SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.13700 · ICML · 2026

Optimal Regret for Policy Optimization in Contextual Bandits

Yishay Mansour, Orin Levy

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 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/2602.13700.json · badge: /api/ran/2602.13700.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
vowpalwabbit/vowpal_wabbit canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
find_pixel_start Ran
ran, honoured the contract we drafted
vowpalwabbit/vowpal_wabbit/big_tests/testCode/ocr2vw.py
pointer only (licence: NOASSERTION) · get_code("a12f3d1e4d73aa0d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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.

fmt_acc Ran
ran; our contract draft was wrong, not the code
vowpalwabbit/vowpal_wabbit/demo/dependencyparsing/evaluate.py
pointer only (licence: NOASSERTION) · get_code("dc66d8a7afd52adb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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_label Ran
ran; our contract draft was wrong, not the code
vowpalwabbit/vowpal_wabbit/utl/active_interactor.py
pointer only (licence: NOASSERTION) · get_code("42e12103ee87d559")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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.

open_if_not_none Ran
ran; our contract draft was wrong, not the code
vowpalwabbit/vowpal_wabbit/utl/active_interactor.py
pointer only (licence: NOASSERTION) · get_code("f74529c2d40430a2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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.

pc Ran
ran, honoured the contract we drafted
vowpalwabbit/vowpal_wabbit/demo/dependencyparsing/evaluate.py
pointer only (licence: NOASSERTION) · get_code("636319439bbe00d8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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.

read_letter_names Ran
ran; our contract draft was wrong, not the code
vowpalwabbit/vowpal_wabbit/big_tests/testCode/ocr2vw.py
pointer only (licence: NOASSERTION) · get_code("89ba234857930c0e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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.

recvall Ran
ran; our contract draft was wrong, not the code
vowpalwabbit/vowpal_wabbit/utl/active_interactor.py
pointer only (licence: NOASSERTION) · get_code("46032debef5e34c8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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 Not yet run
unverified (harvested, no recorded run)
vowpalwabbit/vowpal_wabbit/demo/advertising/naive_baseline.py
pointer only (licence: NOASSERTION) · get_code("cf20a46278653526")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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.

train_test_oneday Not yet run
unverified (harvested, no recorded run)
vowpalwabbit/vowpal_wabbit/demo/advertising/naive_baseline.py
pointer only (licence: NOASSERTION) · get_code("b09fe38bb7cec201")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vowpalwabbit/vowpal_wabbit (NOASSERTION). 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

We present the first high-probability optimal regret bound for a policy optimization technique applied to the problem of stochastic contextual multi-armed bandit (CMAB) with general offline function approximation. Our algorithm is both efficient and achieves an optimal regret bound of O( K|A| log |F |), where K is the number of rounds, A is the set of arms, and F is the function class used to approximate the losses. Our results bridge the gap between theory and practice, demonstrating that the widely used policy optimization methods for the contextual bandit problem can achieve a rigorously-proved optimal regret bound. We support our theoretical results with an empirical evaluation of our algorithm.

For agents

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

get_harvested_code_for_paper("2602.13700")
get_code_for_paper("2602.13700")
have("2602.13700")

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

curl https://syntology.ai/api/ran/2602.13700.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.13700.svg)](https://syntology.ai/paper/2602.13700)

Connect an agent — have() is free.