SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.20170 · 2026

KoRe: Compact Knowledge Representations for Large Language Models

Jacopo Staiano, Fausto Giunchiglia, Davide Cavicchini

arXiv · PDF

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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2605.20170.json · badge: /api/ran/2605.20170.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
DavidC001/KoRe canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
align_logits_with_labels Ran
ran; our contract draft was wrong, not the code
DavidC001/KoRe/KG_LM/evaluator.py
pointer only (licence: NONE) · get_code("5af1fce4f74f2e8f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

find_entity_boundaries Ran
ran; our contract draft was wrong, not the code
DavidC001/KoRe/generate_webQSP.py
pointer only (licence: NONE) · get_code("c9dea83868bbff2a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

find_entity_boundaries_in_question Ran
ran, honoured the contract we drafted
DavidC001/KoRe/generate_grailQA.py
pointer only (licence: NONE) · get_code("83efef7cb7729d47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

find_entity_boundaries_in_question Ran
ran, honoured the contract we drafted
DavidC001/KoRe/generate_simplequestions.py
pointer only (licence: NONE) · get_code("493835b8aea7787b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

infer_stop_tokens Ran
ran; our contract draft was wrong, not the code
DavidC001/KoRe/KG_LM/model/KG_LM_arch.py
pointer only (licence: NONE) · get_code("a4a2413ae2d95f97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

parse_simplequestions_line Ran
ran; our contract draft was wrong, not the code
DavidC001/KoRe/generate_simplequestions.py
pointer only (licence: NONE) · get_code("0aa38ea24fde0473")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

compute_hit_k Not yet run
unverified (harvested, no recorded run)
DavidC001/KoRe/KG_LM/evaluator.py
pointer only (licence: NONE) · get_code("c04290b5e62d1dc5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

load_yaml_config Not yet run
unverified (harvested, no recorded run)
DavidC001/KoRe/KG_LM/configuration.py
pointer only (licence: NONE) · get_code("2a20041949ccd2ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

none_or_int Not yet run
unverified (harvested, no recorded run)
DavidC001/KoRe/evaluate.py
pointer only (licence: NONE) · get_code("247457d8ad494caa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DavidC001/KoRe 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.

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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.

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

Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvements in reasoning capabilities. Still, the way these models encode knowledge seems inherently flawed: by design, LLMs encode world-knowledge within their parameters. This way of representing knowledge is inherently opaque, difficult to debug and update, and prone to hallucinations. On the other hand, Knowledge Graphs can provide human-readable and easily editable world knowledge representations, and their application in knowledge-intensive tasks has consistently proven beneficial to downstream performance. Nonetheless, current integration techniques require extensive retraining or finetuning. To overcome this issue, we introduce KoRe, a methodology to encode 1-hop sub-graphs into compact discrete knowledge tokens and inject them into a LLM backbone. We test the proposed approach on three established benchmarks, and report competitive performances coupled with a significant reduction (up to 10x) in token usage. Our results show that compact discrete KG representations can efficiently and effectively be used to ground modern LLMs. The code will be available at https://github.com/DavidC001/KoRe

For agents

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

get_harvested_code_for_paper("2605.20170")
get_code_for_paper("2605.20170")
have("2605.20170")

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

curl https://syntology.ai/api/ran/2605.20170.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.20170.svg)](https://syntology.ai/paper/2605.20170)

Connect an agent — have() is free.