][c_idx]['text'] = clean_text(choice['text'])
    return json_line

torch.manual_seed(0)

ARGS = {
    'json_line': {
        'question': {
            'stem': '  What   is   the   answer  to   life?  ',
            'choices': [
                {'text': '  42   '},
                {'text': '  Not   sure  '},
                {'text': '  Unknown   '}
            ]
        }
    }
}
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 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
convert_qajson_to_entailment Ran
ran on a synthesized input
michiyasunaga/dragon/preprocess_utils/convert_obqa.py
code served (permissive licence) · get_code("174ae40015de395f")
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

torch.manual_seed(0)

qa_json = {
    'question': {
        'stem': 'What is the capital of France?',
        'choices': [
            {'text': 'Paris', 'label': 'A'},
            {'text': 'London', 'label': 'B'},
            {'text': 'Berlin', 'label': 'C'}
        ]
    },
    'answerKey': 'A'
}

ARGS = {
    'qa_json': qa_json
}
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 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
create_output_dict Ran
ran on a synthesized input
michiyasunaga/dragon/preprocess_utils/convert_obqa.py
code served (permissive licence) · get_code("345456d568545c8e")
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

torch.manual_seed(0)

ARGS = {
    'input_json': {'existing_key': 'existing_value'},
    'statement': 'This is a test statement',
    'label': True
}
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 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
del_pos Ran
ran on a synthesized input
michiyasunaga/dragon/preprocess_utils/conceptnet.py
code served (permissive licence) · get_code("5f4eefd99c11e698")
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
import numpy as np

# Create valid arguments for the del_pos function
ARGS = {
    "s": "example/n"
}
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 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
dropout_mask Ran
ran; our contract draft was wrong, not the code
michiyasunaga/dragon/utils/layers.py
code served (permissive licence) · get_code("866c784c24ba2fa8")
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 torch.nn as nn

torch.manual_seed(0)

# Create a small tensor to use as x
x = torch.randn(2, 4)

# Define arguments
ARGS = {
    'x': x,
    'sz': (2, 4),
    'p': 0.5
}
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 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
gelu Ran
ran, honoured the contract we drafted
michiyasunaga/dragon/utils/layers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from qshi95/lergv, is pointer only (licence: NONE) · get_code("b75e9c793d2a286a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from qshi95/lergv, and GitHub detected no licence in that repository 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.

get_fitb_from_question Ran
ran; our contract draft was wrong, not the code
michiyasunaga/dragon/preprocess_utils/convert_csqa.py
code served (permissive licence) · get_code("a9a454bf4414e3fe")
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.

# Setup code for replace_wh_word_with_blank and get_fitb_from_question

# The function takes a question_text string and returns a FITB (Fill In The Blank) version
# Let's create test cases for different scenarios

ARGS = {
    "question_text": "What is the capital of France?"
}
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
make_one_hot Ran
ran; our contract draft was wrong, not the code
michiyasunaga/dragon/modeling/modeling_gnn.py
code served (permissive licence) · get_code("440036c58abd9ccc")
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. 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, 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create labels: a LongTensor of shape (2,) with class indices
# Each value should be between 0 and C-1
labels = torch.LongTensor([0, 2])
labels = Variable(labels)

# Number of classes
C = 4

ARGS = {
    "labels": labels,
    "C": C,
}
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 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
sep_params Ran
ran; our contract draft was wrong, not the code
michiyasunaga/dragon/dragon.py
code served (permissive licence) · get_code("b7b66139532f1ae7")
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. 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

torch.manual_seed(0)

# Create a simple model with named parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        return x

model = SimpleModel()

# Create loaded_roberta_keys - a set of parameter names that were loaded
# The function checks `if n in loaded_roberta_keys`, so it needs to be a container
# that supports the `in` operator
loaded_roberta_keys = {
    'layer1.weight',
    'layer1.bias',
}

ARGS = {
    'model': model,
    'loaded_roberta_keys': loaded_roberta_keys,
}
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 tuple — a tuple 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
concepts2adj Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/graph.py
code served (permissive licence) · get_code("90b1b740bfed326c")
How it ran

no invocation recorded.

construct_graph Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/conceptnet.py
code served (permissive licence) · get_code("be8c35c9c1d52b66")
How it ran

no invocation recorded.

convert_qajson_to_entailment Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/convert_csqa.py
code served (permissive licence) · get_code("15baaf34a0e42ec6")
How it ran

no invocation recorded.

generate_adj_matrix_per_inst Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/graph.py
code served (permissive licence) · get_code("96ec8d520ae857f1")
How it ran

no invocation recorded.

get_glove_score Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/graph_umls_with_glove.py
code served (permissive licence) · get_code("29a699b766ece561")
How it ran

no invocation recorded.

glove_init Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/conceptnet.py
code served (permissive licence) · get_code("9dcf00b849de8977")
How it ran

no invocation recorded.

masked_softmax Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/utils/layers.py
code served (permissive licence) · get_code("3841430a72ff67fa")
How it ran

no invocation recorded.

plain_graph_generation Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/graph.py
code served (permissive licence) · get_code("66135965fe362f47")
How it ran

no invocation recorded.

sent2glove Not yet run
unverified (harvested, no recorded run)
michiyasunaga/dragon/preprocess_utils/graph_umls_with_glove.py
code served (permissive licence) · get_code("fe81b86935035b80")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 14 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 1 the same month, 10 later) and 4 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
gelu 51 other papers
32 dated earlier, 1 the same month, 16 later, 2 same year, order not determinable · 8 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
and 48 more not named here
del_pos 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
1909.02151 (2019-09)
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
and 2 more not named here
construct_graph 4 other papers
1 dated earlier, 2 later, 1 same year, order not determinable
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
2023.findings-emnlp.540 (2023 (year only))
Open-ended Commonsense Reasoning with Unrestricted Answer Scope
and 1 more not named here
dropout_mask 4 other papers
2 dated earlier, 1 later, 1 same year, order not determinable
2021.findings-emnlp.130 (2021 (year only))
Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
and 1 more not named here
get_fitb_from_question 4 other papers
2 dated earlier, 1 later, 1 same year, order not determinable
1909.02151 (2019-09)
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
and 1 more not named here
glove_init 4 other papers
1 dated earlier, 2 later, 1 same year, order not determinable
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
2023.findings-emnlp.540 (2023 (year only))
Open-ended Commonsense Reasoning with Unrestricted Answer Scope
and 1 more not named here
convert_qajson_to_entailment 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
aaai_26578 (2023 (year only))
Relation-Aware Language-Graph Transformer for Question Answering
create_output_dict 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
aaai_26578 (2023 (year only))
Relation-Aware Language-Graph Transformer for Question Answering
masked_softmax 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
aaai_26578 (2023 (year only))
Relation-Aware Language-Graph Transformer for Question Answering
convert_qajson_to_entailment 2 other papers
1 later, 1 same year, order not determinable
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
aaai_26578 (2023 (year only))
Relation-Aware Language-Graph Transformer for Question Answering
make_one_hot 2 other papers
1 dated earlier, 1 same year, order not determinable
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
2022.findings-naacl.131 (2022 (year only))
Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
generate_adj_matrix_per_inst 1 other paper
1 dated earlier
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
plain_graph_generation 1 other paper
1 dated earlier
2104.06378 (2021-04)
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
sep_params 1 other paper
1 dated earlier
2201.08860 (2022-01)
GreaseLM: Graph REASoning Enhanced Language Models for Question Answering

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

Pretraining a language model (LM) on text has been shown to help various downstream NLP tasks. Recent works show that a knowledge graph (KG) can complement text data, offering structured background knowledge that provides a useful scaffold for reasoning. However, these works are not pretrained to learn a deep fusion of the two modalities at scale, limiting the potential to acquire fully joint representations of text and KG. Here we propose DRAGON (Deep Bidirectional Language-Knowledge Graph Pretraining), a self-supervised method to pretrain a deeply joint language-knowledge foundation model from text and KG at scale. Specifically, our model takes pairs of text segments and relevant KG subgraphs as input and bidirectionally fuses information from both modalities. We pretrain this model by unifying two self-supervised reasoning tasks, masked language modeling and KG link prediction. DRAGON outperforms existing LM and LM+KG models on diverse downstream tasks including question answering across general and biomedical domains, with +5% absolute gain on average. In particular, DRAGON achieves strong performance on complex reasoning about language and knowledge (+10% on questions involving long contexts or multi-step reasoning) and low-resource QA (+8% on OBQA and RiddleSense), and new state-of-the-art results on various BioNLP tasks. Our code and trained models are available at https://github.com/michiyasunaga/dragon. Glamping GNN 1st Layer Glamping GNN Final Layer camp trip beach school beach RoBERTa: A. camp (✗) GreaseLM: C. camp (✗) Glamping: B. school (✓) school trip Glamping GNN 1st Layer Glamping GNN Final Layer garage trip beach school beach garage movie Glamping GNN 1st Layer Glamping GNN Final Layer entertain ment station movie Glamping GNN 1st Layer Glamping GNN Final Layer live movie movie entertain ment station live Model Prediction RoBERTa: B. school (✗) GreaseLM: B. school (✗) Glamping: C. beach (✓) Model Prediction B. movie theater (✓) GreaseLM: B. movie theater (✓) Glamping: B. movie theater (✓) Model Prediction B. movie theater (✗) GreaseLM: B. movie theater (✗)

For agents

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

get_harvested_code_for_paper("2210.09338")
get_code_for_paper("2210.09338")
have("2210.09338")

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

curl https://syntology.ai/api/ran/2210.09338.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.09338.svg)](https://syntology.ai/paper/2210.09338)

Connect an agent — have() is free.