SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.04455 · 2026

Re-Rankers as Relevance Judges

Mohammad Aliannejadi, Fengran Mo, Jiqun Liu, Chuan Meng, Jeff Dalton

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 5 failures of our instrument; 1 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/2601.04455.json · badge: /api/ran/2601.04455.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
ChuanMeng/reranker-as-judge canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
add_ranks Ran
ran; our contract draft was wrong, not the code
ChuanMeng/reranker-as-judge/monot5.py
pointer only (licence: NONE) · get_code("a480ff1b58b2ec4b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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.

best_threshold_rj Ran
ran, honoured the contract we drafted
ChuanMeng/reranker-as-judge/cross_evaluation.py
pointer only (licence: NONE) · get_code("08cf3d5963893d53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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.

best_threshold_system Ran
ran, honoured the contract we drafted
ChuanMeng/reranker-as-judge/cross_evaluation.py
pointer only (licence: NONE) · get_code("f1f165d50af3e74d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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.

extract_metric_vectors Ran
ran; our contract draft was wrong, not the code
ChuanMeng/reranker-as-judge/evaluate_system_ranking.py
pointer only (licence: NONE) · get_code("0931c3571158bdde")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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_passage Ran
ran; our contract draft was wrong, not the code
ChuanMeng/reranker-as-judge/prepare_rerank_file.py
pointer only (licence: NONE) · get_code("b51bdc54aeb5455e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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.

load_json Ran
ran; our contract draft was wrong, not the code
ChuanMeng/reranker-as-judge/cross_evaluation.py
pointer only (licence: NONE) · get_code("e36b276d9d394d5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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.

load_ranking_performance Ran
ran; our contract draft was wrong, not the code
ChuanMeng/reranker-as-judge/evaluate_system_ranking.py
pointer only (licence: NONE) · get_code("f7c33325ce77dbf0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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.

load_corpus Not yet run
unverified (harvested, no recorded run)
ChuanMeng/reranker-as-judge/prepare_rerank_file.py
pointer only (licence: NONE) · get_code("d2be521ea106af46")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChuanMeng/reranker-as-judge 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 7 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
load_json 7 other papers
6 dated earlier, 1 later
2411.10954 (2024-11)
Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties
2504.04907 (2025-04)
Video-Bench: Human-Aligned Video Generation Benchmark
2506.19054 (2025-06)
POLY-GUARD: Multi-Domain, Policy-Grounded, AI Security Guardrail Benchmark
and 4 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

Using large language models (LLMs) to predict relevance judgments has shown promising results. Most studies treat this task as a distinct research line, e.g., focusing on prompt design for predicting relevance labels given a query and passage. However, predicting relevance judgments is essentially a form of relevance prediction, a problem extensively studied in tasks such as re-ranking. Despite this potential overlap, little research has explored reusing or adapting established re-ranking methods to predict relevance judgments, leading to potential resource waste and redundant development. To bridge this gap, we reproduce re-rankers in a re-ranker-as-relevancejudge setup. We design two adaptation strategies: (i) using binary tokens (e.g., "true" and "false") generated by a re-ranker as direct judgments, and (ii) converting continuous re-ranking scores into binary labels via thresholding. We perform extensive experiments on TREC-DL 2019-2023 with 8 re-rankers from 3 families, ranging from 220M to 32B, and analyse the evaluation bias exhibited by reranker-based judges. Results show that re-ranker-based relevance judges, under both strategies, can outperform UMBRELA, a stateof-the-art LLM-based relevance judge, in around 40%-50% of the cases; they also exhibit strong self-preference towards their own and same-family re-rankers, as well as cross-family bias. • Information systems → Evaluation of retrieval results.

For agents

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

get_harvested_code_for_paper("2601.04455")
get_code_for_paper("2601.04455")
have("2601.04455")

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

curl https://syntology.ai/api/ran/2601.04455.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.04455.svg)](https://syntology.ai/paper/2601.04455)

Connect an agent — have() is free.