SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.25959 · 2026

Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs

Fanfu Wei

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 (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 1 has 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/2607.25959.json · badge: /api/ran/2607.25959.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
ECLADATTA/KONTRAST community
Papers with Code archive
6 ran · 3 no recorded run
FunctionStatusWhere it lives
ParsedDate Ran
ran on a synthesized input · constructed an object; no result was computed
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("fd0e4613bc591987")
How it ran

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

clean_text Ran
ran; our contract draft was wrong, not the code
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("cc20d3e7db14a81f")
How it ran

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

is_plausible_year Ran
ran, violated the contract we drafted
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("83b094436766768e")
How it ran

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

normalize_delimiters Ran
ran; our contract draft was wrong, not the code
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("cb23316f9b907175")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ECLADATTA/KONTRAST 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_date_like Ran
ran; our contract draft was wrong, not the code
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("b9b07928d7004ebc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ECLADATTA/KONTRAST 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_answers Ran
ran; our contract draft was wrong, not the code
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("764fffc49e096c15")
How it ran

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

assign_taxonomy_label Not yet run
unverified (harvested, no recorded run)
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("8d356c2f9d2c7a63")
How it ran

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

classify_single_date_pair Not yet run
unverified (harvested, no recorded run)
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("1145abc627159925")
How it ran

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

compare_dates Not yet run
unverified (harvested, no recorded run)
ECLADATTA/KONTRAST/Output_GRASP/Qwen3-4B-Instruct-2507/ComplexQA/tag.py
pointer only (licence: NONE) · get_code("95bbe7e02daac954")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ECLADATTA/KONTRAST 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

Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation. Their knowledge is deeply connected but scattered across text, tables, and knowledge graphs. This raises a practical question: when these modalities disagree, how can we detect and explain the conflict? We study this problem as modality-level inconsistency detection. We first introduce a taxonomy of cross-modal knowledge inconsistencies, covering information granularity differences, direct conflicts, temporal changes, and KG incompleteness. We then present Kontrast, an automatic framework that uses Textto-SPARQL and LLM reasoning to compare table-based answers with KG evidence and categorize the resulting inconsistencies. Experiments on various Table-QA datasets show that cross-modal inconsistencies are common and informative. They reveal not only true knowledge conflicts, but also missing KG structure and temporal mismatches while being limited by Text-to-SPARQL errors and noise. Our analysis shows that text, tables, and KGs can complement and correct one another through systematic comparison. Kontrast provides a practical tool for largescale knowledge auditing and establishes a benchmark for future work on cross-modal knowledge consistency. Code and data are available at https://github.com/ECLADATTA/KONTRAST.

For agents

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

get_harvested_code_for_paper("2607.25959")
get_code_for_paper("2607.25959")
have("2607.25959")

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

curl https://syntology.ai/api/ran/2607.25959.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.25959.svg)](https://syntology.ai/paper/2607.25959)

Connect an agent — have() is free.