SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.03115 · 2023

KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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 0 have no contract verdict; 4 failures of our instrument; 3 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/2307.03115.json · badge: /api/ran/2307.03115.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
thu-keg/korc canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
count_trainable_parameters Ran
ran, honoured the contract we drafted
thu-keg/korc/RAG/callbacks_rag.py
pointer only (licence: MIT); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("a3826392847cbef3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from manga-uofa/fdistill, 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_early_stopping_callback Ran
ran; our contract draft was wrong, not the code
thu-keg/korc/RAG/callbacks_rag.py
pointer only (licence: MIT); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("295d9fdc5ce0b054")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from manga-uofa/fdistill, 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.

split_text Ran
ran; our contract draft was wrong, not the code
thu-keg/korc/RAG/openqa_dataset.py
code served (permissive licence) · get_code("8b86ae69734a1fa4")
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 1, 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.

import torch
import numpy as np

# Construct arguments for split_text function
text_input = "The quick brown fox jumps over the lazy dog and the cat sat on the mat"
n_value = 3
character_value = ' '

ARGS = {
    'text': text_input,
    'n': n_value,
    'character': character_value
}
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 list, ndim 1, 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
str2bool Ran
ran, violated the contract we drafted
thu-keg/korc/EmbedKGQA/utils.py
code served (permissive licence) · get_code("8a6c8973b41cc0b9")
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 torch

torch.manual_seed(0)

ARGS = {
    "v": "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 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
trim_batch Ran
ran; our contract draft was wrong, not the code
thu-keg/korc/RAG/openqa_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from Sahandfer/CEM, is pointer only (licence: NONE) · get_code("eeb8dc60c6ef1fa4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Sahandfer/CEM, 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.

validate Ran
ran; our contract draft was wrong, not the code
thu-keg/korc/EmbedKGQA/utils.py
code served (permissive licence) · get_code("db9fdd2a894a7360")
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 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.

import torch
import torch.nn as nn
from pathlib import Path

torch.manual_seed(0)

# Create a minimal dataset class
class MinimalDataset:
    def __init__(self):
        self.mode = 'train'
        self.entity2idx = {f'entity_{i}': i for i in range(10)}
        self.idx2entity = {i: f'entity_{i}' for i in range(10)}
        self.data = [
            (
                torch.randn(4),  # question_tokenized
                torch.ones(4),   # attention_mask
                torch.tensor(0),  # head
                torch.tensor([1, 0, 1, 0, 0, 0, 0, 0, 0, 0]),  # ans
                [5, 7]  # not_in_kg
            ),
            (
                torch.randn(4),
                torch.ones(4),
                torch.tensor(1),
                torch.tensor([0, 1, 0, 1, 0, 0, 0, 0, 0, 0]),
                [3]
            )
        ]
    
    def __len__(self):
        return len(self.data)
    
    def __iter__(self):
        return iter(self.data)

# Create a minimal model class
class MinimalModel(nn.Module):
    def __init__(self, num_entities=10, hidden_dim=4):
        super().__init__()
        self.num_entities = num_entities
        self.embedding = nn.Embedding(num_entities, hidden_dim)
        self.score_layer = nn.Linear(hidden_dim, hidden_dim)
    
    def get_score_ranked(self, head, question_tokenized, attention_mask):
        # Return scores for all entities
        scores = torch.randn(self.num_entities)
        return (scores,)

dataset = MinimalDataset()
model = MinimalModel(num_entities=10, hidden_dim=4)
device = 'cpu'
writeCandidatesToFile = False
data_path = None
hops = None
output_path = None

ARGS = {
    'dataset': dataset,
    'model': model,
    'device': device,
    'writeCandidatesToFile': writeCandidatesToFile,
    'data_path': data_path,
    'hops': hops,
    'output_path': output_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — 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 float — 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
encode_line Not yet run
unverified (harvested, no recorded run)
thu-keg/korc/RAG/openqa_dataset.py
code served (permissive licence) · get_code("46db9d78be46a32a")
How it ran

no invocation recorded.

get_checkpoint_callback Not yet run
unverified (harvested, no recorded run)
thu-keg/korc/RAG/callbacks_rag.py
code served (permissive licence) · get_code("02407515847e6c7a")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
thu-keg/korc/Seq2Seq-MRC/model.py
code served (permissive licence) · get_code("2b6ed68c8a938e0f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 9 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 2 later) and 0 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_trainable_parameters 13 other papers
10 dated earlier, 1 the same month, 1 later, 1 same year, order not determinable
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2010.05953 (2020-10)
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
and 10 more not named here
get_early_stopping_callback 9 other papers
7 dated earlier, 1 the same month, 1 same year, order not determinable
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2010.11856 (2020-10)
XOR QA: Cross-lingual Open-Retrieval Question Answering
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
and 6 more not named here
trim_batch 9 other papers
6 dated earlier, 2 later, 1 same year, order not determinable
2005.01107 (2020-05)
Simplifying Paragraph-level Question Generation via Transformer Language Models
2104.08661 (2021-04)
Explaining Answers with Entailment Trees
2108.02866 (2021-08)
Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering
and 6 more not named here
encode_line 4 other papers
3 dated earlier, 1 same year, order not determinable
2104.08661 (2021-04)
Explaining Answers with Entailment Trees
2109.12595 (2021-09)
MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents
2205.09224 (2022-05)
Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner
and 1 more not named here
get_checkpoint_callback 1 other paper
1 same year, order not determinable
2023.findings-acl.743 (2023 (year only))
KORC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
get_model 1 other paper
1 same year, order not determinable
2023.findings-acl.743 (2023 (year only))
KORC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
split_text 1 other paper
1 same year, order not determinable
2023.findings-acl.743 (2023 (year only))
KORC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
str2bool 1 other paper
1 same year, order not determinable
2023.findings-acl.743 (2023 (year only))
KORC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding
validate 1 other paper
1 same year, order not determinable
2023.findings-acl.743 (2023 (year only))
KORC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding

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

Deep text understanding, which requires the connections between a given document and prior knowledge beyond its text, has been highlighted by many benchmarks in recent years. However, these benchmarks have encountered two major limitations. On the one hand, most of them require human annotation of knowledge, which leads to limited knowledge coverage. On the other hand, they usually use choices or spans in the texts as the answers, which results in narrow answer space. To overcome these limitations, we build a new challenging benchmark named KoRc in this paper. Compared with previous benchmarks, KoRC has two advantages, i.e., broad knowledge coverage and flexible answer format. Specifically, we utilize massive knowledge bases to guide annotators or large language models (LLMs) to construct knowledgable questions. Moreover, we use labels in knowledge bases rather than spans or choices as the final answers. We test state-of-the-art models on KoRC and the experimental results show that the strongest baseline only achieves 68.3% and 30.0% F1 measure in the in-distribution and out-of-distribution test set, respectively. These results indicate that deep text understanding is still an unsolved challenge. The benchmark dataset, leaderboard, and baseline methods are released in https://github.com/THU-KEG/KoRC.

For agents

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

get_harvested_code_for_paper("2307.03115")
get_code_for_paper("2307.03115")
have("2307.03115")

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

curl https://syntology.ai/api/ran/2307.03115.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.03115.svg)](https://syntology.ai/paper/2307.03115)

Connect an agent — have() is free.