SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.01007 · NeurIPS · 2023

Effective Human-AI Teams via Learned Natural Language Rules and Onboarding

Hussein Mozannar, David Sontag, Subhro Das, Prasanna Sattigeri, Dennis Wei, Jimin Lee

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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, 1 violated it and 0 have no contract verdict; 7 failures of our instrument; 4 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/2311.01007.json · badge: /api/ran/2311.01007.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
clinicalml/onboarding_human_ai canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_metrics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clinicalml/onboarding_human_ai/src/teacher_methods/teacher_human.py
pointer only (licence: NONE) · get_code("173ade9e3012230f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clinicalml/onboarding_human_ai 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_distribution_list Ran
ran; our contract draft was wrong, not the code
clinicalml/onboarding_human_ai/integrai/utils.py
pointer only (licence: NONE) · get_code("5df2e5ed9131830c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clinicalml/onboarding_human_ai 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_metrics Ran
ran; our contract draft was wrong, not the code
clinicalml/onboarding_human_ai/src/teacher_methods/teacher_human.py
pointer only (licence: NONE) · get_code("83e80b8b56bd781e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clinicalml/onboarding_human_ai 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_synth_ai_human_regions Ran
ran; our contract draft was wrong, not the code
clinicalml/onboarding_human_ai/experiments/synth_regions.py
pointer only (licence: NONE) · get_code("2f90cdceb31e1668")
How it ran

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

loss_01 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clinicalml/onboarding_human_ai/integrai/utils.py
pointer only (licence: NONE) · get_code("7af6bc32b3a4ea38")
How it ran

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

loss_01_pointwise Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clinicalml/onboarding_human_ai/integrai/utils.py
pointer only (licence: NONE) · get_code("030639705d7da61b")
How it ran

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

pil_to_detectronformat Ran
ran, violated the contract we drafted
clinicalml/onboarding_human_ai/src/datasets_hai/coco.py
pointer only (licence: NONE) · get_code("354a37ff5a56cca2")
How it ran

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

squared_distance Ran
ran; our contract draft was wrong, not the code
clinicalml/onboarding_human_ai/integrai/integrai_discover.py
pointer only (licence: NONE) · get_code("622e5b1b5cdbd1ab")
How it ran

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

ai_error_analysis Not yet run
unverified (harvested, no recorded run)
clinicalml/onboarding_human_ai/src/human_ai_card/error_analysis.py
pointer only (licence: NONE) · get_code("67aa6df802437470")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clinicalml/onboarding_human_ai 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_text_embeddings_clip Not yet run
unverified (harvested, no recorded run)
clinicalml/onboarding_human_ai/integrai/embedding_funcs.py
pointer only (licence: NONE) · get_code("d14723965be5cd52")
How it ran

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

prepare_bdd_dataset Not yet run
unverified (harvested, no recorded run)
clinicalml/onboarding_human_ai/src/datasets_hai/bdd.py
pointer only (licence: NONE) · get_code("d398222f6dd914e1")
How it ran

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

prepare_coco_dataset Not yet run
unverified (harvested, no recorded run)
clinicalml/onboarding_human_ai/src/datasets_hai/coco.py
pointer only (licence: NONE) · get_code("ac82e3557ab9869f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clinicalml/onboarding_human_ai 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

People are relying on AI agents to assist them with various tasks. The human must know when to rely on the agent, collaborate with the agent, or ignore its suggestions. In this work, we propose to learn rules, grounded in data regions and described in natural language, that illustrate how the human should collaborate with the AI. Our novel region discovery algorithm finds local regions in the data as neighborhoods in an embedding space where prior human behavior should be corrected. Each region is then described using a large language model in an iterative and contrastive procedure. We then teach these rules to the human via an onboarding stage. Through user studies on object detection and question-answering tasks, we show that our method can lead to more accurate human-AI teams. We also

For agents

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

get_harvested_code_for_paper("2311.01007")
get_code_for_paper("2311.01007")
have("2311.01007")

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

curl https://syntology.ai/api/ran/2311.01007.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.01007.svg)](https://syntology.ai/paper/2311.01007)

Connect an agent — have() is free.