Tootfinder

Spirit Halloween guard kills suspected shoplifter: Cops
https://lawandcrime.com/crime/ill-f-shoot-you-spirit-halloween-security-guard-kills-man-suspected-of-stealing-items-worth-less-than-90-police-say/

Group Fair Matchings using Convex Cost Functions
Atasi Panda, Harsh Sharma, Anand Louis, Prajakta Nimbhorkar
https://arxiv.org/abs/2508.12549 https://arxiv…

Group Fair Matchings using Convex Cost Functions
We consider the problem of assigning items to platforms where each item has a utility associated with each of the platforms to which it can be assigned. Each platform has a soft constraint over the total number of items it serves, modeled via a convex cost function. Additionally, items are partitioned into groups, and each platform also incurs group-specific convex cost over the number of items from each group that can be assigned to the platform. These costs promote group fairness by penalizin…

Quote post work-in-progress thread.
Boost count Quote count.
#PhanpySocialDev

from my link log —
The two dualities of computation: negative and fractional (subtraction and division) types.
https://ia800204.us.archive.org/0/items/djoyner-papers/SHA256E-s568323--ecf5da2ef2…

I would suspect that many birth-citizenship US citizens could not pass this citizenship test.
(I note that the USCIS website for citizenship test materials has many items blocked by Privacy Badger and Ublock Origin - in other words, the website has trackers, some of which are private companies.)
Just read the hogwash in this announcement:
"“American citizenship is the most sacred citizenship in the world and should only be reserved for aliens who will fully embrace our…

USCIS Unveils First Changes to Naturalization Test in Multi-Step Overhaul of American Citizenship Standards
Today, U.S. Citizenship and Immigration Services posted a Federal Register notice announcing implementation of the 2025 naturalization civics test.

Enhancing Time Awareness in Generative Recommendation
Sunkyung Lee, Seongmin Park, Jonghyo Kim, Mincheol Yoon, Jongwuk Lee
https://arxiv.org/abs/2509.13957 https://

Enhancing Time Awareness in Generative Recommendation
Generative recommendation has emerged as a promising paradigm that formulates the recommendations into a text-to-text generation task, harnessing the vast knowledge of large language models. However, existing studies focus on considering the sequential order of items and neglect to handle the temporal dynamics across items, which can imply evolving user preferences. To address this limitation, we propose a novel model, Generative Recommender Using Time awareness (GRUT), effectively capturing hi…

You've got mail!

Burglary ring targeting Joe Burrow, other athletes leads to guilty plea for New York pawn shop owner

https://www.cbssports.com/nfl/news/burglar

The NazoNazo Benchmark: A Cost-Effective and Extensible Test of Insight-Based Reasoning in LLMs
Masaharu Mizumoto, Dat Nguyen, Zhiheng Han, Jiyuan Fang, Heyuan Guan, Xingfu Li, Naoya Shiraishi, Xuyang Tian, Yo Nakawake, Le Minh Nguyen
https://arxiv.org/abs/2509.14704

The NazoNazo Benchmark: A Cost-Effective and Extensible Test of Insight-Based Reasoning in LLMs
Benchmark saturation and contamination undermine confidence in LLM evaluation. We present Nazonazo, a cost-effective and extensible benchmark built from Japanese children's riddles to test insight-based reasoning. Items are short (mostly one sentence), require no specialized domain knowledge, and can be generated at scale, enabling rapid refresh of blind sets when leakage is suspected. We evaluate 38 frontier models and 126 adults on 120 riddles. No model except for GPT-5 is comparable to human…

RoboEye: Enhancing 2D Robotic Object Identification with Selective 3D Geometric Keypoint Matching
Xingwu Zhang, Guanxuan Li, Zhuocheng Zhang, Zijun Long
https://arxiv.org/abs/2509.14966

RoboEye: Enhancing 2D Robotic Object Identification with Selective 3D Geometric Keypoint Matching
The rapidly growing number of product categories in large-scale e-commerce makes accurate object identification for automated packing in warehouses substantially more difficult. As the catalog grows, intra-class variability and a long tail of rare or visually similar items increase, and when combined with diverse packaging, cluttered containers, frequent occlusion, and large viewpoint changes-these factors amplify discrepancies between query and reference images, causing sharp performance drops…

Strategic Pricing and Ranking in Recommendation Systems with Seller Competition
Tushar Shankar Walunj, Veeraruna Kavitha, Jayakrishnan Nair, Priyank Agarwal
https://arxiv.org/abs/2509.13462

Strategic Pricing and Ranking in Recommendation Systems with Seller Competition
We study a recommendation system where sellers compete for visibility by strategically offering commissions to a platform that optimally curates a ranked menu of items and their respective prices for each customer. Customers interact sequentially with the menu following a cascade click model, and their purchase decisions are influenced by price sensitivity and positions of various items in the menu. We model the seller-platform interaction as a Stackelberg game with sellers as leaders and consi…

Watching Ball x Pit and its auto selected stat upgrades makes me wonder is there a game where you pick up items that feed into the next chosen stat upgrade? Like you're picking up votes and if you want to lean into Agility you need to avoid Strength?
Maybe the number of total votes you pickup doesn't matter so there's no incentive to get them all and it becomes a bit bullet hell to avoid stats you're not maxing?

Smash-and-grab thieves in Seattle made off with an estimated $2m in diamonds, luxury watches, gold and other items in a daring midday jewelry store robbery that took just about 90 seconds, police said on Friday.
Video from the west Seattle store’s surveillance cameras shows four masked suspects shattering the locked glass front door with hammers and then ransacking six display cases on Thursday.
One display held about $750,000 worth in Rolex watches, police said in a statement, and…

Bustling 🫜
攒动 🫜
📷 Nikon FE
🎞️FOMAPAN Action 400
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

‘The ocean is spitting our rubbish back’: Italy’s museum of plastic pollution https://www.theguardian.com/environment/2025/aug/09/italy-museum-of-plastic-pollution-faded-items-beaches-ocean

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 262111 nodes and 1234877 edges.
Tags: Economic, Commerce, Unweighted

Retired School Teachers and Students: Be aware when traveling to the USA
#Math #Travel

Si bien esto no es exactamente un šlbum, fue publicado en plataformas de streaming como una serie de singles luego de ser lanzado de forma exclusiva en la web de la vocalista de Paramore, Hayley Williams. 17 canciones que han titulado «Ego»
https://open.spotify.com/playlist/3gOkujQB…

We’re closing in on this month’s release of OmniFocus 4.7, with planned dates, mutually-exclusive tags, and improved repeats!
Updated test builds are now available, adding new settings for Forecast counts and summary dots, adding support for keyboard modifiers when using drag-and-drop in Forecast on iPad and visionOS (bringing parity with the support already on Mac), and making other improvements and bug fixes.

"Meme Marketing in Social Media: Ein medienpraxeografischer Vergleich von Memes und Werbung" http://omeka.buechner-verlag.de/items/show/38 #socialmedia

An interesting spectral gap problem, from Jim Fill
James Allen Fill
https://arxiv.org/abs/2508.12557 https://arxiv.org/pdf/2508.12557

An interesting spectral gap problem, from Jim Fill
At the request of Laszlo Babai, founder and an editor of the free online journal Theory of Computing (ToC), theoryofcomputing.org, in August, 2025, I am posting on the arXiv, essentially unedited and not updated, a combination of two closely related sets of unpublished notes from 2003. ToC is keen on publishing links to all bibliography items, and a paper soon to be published there makes progress on a conjecture in my 2003 notes. The sections "The problem", "Evidence in favor of the conjecture"…

"‘The ocean is spitting our rubbish back’: Italy’s museum of plastic pollution"
#Italy #Plastic #Plastics

Fair Division of Indivisible Items
Kevin Hsu
https://arxiv.org/abs/2510.12158 https://arxiv.org/pdf/2510.12158

Fair Division of Indivisible Items
We study the fair division of indivisible items. In the general model, the goal is to allocate $m$ indivisible items to $n$ agents while satisfying fairness criteria such as MMS, EF1, and EFX. We also study a recently-introduced graphical model that represents the fair division problem as a multigraph, in which vertices correspond to agents and edges to items. The graphical model stipulates that an item can have non-zero marginal utility to an agent only if its corresponding edge is incident to…

Jeez!
Mona is the best client for Mastodon.
Their tech support (at thespringsapp@gmail.com) got back to me IMMEDIATELY. Jonny suggested that I'd accidentally added something to my Mute Items tab.
I had. I'd added the word "the". That cut down on the messages I see...
But next time I need a rest, I'll try adding some letters, "e" or "s".
DUH!
#Mona

Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings
Jinsong Chen
https://arxiv.org/abs/2509.08920 https://

Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings
This research introduces a novel psychometric method for analyzing textual data using large language models. By leveraging contextual embeddings to create contextual scores, we transform textual data into response data suitable for psychometric analysis. Treating documents as individuals and words as items, this approach provides a natural psychometric interpretation under the assumption that certain keywords, whose contextual meanings vary significantly across documents, can effectively differ…

SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
Qihang Zhao, Zhongbo Sun, Xiaoyang Zheng, Xian Guo, Siyuan Wang, Zihan Liang, Mingcan Peng, Ben Chen, Chenyi Lei
https://arxiv.org/abs/2510.12604

SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding issue. Existing methods align items' side content with collaborative information to transfer collaborative signals from high-popularity items to cold-start items. However, these methods fail to account for the asymmetry between collaboration and content, nor th…

SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy
Kuanning Wang, Yongchong Gu, Yuqian Fu, Zeyu Shangguan, Sicheng He, Xiangyang Xue, Yanwei Fu, Daniel Seita
https://arxiv.org/abs/2510.11566

SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy
Scooping items with tools such as spoons and ladles is common in daily life, ranging from assistive feeding to retrieving items from environmental disaster sites. However, developing a general and autonomous robotic scooping policy is challenging since it requires reasoning about complex tool-object interactions. Furthermore, scooping often involves manipulating deformable objects, such as granular media or liquids, which is challenging due to their infinite-dimensional configuration spaces and…

Archived PDF: The vOICe or Neuralink Blindsight https://ia601000.us.archive.org/1/items/neuralink_202509/neuralink.pdf September 14, 2025

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 262111 nodes and 1234877 edges.
Tags: Economic, Commerce, Unweighted

At least 2/3 of Americans aren’t daily coffee drinkers. ☕️
Wait, they are.
Well, at least hundreds of millions of American coffee drinkers don’t drink an average of 3 cups a day.
Wait, they do.
Folks, these are #TrumpTariffs, taking money from the American people.
via @…

My kid hade some time to kill after school... so she went picking mushrooms with a friend - and gave it to ME!

This is Costco's 'scan & go' project, where a roaming employee w/ a tablet & handscanner:
1️⃣ walks up to you in line
2️⃣ scans your membership card
3️⃣ scans items in your cart
...and when you checkout, you slide your credit card & you're done.
#savedyouaclick
Original post:

Poisson Inventory Models with Many Items: An Empirical Bayes Approach
Edward Anderson, Nam Ho-Nguyen, Peter Radchenko
https://arxiv.org/abs/2508.03074 https://

Poisson Inventory Models with Many Items: An Empirical Bayes Approach
We consider inventory decisions with many items, each of which has Poisson demand. The rate of demand for individual items is estimated on the basis of observations of past demand. The problem is to determine the items to hold in stock and the amount of each one. Our setting provides a natural framework for the application of the empirical Bayes methodology. We show how to do this in practice and demonstrate the importance of making posterior estimates of different demand levels, rather than ju…

Adaptive K-PackCache: Cost-Centric Data Caching in Cloud
Suvarthi Sarkar, Aadarshraj Sah, Poddutoori Sweeya Reddy, Aryabartta Sahu
https://arxiv.org/abs/2509.11156 https://

Adaptive K-PackCache: Cost-Centric Data Caching in Cloud
Recent advances in data analytics have enabled the accurate prediction of user access patterns, giving rise to the idea of packed caching delivering multiple co accessed data items together as a bundle. This improves caching efficiency, as accessing one item often implies the need for others. Prior work has explored only 2 item pairwise packing. In this paper, we extend the concept to general K packing, allowing variable size bundles for improved flexibility and performance. We formulate the K …

"Monopole im medienindustriellen Komplex? : Verwertungsgesellschaften gestern, heute, morgen" http://omeka.buechner-verlag.de/items/show/37 #GEMA

Representation Quantization for Collaborative Filtering Augmentation
Yunze Luo, Yinjie Jiang, Gaode Chen, Jingchi Wang, Shicheng Wang, Ruina Sun, Jiang Yuezihan, Jun Zhang, Jian Liang, Han Li, Kun Gai, Kaigui Bian
https://arxiv.org/abs/2508.11194

Representation Quantization for Collaborative Filtering Augmentation
As the core algorithm in recommendation systems, collaborative filtering (CF) algorithms inevitably face the problem of data sparsity. Since CF captures similar users and items for recommendations, it is effective to augment the lacking user-user and item-item homogeneous linkages. However, existing methods are typically limited to connecting through overlapping interacted neighbors or through similar attributes and contents. These approaches are constrained by coarse-grained, sparse attributes…

A Visualized Framework for Event Cooperation with Generative Agents
Yuyang Tian, Shunqiang Mao, Wenchang Gao, Lanlan Qiu, Tianxing He
https://arxiv.org/abs/2509.13011 https://…

A Visualized Framework for Event Cooperation with Generative Agents
Large Language Models (LLMs) have revolutionized the simulation of agent societies, enabling autonomous planning, memory formation, and social interactions. However, existing frameworks often overlook systematic evaluations for event organization and lack visualized integration with physically grounded environments, limiting agents' ability to navigate spaces and interact with items realistically. We develop MiniAgentPro, a visualization platform featuring an intuitive map editor for customizin…

Yes, I have an issue with #Spotify, and I don't care, I want artists to be fairly paid!
#Bandcamp

Der Standard überraschte in seiner Besprechung der Fleisch!-Ausstellung des Wien Museum heute mit einer gar nicht so trivialen Kurrent-Leseübung. https://www.wienmuseum.at/items/uploads/images/1756113454_iqFPz8JM7wxF.jpg

Police recover items at NYC shooter's apartment https://www.espn.com/nfl/story/_/id/45882079/police-recover-items-nyc-shooter-las-vegas-apartment

An analysis of nearly 50 Amazon purchases over six months in 2025: during the October 7-8 Prime Day sales, average savings were only 0.6% and some items went up (Geoffrey A. Fowler/Washington Post)
https://www.washingtonpost.com/technology/2025/10/09/amazon-prim…

I tracked Amazon’s Prime Day prices. We’ve been played.
Here’s what you should do to actually get a good deal on Amazon.

Nearly Optimal Bounds for Stochastic Online Sorting
Yang Hu
https://arxiv.org/abs/2508.07823 https://arxiv.org/pdf/2508.07823

Nearly Optimal Bounds for Stochastic Online Sorting
In the online sorting problem, we have an array $A$ of $n$ cells, and receive a stream of $n$ items $x_1,\dots,x_n\in [0,1]$. When an item arrives, we need to immediately and irrevocably place it into an empty cell. The goal is to minimize the sum of absolute differences between adjacent items, which is called the \emph{cost} of the algorithm. It has been shown by Aamand, Abrahamsen, Beretta, and Kleist (SODA 2023) that when the stream $x_1,\dots,x_n$ is generated adversarially, the optimal cos…

The Bin Packing Problem with Setups: Formulation, Structural Properties and Computational Insights
Roberto Baldacci, Fabio Ciccarelli, Stefano Conglio, Valerio Dose, Fabio Furini
https://arxiv.org/abs/2509.10075

The Bin Packing Problem with Setups: Formulation, Structural Properties and Computational Insights
We introduce and study a novel generalization of the classical Bin Packing Problem (BPP), called the Bin Packing Problem with Setups (BPPS). In this problem, which has many practical applications in production planning and logistics, the items are partitioned into classes and, whenever an item from a given class is packed into a bin, a setup weight and cost are incurred. We present a natural Integer Linear Programming (ILP) formulation for the BPPS and analyze the structural properties of its L…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 410236 nodes and 3356824 edges.
Tags: Economic, Commerce, Unweighted

@… @… looks like adjusting your image sizes in Eleventy Image, inlining your CSS, and maybe a fetchpriority=high paired with loading=eager to improve your LCP are the big ticket items reported there!
But the site is fast as-is so …

deep new project by john brackett, @…, examining documents from the #GratefulDead business archive at UC santa cruz. he's got a new scholarly book out in the spring about "touch of grey" (!!). his last was…

"Hauling items for the mob": "Independent promotion companies," payola, and "Touch of Grey" (1987)
This is a document that I examine in my forthcoming book, Touch of Grey, or, How the Grateful Dead Became Pop Stars (forthcoming spring 2026 from Duke University Press).

Building a Runtime JAR inspector in 10 hours
https://devblogs.microsoft.com/java/building-a-runtime-jar-inspector-in-10-hours/

Forget about nation-states for a moment: The top four items in today's Metacurity all deal with serious cybersecurity threats emanating from teen hackers.
Don't miss today's issue for the complete run-down of infosec developments you should know, including
--ShinyHunters threatens to release data stolen from dozens of Fortune 500 firms,
--Salesforce refuses to pay ShinyHunters ransom,
--Qantas braces for the release of its data,
--Two teens busted for…

ShinyHunters threatens to release data stolen from dozens of Fortune 500 firms
Salesforce refuses to pay ShinyHunters ransom, Qantas braces for the release of its data, Two teens busted for Kido nurseries cyberattack, Qilin claims attack on Asahi, Chinese hackers infiltrated Williams & Connolly, DPRK hackers have stolen $2b in crypto so far in 2025, much more

aus der reihe "amüsante buchtitel" heute: "»Vrummmummmmm FVISH!« : Soundscapes as Part of Constant Conversations in Action-Adventure Video Game Heterotopias" http://omeka.buechner-verlag.de/items/show/39

Post from a friend about his bike getting stolen:
"My bike was in the very back corner of our garage, they passed my wife's bike, and they left our cars and other garage items alone.
They left a Schwinn mountain bike leaned against the garage.
I'm not upset to lose a rather uncomfortable old bike I paid $300 off of Craigslist 14 years ago. I won't be able to take the kids on a bike ride until I fix this.
I'd rather help whoever this is get the ri…

Mitigating Filter Bubble from the Perspective of Community Detection: A Universal Framework
Ming Tang, Xiaowen Huang, Jitao Sang
https://arxiv.org/abs/2508.11239 https://…

Mitigating Filter Bubble from the Perspective of Community Detection: A Universal Framework
In recent years, recommender systems have primarily focused on improving accuracy at the expense of diversity, which exacerbates the well-known filter bubble effect. This paper proposes a universal framework called CD-CGCN to address the filter bubble issue in recommender systems from a community detection perspective. By analyzing user-item interaction histories with a community detection algorithm, we reveal that state-of-the-art recommendations often focus on intra-community items, worsening…

Re the “expert” opinion: see items 4-5 in https://how.complexsystems.fail

Dark prediction:
- Intellectual Property Class Action against AI companies gains traction
- AI companies use this as a plausible excuse to bail on AGI tech (that doesn’t exist)
- We see a pop like we saw “shipping heavy items by mail isn’t sustainable?!” pop in 2001
- AI companies fail, overwhelmingly, blaming only the IP Class Action
- The Money switches to a new/old grift; maybe back to crypto… lots of GPUs available
- In 5 years, everyone forgets and we have…

Chico Mello - "Helinho Brandão" (1984)
#NowPlaying #BrazilianMusic #MúsicaBrasileña

Well this has been fun!
Experimenting building a chrome extension for detecting schema markup on a webpage.

Hmm, I think I might have done something almost useful with an LLM; I used it, to categorise shopping items and sort the receipt from the supermarket into a sensible order. It's a nice use because at no point do you trust it, and it's output is simple words and not creating text.
https://www.trebli…

Had so much fun today at the V&A East Storehouse in London - a spectacular #museum and public display of their stored items.
Marvellous exhibits inside great #architecture
#exhibition

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Multidimensional Budget-Feasible Mechanism Design
Rian Neogi, Kanstantsin Pashkovich, Chaitanya Swamy
https://arxiv.org/abs/2508.09367 https://arxiv.org/pd…

Multidimensional Budget-Feasible Mechanism Design
In budget-feasible mechanism design, a buyer wishes to procure a set of items of maximum value from self-interested players. We have a valuation function $v:2^U \to \mathbb{R}_+$, where $U$ is the set of all items, where $v(S)$ specifies the value obtained from set $S$ of items. The entirety of current work on budget-feasible mechanisms has focused on the single-dimensional setting, wherein each player holds a single item $e$ and incurs a private cost $c_e$ for supplying item $e$. We introduc…

Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning
Sofia Kirsanova, Yao-Yi Chiang, Weiwei Duan
https://arxiv.org/abs/2510.08385 https://

Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning
Historical map legends are critical for interpreting cartographic symbols. However, their inconsistent layouts and unstructured formats make automatic extraction challenging. Prior work focuses primarily on segmentation or general optical character recognition (OCR), with few methods effectively matching legend symbols to their corresponding descriptions in a structured manner. We present a method that combines LayoutLMv3 for layout detection with GPT-4o using in-context learning to detect and …

DRIVE-T: A Methodology for Discriminative and Representative Data Viz Item Selection for Literacy Construct and Assessment
Angela Locoro, Silvia Golia, Davide Falessi
https://arxiv.org/abs/2508.04160

DRIVE-T: A Methodology for Discriminative and Representative Data Viz Item Selection for Literacy Construct and Assessment
The underspecification of progressive levels of difficulty in measurement constructs design and assessment tests for data visualization literacy may hinder the expressivity of measurements in both test design and test reuse. To mitigate this problem, this paper proposes DRIVE-T (Discriminating and Representative Items for Validating Expressive Tests), a methodology designed to drive the construction and evaluation of assessment items. Given a data vizualization, DRIVE-T supports the identificat…

Trump Claims Video Of Items Being Tossed From WH Window Is AI (White House Spox Says Video Is Real) - Joe.My.God.
https://www.joemygod.com/2025/09/trump-claims-video-of-items-being-tossed-from-wh-window-is-ai-white-house-spox-says-video-is-real/

Enough Stuff is a free thrift store based in East Peoria, Illinois,
which is stocked with donated items and give away those items for free to customers.
They aim to meet the needs for those who are without the basic necessities of adequate clothing, home goods and food items.
But the shop is for all, whoever is in need of items but also if people just want to change up their wardrobe.

Enough Stuff

Did Apple TV commit user-interface suicide in the last 24 hours?
We are seeing an obsolete login, lost users, and a on-screen menu system with items slopping onto one another.
All within the last 24 hours.
This is via the AppleTV app on a Roku.

lol 🤦‍♂️ https://github.com/bluesky-social/social-app/commit/965bcc44dc6b5c5fa9d013b32da3cc9f8fdce93a

Analytics of Adaptive Online Testing in Practice Over a Decade
Hideo Hirose
https://arxiv.org/abs/2508.08643 https://arxiv.org/pdf/2508.08643

Analytics of Adaptive Online Testing in Practice Over a Decade
Adaptive online testing efficiently assesses examinee proficiency by dynamically adjusting the difficulty of test items based on their performance. To achieve this, items are selected so that their difficulty closely matches the test taker's estimated ability at each stage of the test. This alignment implies that the probability of a correct answer tends toward 0.5. However, in practical settings, this probability may not converge to 0.5 unless the test comprises a sufficiently large number of …

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Cover 32: Lions offensive outburst should put the NFL on notice, plus game balls, gaffes from Week 2

https://www.cbssports.com/nfl/news/nfl-week-2-takeaways-gam…

STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
Zhenye Yang, Jinpeng Chen, Huan Li, Xiongnan Jin, Xuanyang Li, Junwei Zhang, Hongbo Gao, Kaimin Wei, Senzhang Wang
https://arxiv.org/abs/2508.10669

STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation
Conversational recommender systems (CRSs) aim to proactively capture user preferences through natural language dialogue and recommend high-quality items. To achieve this, CRS gathers user preferences via a dialog module and builds user profiles through a recommendation module to generate appropriate recommendations. However, existing CRS faces challenges in capturing the deep semantics of user preferences and dialogue context. In particular, the efficient integration of external knowledge graph…

Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation
Xiangxu Zhang, Lei Li, Yanyun Zhou, Xiao Zhou, Yingying Zhang, Xian Wu
https://arxiv.org/abs/2510.09275

Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation
Medical diagnostics is a high-stakes and complex domain that is critical to patient care. However, current evaluations of large language models (LLMs) are fundamentally misaligned with real-world clinical practice. Most of them rely on static benchmarks derived from public medical exam items, which tend to overestimate model performance and ignore the difference between textbook cases and the ambiguous, varying conditions in the real world. Recent efforts toward dynamic evaluation offer a promi…

The General Expiration Streaming Model: Diameter, $k$-Center, Counting, Sampling, and Friends
Lotte Blank, Sergio Cabello, MohammadTaghi Hajiaghayi, Robert Krauthgamer, Sepideh Mahabadi, Andr\'e Nusser, Jeff M. Phillips, Jonas Sauer
https://arxiv.org/abs/2509.07587

The General Expiration Streaming Model: Diameter, $k$-Center, Counting, Sampling, and Friends
An important thread in the study of data-stream algorithms focuses on settings where stream items are active only for a limited time. We introduce a new expiration model, where each item arrives with its own expiration time. The special case where items expire in the order that they arrive, which we call consistent expirations, contains the classical sliding-window model of Datar, Gionis, Indyk, and Motwani [SICOMP 2002] and its timestamp-based variant of Braverman and Ostrovsky [FOCS 2007]. …

Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM
Yushang Zhao, Xinyue Han, Qian Leng, Qianyi Sun, Haotian Lyu, Chengrui Zhou
https://arxiv.org/abs/2509.13179

Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM
The cold-start issue is the challenge when we talk about recommender systems, especially in the case when we do not have the past interaction data of new users or new items. Content-based features or hybrid solutions are common as conventional solutions, but they can only work in a sparse metadata environment with shallow patterns. In this paper, the efficient cold-start recommendation strategy is presented, which is based on the sub word-level representations by applying Byte Pair Encoding (BP…

Wondering if this would be useful?
(I messed up while screen recording this & accidentally mentioned everyone 😂 — now deleted, sorry 🙇‍♂️)
#PhanpySocialDev (still on my local, not on dev site)
#Design

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

How to Resolve Envy by Adding Goods
Matthias Bentert, Robert Bredereck, Eva Deltl, Pallavi Jain, Leon Kellerhals
https://arxiv.org/abs/2508.08682 https://a…

How to Resolve Envy by Adding Goods
We consider the problem of resolving the envy of a given initial allocation by adding elements from a pool of goods. We give a characterization of the instances where envy can be resolved by adding an arbitrary number of copies of the items in the pool. From this characterization, we derive a polynomial-time algorithm returning a respective solution if it exists. If the number of copies or the total number of added items are bounded, the problem becomes computationally intractable even in vario…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Combinatorial Philosopher Inequalities
Enze Sun, Zhihao Gavin Tang, Yifan Wang
https://arxiv.org/abs/2510.10039 https://arxiv.org/pdf/2510.10039

Combinatorial Philosopher Inequalities
In online combinatorial allocation, agents arrive sequentially and items are allocated in an online manner. The algorithm designer only knows the distribution of each agent's valuation, while the actual realization of the valuation is revealed only upon her arrival. Against the offline benchmark, Feldman, Gravin, and Lucier (SODA 2015) designed an optimal $0.5$-competitive algorithm for XOS agents. An emerging line of work focuses on designing approximation algorithms against the (computational…

Cover 32: Aaron Rodgers is pulling off 'Last Dance' bid with Steelers, plus game balls and gaffes from Week 6

https://www.cbssports.com/nfl/news/aaron-r

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation
Yifan Liu, Yaokun Liu, Zelin Li, Zhenrui Yue, Gyuseok Lee, Ruichen Yao, Yang Zhang, Dong Wang
https://arxiv.org/abs/2509.10468

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation
Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via sequence-to-sequence modeling. However, these two stages are optimized for different objectives: semantic reconstruction during tokenizer pretraining versus user interaction modeling during recommender training. This objective misalignment leads to two key limitations: (i) …

Online Allocation with Concave, Diminishing-Returns Objectives
Kalen Patton
https://arxiv.org/abs/2510.11266 https://arxiv.org/pdf/2510.11266

Online Allocation with Concave, Diminishing-Returns Objectives
Online resource allocation problems are central challenges in economics and computer science, modeling situations in which $n$ items arriving one at a time must each be immediately allocated among $m$ agents. In such problems, our objective is to maximize a monotone reward function $f(\mathbf{x})$ over the allocation vector $\mathbf{x} = (x_{ij})_{i, j}$, which describes the amount of each item given to each agent. In settings where $f$ is concave and has "diminishing returns" (monotone decreas…

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation
Chengbing Wang, Yang Zhang, Zhicheng Wang, Tianhao Shi, Keqin Bao, Fuli Feng, Tat-Seng Chua
https://arxiv.org/abs/2509.11524

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation
Fine-tuning large language models (LLMs) for recommendation in a generative manner has delivered promising results, but encounters significant inference overhead due to autoregressive decoding in the language space. This work explores bypassing language-space decoding by directly matching candidate items with the LLM's internal thought representations in the latent space, eliminating the time-consuming autoregressive process to reduce computational costs. Towards this, we introduce Light Latent…

Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users
Haowei Yang, Yushang Zhao, Sitao Min, Bo Su, Chao Yao, Wei Xu
https://arxiv.org/abs/2509.09066

Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users
The cold-start user issue further compromises the effectiveness of recommender systems in limiting access to the historical behavioral information. It is an effective pipeline to optimize instructional prompts on a few-shot large language model (LLM) used in recommender tasks. We introduce a context-conditioned prompt formulation method P(u,\ Ds)\ \rightarrow\ R\widehat, where u is a cold-start user profile, Ds is a curated support set, and R\widehat is the predicted ranked list of items. Based…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 403394 nodes and 3387388 edges.
Tags: Economic, Commerce, Unweighted

Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds
Oscar Villemaud, Suryanarayana Sankagiri, Matthias Grossglauser
https://arxiv.org/abs/2510.01871 https:/…

Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds
Ranking items is a central task in many information retrieval and recommender systems. User input for the ranking task often comes in the form of ratings on a coarse discrete scale. We ask whether it is possible to recover a fine-grained item ranking from such coarse-grained ratings. We model items as having scores and users as having thresholds; a user rates an item positively if the item's score exceeds the user's threshold. Although all users agree on the total item order, estimating that or…

amazon_copurchases: Amazon co-purchasing network (2003)
Network of items for sale on amazon.com in 2003 and the items they "recommend" (via the "Customers Who Bought This Item Also Bought" feature). If one item is frequently co-purchased with another, then the first item recommends the second.
This network has 410236 nodes and 3356824 edges.
Tags: Economic, Commerce, Unweighted

Reinforced Preference Optimization for Recommendation
Junfei Tan, Yuxin Chen, An Zhang, Junguang Jiang, Bin Liu, Ziru Xu, Han Zhu, Jian Xu, Bo Zheng, Xiang Wang
https://arxiv.org/abs/2510.12211

Reinforced Preference Optimization for Recommendation
Recent breakthroughs in large language models (LLMs) have fundamentally shifted recommender systems from discriminative to generative paradigms, where user behavior modeling is achieved by generating target items conditioned on historical interactions. Yet current generative recommenders still suffer from two core limitations: the lack of high-quality negative modeling and the reliance on implicit rewards. Reinforcement learning with verifiable rewards (RLVR) offers a natural solution by enabli…

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
Andrei Chernov, Haroon Wahab, Oleg Novitskij
https://arxiv.org/abs/2510.12461 …

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing methods primarily focus on either fine-tuning LLMs to generate recommendations or integrating LLM-based embeddings into downstream models. In this work, we follow the latter direction and propose \textbf{TextGCN}, which applies parameter-free graph convolution layers directly over LLM-based item-title embeddings, ins…

Semantic IDs for Joint Generative Search and Recommendation
Gustavo Penha, Edoardo D'Amico, Marco De Nadai, Enrico Palumbo, Alexandre Tamborrino, Ali Vardasbi, Max Lefarov, Shawn Lin, Timothy Heath, Francesco Fabbri, Hugues Bouchard
https://arxiv.org/abs/2508.10478

Semantic IDs for Joint Generative Search and Recommendation
Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models is how to represent items, traditionally through unique identifiers (IDs) and more recently with Semantic IDs composed of discrete codes, obtained from embeddings. While task-specific embedding models can improve performance for individual tasks, they may not generalize well in a joint setting. In this paper, we explo…

Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts
Yunke Qu, Liang Qu, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin
https://arxiv.org/abs/2508.05993

Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts
Streaming recommender systems (SRSs) are widely deployed in real-world applications, where user interests shift and new items arrive over time. As a result, effectively capturing users' latest preferences is challenging, as interactions reflecting recent interests are limited and new items often lack sufficient feedback. A common solution is to enrich item representations using multimodal encoders (e.g., BERT or ViT) to extract visual and textual features. However, these encoders are pretrained…

Faster and Memory-Efficient Training of Sequential Recommendation Models for Large Catalogs
Maxim Zhelnin, Dmitry Redko, Volkov Daniil, Anna Volodkevich, Petr Sokerin, Valeriy Shevchenko, Egor Shvetsov, Alexey Vasilev, Darya Denisova, Ruslan Izmailov, Alexey Zaytsev
https://arxiv.org/abs/2509.09682…

Faster and Memory-Efficient Training of Sequential Recommendation Models for Large Catalogs
Sequential recommendations (SR) with transformer-based architectures are widely adopted in real-world applications, where SR models require frequent retraining to adapt to ever-changing user preferences. However, training transformer-based SR models often encounters a high computational cost associated with scoring extensive item catalogs, often exceeding thousands of items. This occurs mainly due to the use of cross-entropy loss, where peak memory scales proportionally to catalog size, batch s…

RecoWorld: Building Simulated Environments for Agentic Recommender Systems
Fei Liu, Xinyu Lin, Hanchao Yu, Mingyuan Wu, Jianyu Wang, Qiang Zhang, Zhuokai Zhao, Yinglong Xia, Yao Zhang, Weiwei Li, Mingze Gao, Qifan Wang, Lizhu Zhang, Benyu Zhang, Xiangjun Fan
https://arxiv.org/abs/2509.10397

RecoWorld: Building Simulated Environments for Agentic Recommender Systems
We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can learn from errors without impacting real users. RecoWorld distinguishes itself with a dual-view architecture: a simulated user and an agentic recommender engage in multi-turn interactions aimed at maximizing user retention. The user simulator reviews recommended items, updates its mindset, and when sensing potential u…

Generation and annotation of item usage scenarios in e-commerce using large language models
Madoka Hagiri, Kazushi Okamoto, Koki Karube, Kei Harada, Atsushi Shibata
https://arxiv.org/abs/2510.07885

Generation and annotation of item usage scenarios in e-commerce using large language models
Complementary recommendations suggest combinations of useful items that play important roles in e-commerce. However, complementary relationships are often subjective and vary among individuals, making them difficult to infer from historical data. Unlike conventional history-based methods that rely on statistical co-occurrence, we focus on the underlying usage context that motivates item combinations. We hypothesized that people select complementary items by imagining specific usage scenarios an…

On Negative-aware Preference Optimization for Recommendation
Chenlu Ding, Daoxuan Liu, Jiancan Wu, Xingyu Hu, Junkang Wu, Haitao Wang, Yongkang Wang, Xingxing Wang, Xiang Wang
https://arxiv.org/abs/2508.09653

On Negative-aware Preference Optimization for Recommendation
Recommendation systems leverage user interaction data to suggest relevant items while filtering out irrelevant (negative) ones. The rise of large language models (LLMs) has garnered increasing attention for their potential in recommendation tasks. However, existing methods for optimizing LLM-based recommenders face challenges in effectively utilizing negative samples. Simply integrating large numbers of negative samples can improve ranking accuracy and mitigate popularity bias but often leads t…

On Inherited Popularity Bias in Cold-Start Item Recommendation
Gregor Meehan, Johan Pauwels
https://arxiv.org/abs/2510.11402 https://arxiv.org/pdf/2510.114…

On Inherited Popularity Bias in Cold-Start Item Recommendation
Collaborative filtering (CF) recommender systems struggle with making predictions on unseen, or 'cold', items. Systems designed to address this challenge are often trained with supervision from warm CF models in order to leverage collaborative and content information from the available interaction data. However, since they learn to replicate the behavior of CF methods, cold-start models may therefore also learn to imitate their predictive biases. In this paper, we show that cold-start systems c…

Comparative Explanations via Counterfactual Reasoning in Recommendations
Yi Yu, Zhenxing Hu
https://arxiv.org/abs/2510.10920 https://arxiv.org/pdf/2510.109…

Comparative Explanations via Counterfactual Reasoning in Recommendations
Explainable recommendation through counterfactual reasoning seeks to identify the influential aspects of items in recommendations, which can then be used as explanations. However, state-of-the-art approaches, which aim to minimize changes in product aspects while reversing their recommended decisions according to an aggregated decision boundary score, often lead to factual inaccuracies in explanations. To solve this problem, in this work we propose a novel method of Comparative Counterfactual E…

Multi-Granularity Sequence Denoising with Weakly Supervised Signal for Sequential Recommendation
Liang Li, Zhou Yang, Xiaofei Zhu
https://arxiv.org/abs/2510.10564 https://

Multi-Granularity Sequence Denoising with Weakly Supervised Signal for Sequential Recommendation
Sequential recommendation aims to predict the next item based on user interests in historical interaction sequences. Historical interaction sequences often contain irrelevant noisy items, which significantly hinders the performance of recommendation systems. Existing research employs unsupervised methods that indirectly identify item-granularity irrelevant noise by predicting the ground truth item. Since these methods lack explicit noise labels, they are prone to misidentify users' interested i…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Donglin Zhou, Weike Pan, Zhong Ming
https://arxiv.org/abs/2510.10556 htt…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Sequential recommendation (SR) models often capture user preferences based on the historically interacted item IDs, which usually obtain sub-optimal performance when the interaction history is limited. Content-based sequential recommendation has recently emerged as a promising direction that exploits items' textual and visual features to enhance preference learning. However, there are still three key challenges: (i) how to reduce the semantic gap between different content modality representatio…

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Qiya Yang, Xiaoxi Liang, Zeping Xiao, Yingjie Deng, Yalong Wang, Yongqi Liu, Han Li
https://arxiv.org/abs/2510.10127

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Reranking, as the final stage of recommender systems, demands real-time inference, accuracy, and diversity. It plays a crucial role in determining the final exposure, directly influencing user experience. Recently, generative reranking has gained increasing attention for its strong ability to model complex dependencies among items. However, most existing methods suffer from the "likelihood trap", where high-likelihood sequences are often perceived as low-quality by humans. These models tend to …