SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.11348 · ICML · 2025

RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals

Victor Veitch, David Reber, Sean Richardson, Todd Nief, Cristina Garbacea

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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 1 has no contract verdict; 9 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2410.11348.json · badge: /api/ran/2410.11348.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
toddnief/RATE canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
toddnief/rate canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
add_json_to_dataset Ran
ran; our contract draft was wrong, not the code
toddnief/RATE/src/rate/create_dataset.py
pointer only (licence: NONE) · get_code("23e857cbe5063d81")
How it ran

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

calculate_rewrite_effect Ran
ran; our contract draft was wrong, not the code
toddnief/rate/src/rate/treatment_effects.py
pointer only (licence: NONE) · get_code("dcd01497f33a59c1")
How it ran

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

calculate_treatment_effects Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
toddnief/rate/src/rate/treatment_effects.py
pointer only (licence: NONE) · get_code("833e6e13743ea918")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, toddnief/rate 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_api_batch Ran
ran; our contract draft was wrong, not the code
toddnief/RATE/src/rate/gpt4_api.py
pointer only (licence: NONE) · get_code("fb459ec3ad95f049")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, toddnief/RATE 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_dataset_from_json Ran
ran; our contract draft was wrong, not the code
toddnief/RATE/src/rate/utils.py
pointer only (licence: NONE) · get_code("eb6e7eb943de1c18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, toddnief/RATE 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_scoring_utils Ran
ran; our contract draft was wrong, not the code
toddnief/RATE/src/rate/scoring_template.py
pointer only (licence: NONE) · get_code("17725b319f32e7e0")
How it ran

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

sample_rewrites Ran
ran; our contract draft was wrong, not the code
toddnief/RATE/src/rate/utils_plotting.py
pointer only (licence: NONE) · get_code("c1ec67a43b08f1d3")
How it ran

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

sample_rewrites_tabular Ran
ran; our contract draft was wrong, not the code
toddnief/RATE/src/rate/utils_plotting.py
pointer only (licence: NONE) · get_code("b798e8428e27d719")
How it ran

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

serialize_experiment_template Ran
ran on a synthesized input
toddnief/RATE/src/rate/utils.py
pointer only (licence: NONE) · get_code("4f84c916f8ee3969")
How it ran

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

treatment_effects_pipeline Ran
ran; our contract draft was wrong, not the code
toddnief/rate/src/rate/treatment_effects.py
pointer only (licence: NONE) · get_code("f00425bfab46076f")
How it ran

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

synthetic_plot Not yet run
unverified (harvested, no recorded run)
toddnief/RATE/src/rate/utils_plotting.py
pointer only (licence: NONE) · get_code("5c47a0d5dbae9173")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, toddnief/RATE 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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

Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what they are actually rewarding. In this paper, we develop Rewrite-based Attribute Treatment Estimator (RATE) as an effective method for measuring the sensitivity of a reward model to high-level attributes of responses, such as sentiment, helpfulness, or complexity. Importantly, RATE measures the causal effect of an attribute on the reward. RATE uses LLMs to rewrite responses to produce imperfect counterfactual examples that can be used to measure causal effects. A key challenge is that these rewrites are imperfect in a manner that can induce substantial bias in the estimated sensitivity of the reward model to the target attribute. The core idea of RATE is to adjust for this imperfect-rewrite effect by rewriting twice. We establish the validity of the RATE procedure and show empirically that it is an effective estimator. Code is available at https://github.com/toddnief/RATE.

For agents

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

get_harvested_code_for_paper("2410.11348")
get_code_for_paper("2410.11348")
have("2410.11348")

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

curl https://syntology.ai/api/ran/2410.11348.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.11348.svg)](https://syntology.ai/paper/2410.11348)

Connect an agent — have() is free.