SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.09072 · 2026

Human-AI Co-design for Clinical Prediction Models

Chandan Singh, Jean Feng, Avni Kothari, Yan Shuo Tan, Aaron Kornblith, Patrick Vossler, Andrew Bishara, Lucas Zier, Newton Addo

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 3 violated it and 8 have no contract verdict; 3 failures of our instrument; 2 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/2601.09072.json · badge: /api/ran/2601.09072.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
jjfenglab/HACHI community
Papers with Code archive
15 ran · 2 no recorded run
FunctionStatusWhere it lives
CandidateConcept Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("a48e53676f6f3d6d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

ConceptConfig Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("accfcf95c0c5bcc8")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

DataConfig Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("435424ab35cb2e68")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

EnsembleConfig Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("33b95654115b9687")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

LLMConfig Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("c32b222b9b659268")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

ModelConfig Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("f2d71c471c1d4559")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

TrainingConfig Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("8dd29d8eb9cbe0b4")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

TrainingHistory Ran
ran on a synthesized input · constructed an object; no result was computed
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("0d27973a7e604c34")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

fit_residual Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("d3a98897cf0ee11d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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_auc_and_probs Ran
ran; our contract draft was wrong, not the code
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("34d657855a91e919")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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_features Ran
ran, honoured the contract we drafted
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("b0bcd9a5ee0ca100")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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_safe_logit Ran
ran, violated the contract we drafted
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("df83fdd13cdbdbd5")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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_safe_prob Ran
ran, violated the contract we drafted
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("7b83bd613521d992")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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_tabular Ran
ran, violated the contract we drafted
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("fbcdf65a3976efdf")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

train_LR Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("5d4a0356e700deac")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

CandidateConcepts Not yet run
unverified (harvested, no recorded run)
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("929d7cbbff8d8714")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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.

GreedyConceptSelector Not yet run
unverified (harvested, no recorded run)
jjfenglab/HACHI/src/ensemble_trainer/greedy_concept_selector.py
pointer only (licence: GPL-3.0) · get_code("f07f17f1839fb824")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jjfenglab/HACHI, is not in the permissive set Syntology serves inline. 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 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 17 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

Developing safe, effective, and practically useful clinical prediction models (CPMs) traditionally requires iterative collaboration between clinical experts, data scientists, and informaticists. This process refines the often small but critical details of the model building process, such as which features/patients to include and how clinical categories should be defined. However, this traditional collaboration process is extremely time-and resource-intensive, resulting in only a small fraction of CPMs reaching clinical practice. This challenge intensifies when teams attempt to reliably incorporate information from unstructured clinical notes, which can contain an essentially infinite number of concepts. To address this challenge, we introduce HACHI, an iterative human-in-theloop framework that uses AI agents to accelerate the development of fully interpretable CPMs by enabling the exploration of concepts in clinical notes. HACHI alternates between (i) an AI agent rapidly exploring and evaluating candidate concepts in clinical notes and (ii) clinical and domain experts providing feedback to improve the CPM learning process. HACHI defines concepts as simple yes-no questions that are used in linear models, allowing the clinical AI team to transparently review, refine, and validate the CPM learned in each round. In two real-world prediction tasks (acute kidney injury and traumatic brain injury), HACHI outperforms existing approaches, surfaces new clinically relevant concepts not included in commonly-used CPMs, and improves model generalizability across clinical sites and time periods. Furthermore, HACHI reveals the critical role of the clinical AI team, such as directing the AI agent to explore entire categories of concepts that it had not previously considered, adjusting the granularity of concepts it considers, changing the objective function to better align with the clinical objectives, and identifying issues of data bias and leakage. Code for HACHI is available at http://github.com/jjfenglab/HACHI.

For agents

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

get_harvested_code_for_paper("2601.09072")
get_code_for_paper("2601.09072")
have("2601.09072")

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

curl https://syntology.ai/api/ran/2601.09072.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.09072.svg)](https://syntology.ai/paper/2601.09072)

Connect an agent — have() is free.