velocitatem/PHANTOM
1
0
Fork 0
mirror of https://github.com/velocitatem/PHANTOM.git synced 2026-05-31 08:33:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: docs

Browse Source
This commit is contained in:
Daniel Rosel
2026-03-10 14:23:49 +01:00
parent 4c7d911043
commit a9f1e19488
3 changed files with 131 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.env.sweep.example
View File

@@ -19,4 +19,6 @@ GITHUB_TOKEN=
# Optional local benchmark defaults.
# LOCAL_BENCHMARK_ARGS=--tiers static,surge,linear,qtable,ppo --alpha-values 0.0,0.3 --episodes 3 --total-timesteps 3000 --max-steps 40 --device cpu
# SIMPLE_BENCHMARK_ARGS=--tiers qtable,ppo,dqn,a2c --alpha-values 0.0,0.15,0.3,0.45,0.6 --episodes 8 --total-timesteps 8000 --max-steps 40 --device cpu
# PHANTOM_BENCHMARK_COMPARE_ROBUST=1
# BENCHMARK_AGENT_ARGS=--tiers static,surge,linear,qtable,ppo --alpha-values 0.0,0.3,0.6 --episodes 5

10
Makefile
View File

@@ -17,6 +17,7 @@ WANDB_PROJECT ?= capstone
SWEEP_ID ?=
LOCAL_TRAIN_ARGS ?= --algo ppo --total-timesteps 50000
LOCAL_BENCHMARK_ARGS ?= --tiers static,surge,linear,qtable,ppo --alpha-values 0.0,0.3 --episodes 3 --total-timesteps 3000 --max-steps 40 --device cpu
SIMPLE_BENCHMARK_ARGS ?= --tiers qtable,ppo,dqn,a2c --alpha-values 0.0,0.15,0.3,0.45,0.6 --episodes 8 --total-timesteps 8000 --max-steps 40 --device cpu
BENCHMARK_AGENT_ARGS ?=
AGENT_COUNT ?= 0
@@ -34,7 +35,7 @@ SWEEP_ENV_LOAD = set -a; [ -f "$(SWEEP_ENV_FILE)" ] && . "$(SWEEP_ENV_FILE)" ||
.PHONY: help
help:
@echo "pdf.build pdf.watch pdf.clean pdf.genpop pdf.genpop.watch | test.backend test.e2e test.all | web.dev | install | train | benchmark | benchmark.agent | train.agent | train.bootstrap | stats.lines"
@echo "pdf.build pdf.watch pdf.clean pdf.genpop pdf.genpop.watch | test.backend test.e2e test.all | web.dev | install | train | benchmark | benchmark.simple | benchmark.agent | train.agent | train.bootstrap | stats.lines"
@echo "backend.server backend.provider backend.worker | platform.up platform.down platform.logs | docker.train.publish"
@echo ""
@echo "Build general public version:"
@@ -46,6 +47,9 @@ help:
@echo "Local benchmark run:"
@echo " make benchmark LOCAL_BENCHMARK_ARGS='--tiers static,surge,linear --alpha-values 0.0,0.3 --episodes 3 --no-wandb'"
@echo ""
@echo "Simple benchmark run (.env.sweep defaults, robust+no_robust compare by default):"
@echo " make benchmark.simple"
@echo ""
@echo "Local sweep agent from this repo:"
@echo " make train.agent SWEEP_ID=entity/project/id AGENT_COUNT=5"
@echo ""
@@ -109,6 +113,10 @@ train:
benchmark:
@WANDB_ENTITY="$(WANDB_ENTITY)" WANDB_PROJECT="$(WANDB_PROJECT)" SWEEP_ENV_FILE="$(SWEEP_ENV_FILE)" LOCAL_BENCHMARK_ARGS="$(LOCAL_BENCHMARK_ARGS)" $(NX) run research:benchmark
.PHONY: benchmark.simple
benchmark.simple:
@WANDB_ENTITY="$(WANDB_ENTITY)" WANDB_PROJECT="$(WANDB_PROJECT)" SWEEP_ENV_FILE="$(SWEEP_ENV_FILE)" SIMPLE_BENCHMARK_ARGS="$(SIMPLE_BENCHMARK_ARGS)" PHANTOM_BENCHMARK_COMPARE_ROBUST="$(PHANTOM_BENCHMARK_COMPARE_ROBUST)" $(NX) run research:benchmark-simple
.PHONY: benchmark.agent
benchmark.agent:
@WANDB_ENTITY="$(WANDB_ENTITY)" WANDB_PROJECT="$(WANDB_PROJECT)" SWEEP_ENV_FILE="$(SWEEP_ENV_FILE)" SWEEP_ID="$(SWEEP_ID)" AGENT_COUNT="$(AGENT_COUNT)" BENCHMARK_AGENT_ARGS="$(BENCHMARK_AGENT_ARGS)" $(NX) run research:benchmark-agent

246
docs/index.html
View File

@@ -17,8 +17,8 @@
<meta property="og:site_name" content="PHANTOM Research">
<meta property="og:title" content="PHANTOM: Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms">
<meta property="og:description" content="Developing pricing heuristics to protect e-commerce platforms from systematic exploitation by LLM agents in dynamic pricing environments through behavioral signature detection.">
<meta property="og:url" content="TODO">
<meta property="og:image" content="TODO">
<meta property="og:url" content="https://velocitatem.github.io/PHANTOM/">
<meta property="og:image" content="https://raw.githubusercontent.com/velocitatem/PHANTOM/main/docs/static/images/carousel1.jpg">
<meta property="og:image:width" content="1200">
<meta property="og:image:height" content="630">
<meta property="og:image:alt" content="PHANTOM Research Preview">
@@ -30,17 +30,12 @@
<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image">
<!-- TODO: Replace with your lab/institution Twitter handle -->
<meta name="twitter:site" content="@YOUR_TWITTER_HANDLE">
<!-- TODO: Replace with first author's Twitter handle -->
<meta name="twitter:creator" content="@AUTHOR_TWITTER_HANDLE">
<!-- TODO: Same as paper title above -->
<meta name="twitter:title" content="PAPER_TITLE">
<!-- TODO: Same as description above -->
<meta name="twitter:description" content="BRIEF_DESCRIPTION_OF_YOUR_RESEARCH_CONTRIBUTION_AND_FINDINGS">
<!-- TODO: Same as social preview image above -->
<meta name="twitter:image" content="https://YOUR_DOMAIN.com/static/images/social_preview.png">
<meta name="twitter:image:alt" content="PAPER_TITLE - Research Preview">
<meta name="twitter:site" content="@velocitatem">
<meta name="twitter:creator" content="@velocitatem">
<meta name="twitter:title" content="PHANTOM: Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms">
<meta name="twitter:description" content="A thesis project on defending dynamic pricing against LLM-driven reconnaissance and transaction orchestration.">
<meta name="twitter:image" content="https://raw.githubusercontent.com/velocitatem/PHANTOM/main/docs/static/images/carousel1.jpg">
<meta name="twitter:image:alt" content="PHANTOM research visual">
<!-- Academic/Research Specific -->
<meta name="citation_title" content="Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms">
@@ -103,50 +98,42 @@
{
"@context": "https://schema.org",
"@type": "ScholarlyArticle",
"headline": "PAPER_TITLE",
"description": "BRIEF_DESCRIPTION_OF_YOUR_RESEARCH_CONTRIBUTION_AND_FINDINGS",
"headline": "PHANTOM: Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms",
"description": "Research on preserving dynamic pricing integrity under LLM-mediated reconnaissance and purchasing behavior.",
"author": [
{
"@type": "Person",
"name": "FIRST_AUTHOR_NAME",
"name": "Daniel Rösel",
"affiliation": {
"@type": "Organization",
"name": "INSTITUTION_NAME"
}
},
{
"@type": "Person",
"name": "SECOND_AUTHOR_NAME",
"affiliation": {
"@type": "Organization",
"name": "INSTITUTION_NAME"
"name": "IE University"
}
}
],
"datePublished": "2024-01-01",
"datePublished": "2025-01-01",
"publisher": {
"@type": "Organization",
"name": "CONFERENCE_OR_JOURNAL_NAME"
"name": "IE University"
},
"url": "https://YOUR_DOMAIN.com/YOUR_PROJECT_PAGE",
"image": "https://YOUR_DOMAIN.com/static/images/social_preview.png",
"keywords": ["KEYWORD1", "KEYWORD2", "KEYWORD3", "machine learning", "computer vision"],
"abstract": "FULL_ABSTRACT_TEXT_HERE",
"citation": "BIBTEX_CITATION_HERE",
"url": "https://velocitatem.github.io/PHANTOM/",
"image": "https://raw.githubusercontent.com/velocitatem/PHANTOM/main/docs/static/images/carousel1.jpg",
"keywords": ["dynamic pricing", "llm agents", "e-commerce", "distributionally robust optimization", "reinforcement learning"],
"abstract": "This thesis formalizes Cost of Information erosion under agentic reconnaissance, learns separable human and agent behavior kernels, and trains contamination-aware robust pricing policies.",
"citation": "Rösel, Daniel. PHANTOM: Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms. IE University, 2025.",
"isAccessibleForFree": true,
"license": "https://creativecommons.org/licenses/by/4.0/",
"mainEntity": {
"@type": "WebPage",
"@id": "https://YOUR_DOMAIN.com/YOUR_PROJECT_PAGE"
"@id": "https://velocitatem.github.io/PHANTOM/"
},
"about": [
{
"@type": "Thing",
"name": "RESEARCH_AREA_1"
"name": "Dynamic Pricing"
},
{
"@type": "Thing",
"name": "RESEARCH_AREA_2"
"name": "Agent Behavior Modeling"
}
]
}
@@ -158,8 +145,7 @@
"@context": "https://schema.org",
"@type": "Organization",
"name": "IE University",
"url": "https://www.ie.edu",
"logo": "TODO"
"url": "https://www.ie.edu"
}
</script>
</head>
@@ -173,45 +159,64 @@
<!-- More Works Dropdown -->
<div class="more-works-container">
<button class="more-works-btn" onclick="toggleMoreWorks()" title="View More Works from Our Lab">
<button class="more-works-btn" onclick="toggleMoreWorks()" title="View project links and artifacts">
<i class="fas fa-flask"></i>
More Works
Project Links
<i class="fas fa-chevron-down dropdown-arrow"></i>
</button>
<div class="more-works-dropdown" id="moreWorksDropdown">
<div class="dropdown-header">
<h4>More Works from Our Lab</h4>
<h4>Project Links</h4>
<button class="close-btn" onclick="toggleMoreWorks()">
<i class="fas fa-times"></i>
</button>
</div>
<div class="works-list">
<!-- TODO: Replace with your lab's related works -->
<a href="https://arxiv.org/abs/PAPER_ID_1" class="work-item" target="_blank">
<a href="https://pub-d5b94a3c29fd40c6b3881946e463fdb7.r2.dev/thesis-latest.pdf" class="work-item" target="_blank">
<div class="work-info">
<!-- TODO: Replace with actual paper title -->
<h5>Paper Title 1</h5>
<!-- TODO: Replace with brief description -->
<p>Brief description of the work and its main contribution.</p>
<!-- TODO: Replace with venue and year -->
<span class="work-venue">Conference/Journal 2024</span>
<h5>Thesis PDF</h5>
<p>Latest public build of the full thesis document.</p>
<span class="work-venue">IE University, 2025</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<!-- TODO: Add more related works or remove extra items -->
<a href="https://arxiv.org/abs/PAPER_ID_2" class="work-item" target="_blank">
<a href="https://github.com/velocitatem/PHANTOM" class="work-item" target="_blank">
<div class="work-info">
<h5>Paper Title 2</h5>
<p>Brief description of the work and its main contribution.</p>
<span class="work-venue">Conference/Journal 2023</span>
<h5>PHANTOM Repository</h5>
<p>Monorepo with paper source, platform code, and experiments.</p>
<span class="work-venue">Open Source</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://arxiv.org/abs/PAPER_ID_3" class="work-item" target="_blank">
<a href="https://github.com/velocitatem/p4p" class="work-item" target="_blank">
<div class="work-info">
<h5>Paper Title 3</h5>
<p>Brief description of the work and its main contribution.</p>
<span class="work-venue">Conference/Journal 2023</span>
<h5>P4P Interaction Layer</h5>
<p>Reusable storefront and logging layer released for replication.</p>
<span class="work-venue">Public Artifact</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://phantom-hotel.vercel.app" class="work-item" target="_blank">
<div class="work-info">
<h5>Hotel Mode Demo</h5>
<p>Public deployment of the hotel-style experiment interface.</p>
<span class="work-venue">Live Demo</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://phantom-airline.vercel.app" class="work-item" target="_blank">
<div class="work-info">
<h5>Airline Mode Demo</h5>
<p>Public deployment of the airline-style experiment interface.</p>
<span class="work-venue">Live Demo</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="goals/README.md" class="work-item" target="_blank">
<div class="work-info">
<h5>Goal Library</h5>
<p>Task definitions used to assign actor objectives in experiments.</p>
<span class="work-venue">Experiment Design</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
@@ -248,14 +253,13 @@
</a>
</span>
<!-- TODO: Add your supplementary material PDF or remove this section -->
<span class="link-block">
<a href="static/pdfs/supplementary_material.pdf" target="_blank"
<a href="goals/goals.csv" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
<i class="fas fa-list"></i>
</span>
<span>Supplementary</span>
<span>Goal Set</span>
</a>
</span>
@@ -269,42 +273,43 @@
</a>
</span>
<!-- TODO: Update with your arXiv paper ID -->
<span class="link-block">
<a href="https://arxiv.org/abs/<ARXIV PAPER ID>" target="_blank"
<a href="https://phantom-hotel.vercel.app" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
<i class="fas fa-globe"></i>
</span>
<span>arXiv</span>
<span>Hotel Demo</span>
</a>
</span>
<span class="link-block">
<a href="https://phantom-airline.vercel.app" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-plane"></i>
</span>
<span>Airline Demo</span>
</a>
</span>
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- Teaser video-->
<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<!-- TODO: Replace with your teaser video -->
<video poster="" id="tree" autoplay controls muted loop height="100%" preload="metadata">
<!-- TODO: Add your video file path here -->
<source src="static/videos/banner_video.mp4" type="video/mp4">
</video>
<!-- TODO: Replace with your video description -->
<h2 class="subtitle has-text-centered">
Aliquam vitae elit ullamcorper tellus egestas pellentesque. Ut lacus tellus, maximus vel lectus at, placerat pretium mi. Maecenas dignissim tincidunt vestibulum. Sed consequat hendrerit nisl ut maximus.
</h2>
<div class="publication-banner">
<img src="static/images/banner.svg" alt="PHANTOM teaser diagram connecting vulnerability, behavioral signal, and robust control" width="1920" height="1080" decoding="async" style="display:block; width:100%; height:auto;" onerror="this.onerror=null;this.src='static/images/carousel2.jpg';"/>
</div>
</div>
</div>
</section>
<!-- End teaser video -->
<!-- Paper abstract -->
<section class="section hero is-light">
@@ -314,10 +319,10 @@
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
This research establishes the following contributions: definition and formalization of non-human transactors in e-commerce platforms, development of a testing-ground for capturing the behavioral essence of these transactors across a large variety of digital systems, construction of a discriminative model to prove separability as a strong learner for downstream mitigation of contamination by non-human entities, translation of such learned separability into existing dynamic pricing machine learning loops, and establishment of a high-level KPI-affecting causal effect and cost-saving framework for the future of internet commerce in the presence of such non-human learners.
PHANTOM formalizes a mechanism failure in dynamic pricing under non-human transaction orchestration. LLM-based agents can run reconnaissance in isolated sessions and execute purchases in clean sessions, reducing the platform's ability to extract the Cost of Information (COI), the premium usually generated by demand signal expression.
</p>
<p>
This work develops behavioral signature models using recommendation system techniques to profile session-level interaction, temporal engagement, and cross-session correlation. The AI Agent market is forecasted to grow from around USD 5-8 billion in 2025 to USD 42-52 billion by 2030, raising the question of how these systems should be designed for future robustness and how to maintain a competitive edge in the analytical components of e-commerce platforms.
The project combines behavioral modeling and robust control. We built a controlled e-commerce platform (hotel and airline modes), logged full interaction trajectories and price exposures, learned separable human/agent transition kernels, and used those signals to train contamination-aware pricing policies with a distributionally robust reinforcement learning objective.
</p>
</div>
</div>
@@ -326,6 +331,26 @@
</section>
<!-- End paper abstract -->
<section class="section">
<div class="container is-max-desktop">
<div class="content has-text-justified">
<h2 class="title is-3 has-text-centered">Project Scope</h2>
<p>
The current thesis revision extends both theory and implementation. The main research question is how a pricing system can preserve margin integrity when browsing and purchasing are increasingly orchestrated by AI agents.
</p>
<ul>
<li>Formal contribution: a Cost of Information erosion theorem showing why price-query saturation can collapse dynamic pricing power.</li>
<li>System contribution: a hybrid online/offline stack (Next.js storefront, pricing provider, Kafka event streams, Airflow ETL, Redis serving layer).</li>
<li>Modeling contribution: class-specific transition kernels for human and agent behavior, with KL-divergence based separability scores.</li>
<li>Control contribution: a contamination-aware DR-RL pricing policy trained under distributional uncertainty using Wasserstein-style robustness.</li>
</ul>
<p>
Controlled trials currently include balanced human and agent sessions with goal-driven tasks across hotel and airline interfaces. Early separability results are strong (Mann-Whitney U=2.0, p=0.0006), while robust pricing gains remain regime-dependent and are being calibrated in larger sweeps.
</p>
</div>
</div>
</section>
<!-- Image carousel -->
<section class="hero is-small">
@@ -333,32 +358,27 @@
<div class="container">
<div id="results-carousel" class="carousel results-carousel">
<div class="item">
<!-- TODO: Replace with your research result images -->
<img src="static/images/carousel1.jpg" alt="First research result visualization" loading="lazy"/>
<!-- TODO: Replace with description of this result -->
<h2 class="subtitle has-text-centered">
First image description.
Early simulator traces showing how policy choice can push prices toward aggressive high-end regimes.
</h2>
</div>
<div class="item">
<!-- Your image here -->
<img src="static/images/carousel2.jpg" alt="Second research result visualization" loading="lazy"/>
<h2 class="subtitle has-text-centered">
Second image description.
Human and agent behavior diverge at the transition-kernel level, enabling usable session-level separability.
</h2>
</div>
<div class="item">
<!-- Your image here -->
<img src="static/images/carousel3.jpg" alt="Third research result visualization" loading="lazy"/>
<h2 class="subtitle has-text-centered">
Third image description.
End-to-end architecture linking web interactions, pricing queries, event streams, and model updates.
</h2>
</div>
<div class="item">
<!-- Your image here -->
<img src="static/images/carousel4.jpg" alt="Fourth research result visualization" loading="lazy"/>
<h2 class="subtitle has-text-centered">
Fourth image description.
Contamination-aware evaluation compares robust and non-robust pricing behavior across alpha sweeps.
</h2>
</div>
</div>
@@ -370,53 +390,27 @@
<!-- Youtube video -->
<section class="hero is-small is-light">
<div class="hero-body">
<div class="container">
<!-- Paper video. -->
<h2 class="title is-3">Video Presentation</h2>
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<div class="publication-video">
<!-- TODO: Replace with your YouTube video ID -->
<iframe src="https://www.youtube.com/embed/JkaxUblCGz0" frameborder="0" allow="autoplay; encrypted-media" allowfullscreen></iframe>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- End youtube video -->
<!-- Video carousel -->
<section class="hero is-small">
<div class="hero-body">
<div class="container">
<h2 class="title is-3">Another Carousel</h2>
<div id="results-carousel" class="carousel results-carousel">
<h2 class="title is-3">Defense Scenes</h2>
<div id="videos-carousel" class="carousel results-carousel">
<div class="item item-video1">
<!-- TODO: Add poster image for better preview -->
<video poster="" id="video1" controls muted loop height="100%" preload="metadata">
<!-- Your video file here -->
<source src="static/videos/carousel1.mp4" type="video/mp4">
<source src="static/videos/COIFirstPrinciplesScene.mp4" type="video/mp4">
</video>
<h2 class="subtitle has-text-centered">COI from first principles.</h2>
</div>
<div class="item item-video2">
<!-- TODO: Add poster image for better preview -->
<video poster="" id="video2" controls muted loop height="100%" preload="metadata">
<!-- Your video file here -->
<source src="static/videos/carousel2.mp4" type="video/mp4">
</video>
<img src="static/images/banner.svg" alt="PHANTOM unified teaser banner" width="1920" height="1080" decoding="async" style="display:block; width:100%; height:auto;" onerror="this.onerror=null;this.src='static/images/carousel2.jpg';"/>
<h2 class="subtitle has-text-centered">Unified teaser: vulnerability, behavioral kernels, and robust control loop.</h2>
</div>
<div class="item item-video3">
<!-- TODO: Add poster image for better preview -->
<video poster="" id="video3" controls muted loop height="100%" preload="metadata">
<!-- Your video file here -->
<source src="static/videos/carousel3.mp4" type="video/mp4">
<source src="static/videos/RobustControlScene.mp4" type="video/mp4">
</video>
<h2 class="subtitle has-text-centered">Distributionally robust control loop.</h2>
</div>
</div>
</div>
@@ -432,10 +426,10 @@
<!-- Paper poster -->
<section class="hero is-small is-light">
<div class="hero-body">
<div class="container">
<h2 class="title">Poster</h2>
<div class="container">
<h2 class="title">Full Thesis</h2>
<iframe src="https://pub-d5b94a3c29fd40c6b3881946e463fdb7.r2.dev/thesis-latest.pdf" width="100%" height="550">
<iframe title="PHANTOM thesis PDF" src="https://pub-d5b94a3c29fd40c6b3881946e463fdb7.r2.dev/thesis-latest.pdf" width="100%" height="550">
</iframe>
</div>
@@ -457,7 +451,7 @@
</div>
<pre id="bibtex-code"><code>@thesis{Rosel2025PHANTOM,
title={Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms},
author={R{\"o}sel, Daniel},
author={Rösel, Daniel},
school={IE University},
year={2025},
address={Madrid, Spain},