SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1003.0146 · 2010

A Contextual-Bandit Approach to Personalized News Article Recommendation

Lihong Li, John Langford, Robert Schapire, Wei Chu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 0 failures of our instrument; 2 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/1003.0146.json · badge: /api/ran/1003.0146.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
danilprov/batch-bandits community
Papers with Code archive
1 ran · 1 no recorded run
antonismand/Personalized-News-Recommendation community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
BaseAgent Ran
ran on a synthesized input · constructed an object; no result was computed
danilprov/batch-bandits/CMAB/LinUCB.py
code served (permissive licence) · get_code("2df4798ead73ae05")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, BaseAgent: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from abc import ABCMeta, abstractmethod

class BaseAgent:
    """Implements the agent for an RL-Glue environment.
    Note:
        agent_init, agent_start, agent_step, agent_end, agent_cleanup, and
        agent_message are required methods.
    """
    __metaclass__ = ABCMeta

    def __init__(self):
        pass

    @abstractmethod
    def agent_init(self, agent_info={}):
        """Setup for the agent called when the experiment first starts."""

    @abstractmethod
    def agent_start(self, observation):
        """The first method called when the experiment starts, called after
        the environment starts.
        Args:
            observation (Numpy array): the state observation from the environment's evn_start function.
        Returns:
            The first action the agent takes.
        """

    @abstractmethod
    def agent_step(self, reward, observation):
        """A step taken by the agent.
        Args:
            reward (float): the reward received for taking the last action taken
            observation (Numpy array): the state observation from the
                environment's step based, where the agent ended up after the
                last step
        Returns:
            The action the agent is taking.
        """

    @abstractmethod
    def agent_end(self, reward):
        """Run when the agent terminates.
        Args:
            reward (float): the reward the agent received for entering the terminal state.
        """

    @abstractmethod
    def agent_cleanup(self):
        """Cleanup done after the agent ends."""

    @abstractmethod
    def agent_message(self, message):
        """A function used to pass information from the agent to the experiment.
        Args:
            message: The message passed to the agent.
        Returns:
            The response (or answer) to the message.
        """


class SimpleAgent(BaseAgent):
    """Concrete implementation of BaseAgent for testing."""
    
    def __init__(self):
        super().__init__()
        self.last_action = None
    
    def agent_init(self, agent_info={}):
        self.agent_info = agent_info
    
    def agent_start(self, observation):
        self.last_action = 0
        return self.last_action
    
    def agent_step(self, reward, observation):
        self.last_action = (self.last_action + 1) % 4
        return self.last_action
    
    def agent_end(self, reward):
        self.last_action = None
    
    def agent_cleanup(self):
        pass
    
    def agent_message(self, message):
        return f"Agent received: {message}"


ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BaseAgent — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BaseAgent output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
LinUCB Not yet run
unverified (harvested, no recorded run)
antonismand/Personalized-News-Recommendation/bandits.py
pointer only (licence: NONE) · get_code("95478b0eca18768a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, antonismand/Personalized-News-Recommendation 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.

LinUCBAgent Not yet run
unverified (harvested, no recorded run)
danilprov/batch-bandits/CMAB/LinUCB.py
code served (permissive licence) · get_code("d7a419719dce112e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Personalized web services strive to adapt their services (advertisements, news articles, etc.) to individual users by making use of both content and user information. Despite a few recent advances, this problem remains challenging for at least two reasons. First, web service is featured with dynamically changing pools of content, rendering traditional collaborative filtering methods inapplicable. Second, the scale of most web services of practical interest calls for solutions that are both fast in learning and computation. In this work, we model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks. The contributions of this work are three-fold. First, we propose a new, general contextual bandit algorithm that is computationally efficient and well motivated from learning theory. Second, we argue that any bandit algorithm can be reliably evaluated offline using previously recorded random traffic. Finally, using this offline evaluation method, we successfully applied our new algorithm to a Yahoo! Front Page Today Module dataset containing over 33 million events. Results showed a 12.5% click lift compared to a standard context-free bandit algorithm, and the advantage becomes even greater when data gets more scarce.

For agents

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

get_harvested_code_for_paper("1003.0146")
get_code_for_paper("1003.0146")
have("1003.0146")

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

curl https://syntology.ai/api/ran/1003.0146.json

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

[![Syntology run record](https://syntology.ai/api/ran/1003.0146.svg)](https://syntology.ai/paper/1003.0146)

Connect an agent — have() is free.