SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.06136 · 2019

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 1 has no contract verdict; 2 failures of our instrument; 2 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/1911.06136.json · badge: /api/ran/1911.06136.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/KEPLER canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
dataset_dest_prefix Ran
ran on a synthesized input
THU-KEG/KEPLER/preprocess.py
pointer only (licence: MIT) · get_code("9eda7f80331d658c")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, THU-KEG/KEPLER, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

load_checkpoint Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THU-KEG/KEPLER/fairseq/checkpoint_utils.py
pointer only (licence: MIT) · get_code("c5ea9d48b6fc2167")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, THU-KEG/KEPLER, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

safe_readline Ran
ran; our contract draft was wrong, not the code
THU-KEG/KEPLER/fairseq/binarizer.py
pointer only (licence: MIT); the stored copy get_code serves, from agi-content-generation/EKD, is pointer only (licence: NOASSERTION) · get_code("82bdf940665aeeb4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, THU-KEG/KEPLER, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

load_checkpoint_to_cpu Not yet run
unverified (harvested, no recorded run)
THU-KEG/KEPLER/fairseq/checkpoint_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from MC-BERT/MC-BERT, is pointer only (licence: MIT) · get_code("df40d96cc20e7f57")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, THU-KEG/KEPLER, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

save_checkpoint Not yet run
unverified (harvested, no recorded run)
THU-KEG/KEPLER/fairseq/checkpoint_utils.py
pointer only (licence: MIT) · get_code("b3616a62387703cb")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, THU-KEG/KEPLER, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 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
safe_readline 66 other papers
4 dated earlier, 62 later
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
1802.06901 (2018-02)
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
1904.01038 (2019-04)
FAIRSEQ: A Fast, Extensible Toolkit for Sequence Modeling
and 63 more not named here
dataset_dest_prefix 7 other papers
2 dated earlier, 5 later
1904.01038 (2019-04)
FAIRSEQ: A Fast, Extensible Toolkit for Sequence Modeling
1904.11660 (2019-04)
Transformers with convolutional context for ASR
2005.02354 (2020-05)
It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information
and 4 more not named here
load_checkpoint_to_cpu 7 other papers
1 dated earlier, 6 later
1904.01038 (2019-04)
FAIRSEQ: A Fast, Extensible Toolkit for Sequence Modeling
2003.09229 (2020-03)
Learning to Encode Position for Transformer with Continuous Dynamical Model
2006.05744 (2020-06)
MC-BERT: Efficient Language Pre-Training via a Meta Controller
and 4 more not named here
load_checkpoint 4 other papers
1 dated earlier, 3 later
1904.01038 (2019-04)
FAIRSEQ: A Fast, Extensible Toolkit for Sequence Modeling
2007.07691 (2020-07)
A Multilingual Parallel Corpora Collection Effort for Indian Languages
2206.02369 (2022-06)
Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
and 1 more not named here
save_checkpoint 4 other papers
1 dated earlier, 3 later
1904.01038 (2019-04)
FAIRSEQ: A Fast, Extensible Toolkit for Sequence Modeling
2003.09229 (2020-03)
Learning to Encode Position for Transformer with Continuous Dynamical Model
2007.07691 (2020-07)
A Multilingual Parallel Corpora Collection Effort for Indian Languages
and 1 more not named here

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

Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative entity embeddings, but conventional KE models cannot take full advantage of the abundant textual information. In this paper, we propose a unified model for Knowledge Embedding and Pre-trained LanguagE Representation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs. In KEPLER, we encode textual entity descriptions with a PLM as their embeddings, and then jointly optimize the KE and language modeling objectives. Experimental results show that KEPLER achieves state-of-the-art performances on various NLP tasks, and also works remarkably well as an inductive KE model on KG link prediction. Furthermore, for pre-training and evaluating KEPLER, we construct Wikidata5M, a large-scale KG dataset with aligned entity descriptions, and benchmark state-of-the-art KE methods on it. It shall serve as a new KE benchmark and facilitate the research on large KG, inductive KE, and KG with text. The source code can be obtained from https://github.com/THU-KEG/KEPLER.

For agents

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

get_harvested_code_for_paper("1911.06136")
get_code_for_paper("1911.06136")
have("1911.06136")

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

curl https://syntology.ai/api/ran/1911.06136.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.06136.svg)](https://syntology.ai/paper/1911.06136)

Connect an agent — have() is free.