SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.06486 · ICML · 2026

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

Guannan Zhang, Li Cai, Lanbo Lin, Jiayao Liu, Sicong Xie, Yuanwu Xu, Tianyuan Yang, Lei Wei

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 0 have no contract verdict; 3 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/2602.06486.json · badge: /api/ran/2602.06486.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
smiling-world/JADE canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
extract_labels_from_item Ran
ran; our contract draft was wrong, not the code
smiling-world/JADE/jade/checklist/multilabel_loader.py
pointer only (licence: NONE) · get_code("6bdb445e4e9f5794")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, smiling-world/JADE 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_labels_from_query Ran
ran; our contract draft was wrong, not the code
smiling-world/JADE/jade/checklist/multilabel_loader.py
pointer only (licence: NONE) · get_code("146a2dfada0cabbf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, smiling-world/JADE 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_rubric_compact Ran
ran; our contract draft was wrong, not the code
smiling-world/JADE/jade/checklist/rubric_loader.py
pointer only (licence: NONE) · get_code("816c6f4847e1ff65")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, smiling-world/JADE 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.

create_builder Not yet run
unverified (harvested, no recorded run)
smiling-world/JADE/jade/checklist/prompts.py
pointer only (licence: NONE) · get_code("3d0e1e4c8f253d07")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, smiling-world/JADE 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.

get_prompts Not yet run
unverified (harvested, no recorded run)
smiling-world/JADE/jade/checklist/prompts.py
pointer only (licence: NONE) · get_code("f958d2e3b817cbb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, smiling-world/JADE 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_config Not yet run
unverified (harvested, no recorded run)
smiling-world/JADE/jade/config.py
pointer only (licence: NONE) · get_code("7c08dd8ff23e0706")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, smiling-world/JADE 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-asa-judge approaches adapt to individual responses yet suffer from instability and bias. Human experts address this dilemma by combining domaingrounded principles with dynamic, claim-level assessment. Inspired by this process, we propose JADE, a two-layer evaluation framework. Layer 1 encodes expert knowledge as a predefined set of evaluation skills, providing stable evaluation criteria. Layer 2 performs report-specific, claim-level evaluation to flexibly assess diverse reasoning strategies, with evidence-dependency gating to invalidate conclusions built on refuted claims. Experiments on BizBench show that JADE improves evaluation stability and reveals critical agent failure modes missed by holistic LLM-based evaluators. We further demonstrate strong alignment with expert-authored rubrics and effective transfer to HealthBench and DR.BENCH, covering medical and 10-domain professional evaluation settings. Code and data are available at https: //github.com/smiling-world/JADE.

For agents

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

get_harvested_code_for_paper("2602.06486")
get_code_for_paper("2602.06486")
have("2602.06486")

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

curl https://syntology.ai/api/ran/2602.06486.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.06486.svg)](https://syntology.ai/paper/2602.06486)

Connect an agent — have() is free.