Tootfinder

Dumping Google’s enshittified search for Kagi - Ars Technica https://arstechnica.com/gadgets/2025/08/enough-is-enough-i-dumped-googles-worsening-search-for-kagi/

Enough is enough—I dumped Google’s worsening search for Kagi
Enough is enough: I’ve jettisoned Google in favor of a search engine that doesn’t treat me like a product.

Just found a unique spammy / cloaking result on Kagi's search engine to a web page published in the last week. It is identical to the same unique result on Google. It does not exist on Bing. I take this as evidence Kagi search sometimes uses Google search. (Unfortunately can't share the search, it's a little private.)

Snap announces a deal to distribute Perplexity's search engine to Snapchat users; Perplexity will pay Snap $400M through a combination of cash and equity (Bloomberg)
https://www.bloomberg.com/news/articles/2025-11-05/snap-…

Snap announces a deal to distribute Perplexity's search engine to Snapchat users; Perplexity will pay Snap $400M through a combination of cash and equity (Bloomberg)
https://www.bloomberg.com/news/articles/2025-11-05/snap-…

@… thanks.
Search engine results were a very weird way to discover the meaning of the acronym.
Cc @…

I've spent most of today -- while I really should have been working on other things -- building a little search engine for @yogthos' Cryogen blogging engine, which is what I use for my blog.
I can now generate an index very fast; the index I'm currently generating is too big, and doesn't have enough metadata, and consequently the search side can't return that metadata, but I'm very pleased with progress for one day.

elboob
A site search engine for Cryogen with search on the client side

Я знала, что #Hetzner - контора пидарасов, но чтобы настолько...
История такая. Я нашла интересный поисковик https://searchmysite.net и захотела добавить в него свой личный веб-сайт, но получила ошибку: "…

Sources: Apple plans an AI search tool, World Knowledge Answers, for spring 2026 as part of a Siri revamp; Apple and Google plan to test a Google model for Siri (Mark Gurman/Bloomberg)
https://www.bloomberg.com/news/articles/20

The ecological impacts of "AI" are bad but if people only used it intentionally, they'd stay there. But with every provider, every search engine, every website firing up some chatbot or summarizer even when not asked it quickly turns from bad to monstrous. "Just integrate an LLM, see if people like it" is like leaving your ICE-powered SUV running because someone might enjoy some cool air inside.

so much formerly public info is disappearing that i really wish there was a search engine that combined the active WWW with the full text contents of the @… wayback machine. or even just a good way to search the latter. (or maybe there is? couldn't find anything easy/functional.)

US v. Google: a judge bars Google from paying to be the exclusive search engine on devices and browsers but allows it to make payments for product distribution (Wall Street Journal)
https://www.wsj.com/tech/judge-bars-googl…

Ho y a du contenu sympa pour le #jdr sur peertube https://sepiasearch.org/search?search=jdr&page=1

Sepia Search
A search engine of PeerTube videos, channels and playlists, developed by Framasoft

MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
Shreeranjani Srirangamsridharan, Ali Abavisani, Reza Yousefi Maragheh, Ramin Giahi, Kai Zhao, Jason Cho, Sushant Kumar
https://arxiv.org/abs/2510.01523

MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
Meta titles and descriptions strongly shape engagement in search and recommendation platforms, yet optimizing them remains challenging. Search engine ranking models are black box environments, explicit labels are unavailable, and feedback such as click-through rate (CTR) arrives only post-deployment. Existing template, LLM, and retrieval-augmented approaches either lack diversity, hallucinate attributes, or ignore whether candidate phrasing has historically succeeded in ranking. This leaves a g…

You.com, which pivoted from AI search to enterprise AI tools, raised $100M led by Cox Enterprises at a $1.5B valuation, after a $50M Series B in September 2024 (Paayal Zaveri/Bloomberg)
https://www.bloomberg.com/news/articles/20

cora: CORA citations (1998)
Citations among papers indexed by CORA, from 1998, an early computer science research paper search engine. If a paper i cites a paper j also in this data set, then a directed edge connects i to j. (Papers not in the data set are excluded.) Self-loops may be present. The dates of these snapshots are uncertain.
This network has 23166 nodes and 91500 edges.
Tags: Informational, Citation, Unweighted

Looking at my first @… snapshot blog post from over 10 years back.
And yes they really made me do the snapshot blog post on my first day. I basically came to the office and was asked, could you do the release today?
Talk about throwing someone in at the deep end.

Russia pressures Apple to make Russian search engines default on locally-sold iPhones https://therecord.media/russia-apple-search-engine-default

AI search engine startup Exa Labs raised an $85M Series B led by Benchmark at a $700M valuation, up 10x on its 2024 Series A, and plans to grow its GPU cluster (Bloomberg)
https://www.bloomberg.com/news/articles/2025-09-03/…

A LOFAR search for coherent radio emission accompanying prompt engine activity in gamma-ray bursts
A. Hennessy, R. L. C. Starling, A. Rowlinson, I. de Ruiter, A. J. van der Horst, G. E. Anderson, N. R. Tanvir, S. ter Veen, K. Wiersema, R. A. M. J. Wijers
https://arxiv.org/abs/2509.21142

A LOFAR search for coherent radio emission accompanying prompt engine activity in gamma-ray bursts
Relativistic jets generated in gamma-ray bursts (GRBs) produce luminous transient events, yet the fundamentals of jet composition and radiation mechanisms remain unclear. One means of identifying a magnetically-dominated outflow would be detection of prompt, coherent radio emission at low frequencies, and we are able to search for this using the LOw Frequency ARray (LOFAR) coupled with modelling of high energy pulses detected by the Neil Gehrels Swift Observatory (Swift). We present the rapid r…

Does anyone know how to make iOS (26 is what I run, but 18 has it too) accept a new default search engine? It appears that in some parts of the world you can add a search engine, but at least in Australia the phone comes without that ability. One can only choose from a short list, with no option to add to the list.
Is there a workaround? The dammits are getting in my way.

Modern applications require search capabilities that go beyond basic text matching. They must be fast, accurate, personalised and context-aware. At this year's Berlin Buzzwords, Saurabh Singh demonstrated how OpenSearch’s latest AI/ML enhancements and engine improvements enable organisations to build intelligent, scalable search experiences that meet these evolving needs.
Watch the full session: #bbuzz 2026: https://tickets.plainschwarz.com/bbuzz26/c/8Hvk0ZvJA/

@… I haven’t convinced my employer to pay yet, but I added my personal Kagi account as the default search engine on my work laptop as well.
Finding SIGNIFICANTLY more useful results for programming problems that come up during the day than I did before.

The best part about @… is that every search has it's own RSS feed.
Give them a try. https://feedle.world

#Python Friday #303: Use a Search Engine With #LangChain - #ai

#303: Use a Search Engine With LangChain - Python Friday
None

Midi, which offers virtual care for women and is developing an AI search engine for health info, raised a $50M Series C, bringing its total funding to ~$150M (Rebecca Torrence/Business Insider)
https://www.businessinsider.com/womens-health-st…

Midi Health raises $50 million in funding as the menopause startup bets on longevity and AI
Midi's Series C raise comes as the startup's menopause care business surges. The company is now posting a $150 million revenue run rate.

cora: CORA citations (1998)
Citations among papers indexed by CORA, from 1998, an early computer science research paper search engine. If a paper i cites a paper j also in this data set, then a directed edge connects i to j. (Papers not in the data set are excluded.) Self-loops may be present. The dates of these snapshots are uncertain.
This network has 23166 nodes and 91500 edges.
Tags: Informational, Citation, Unweighted

#SPARQL -Spielerei: Die Gemälde der Berliner Gemäldegalerie nach Fläche geordnet: https://qlever.cs.uni-freiburg.de/wikidata/DanBp9 (Ausführungszeit 166ms, im WDQS landet die Anfrage im …

I love it when you paste an error message into the search engine, and hit a query from yesterday.
With a solution that works. #emacs

When the search engine allows you to search by postal code radius, or the whole city, so you're searching for a postal code first to find a point close to the train station.

The NIAID Discovery Portal: A Unified Search Engine for Infectious and Immune-Mediated Disease Datasets
Ginger Tsueng (The Scripps Research Institute, La Jolla, CA, USA), Emily Bullen (The Scripps Research Institute, La Jolla, CA, USA), Candice Czech (The Scripps Research Institute, La Jolla, CA, USA), Dylan Welzel (The Scripps Research Institute, La Jolla, CA, USA), Leandro Collares (The Scripps Research Institute, La Jolla, CA, USA), Jason Lin (The Scripps Research Institute, La Joll…

The NIAID Discovery Portal: A Unified Search Engine for Infectious and Immune-Mediated Disease Datasets
The NIAID Data Ecosystem Discovery Portal (https://data.niaid.nih.gov) provides a unified search interface for over 4 million datasets relevant to infectious and immune-mediated disease (IID) research. Integrating metadata from domain-specific and generalist repositories, the Portal enables researchers to identify and access datasets using user-friendly filters or advanced queries, without requiring technical expertise. The Portal supports discovery of a wide range of resources, including epide…

Arriving at Act I, The Alters is quite engaging. It's a video game, in case you are reaching for your favourite search engine. So far, the sci-fi aspect has that structured feeling of the Eastern European/Soviet branch of the genre, mixed up with the post-Soviet era shift of values and cultural trends -- still kind of bland, but looking at the Western guilty thrill of the dystopian. It's a damn good, well-made game. I hope it holds up in that way until the end.

Always, always, ALWAYS check out the "source" of any promotional offers you get. Don't click links in the message. Go to your favorite search engine, look up the organization, and verify from there.
And if they ask for money? Run. #writingcommunity #writers

Return of the Nigerian Prince Redux: Beware Book Club and Book Review Scams - Writer Beware
A few weeks ago, I wrote about a rising and extremely prolific marketing scam that I’ve been able to trace back to operators in Nigeria. Using highly personalized (AI-generated) email solicitations that make it seem the sender (always with a Gmail address, always presenting as a marketing or PR expert) has really read the book,Read More

After testing some things and I decided to throw out the "search" part of my "meta-search" and just keep the custom bangs around and forward the queries to a search engine of the users choice.
For me personally I decided to combine it with #SearXNG.
SearXNG does basically already what I want.
It isn't as customizable for an individual user (e.g. block…

LOKI: Proactively Discovering Online Scam Websites by Mining Toxic Search Queries
Pujan Paudel, Gianluca Stringhini
https://arxiv.org/abs/2509.12181 https://

LOKI: Proactively Discovering Online Scam Websites by Mining Toxic Search Queries
Online e-commerce scams, ranging from shopping scams to pet scams, globally cause millions of dollars in financial damage every year. In response, the security community has developed highly accurate detection systems able to determine if a website is fraudulent. However, finding candidate scam websites that can be passed as input to these downstream detection systems is challenging: relying on user reports is inherently reactive and slow, and proactive systems issuing search engine queries to …

When Content is Goliath and Algorithm is David: The Style and Semantic Effects of Generative Search Engine
Lijia Ma, Juan Qin, Xingchen Xu, Yong Tan
https://arxiv.org/abs/2509.14436

When Content is Goliath and Algorithm is David: The Style and Semantic Effects of Generative Search Engine
Generative search engines (GEs) leverage large language models (LLMs) to deliver AI-generated summaries with website citations, establishing novel traffic acquisition channels while fundamentally altering the search engine optimization landscape. To investigate the distinctive characteristics of GEs, we collect data through interactions with Google's generative and conventional search platforms, compiling a dataset of approximately ten thousand websites across both channels. Our empirical analy…

ChatGPT isn't so much a search engine as a guess engine.

cora: CORA citations (1998)
Citations among papers indexed by CORA, from 1998, an early computer science research paper search engine. If a paper i cites a paper j also in this data set, then a directed edge connects i to j. (Papers not in the data set are excluded.) Self-loops may be present. The dates of these snapshots are uncertain.
This network has 23166 nodes and 91500 edges.
Tags: Informational, Citation, Unweighted

Wolf admits sheep population is in ‘rapid decline’. https://flipboard.com/@thenewsdesk/business-nbfr4cs7z/-/a-1AhrCxHAS1i_bbcq3SK6Hw:a:43591897-/0

Google admits the open web is in ‘rapid decline’
The statement contradicts Google’s recent narrative about the health of the online ecosystem. For months, Google has maintained that the web is “thriving,” AI isn’t tanking traffic, and its search engine is sending people to a wider variety of websites than ever. But in a court filing from last …

I had to use #Google as a search engine again for a few hours, for reasons. And that was even without an active ad blocker. Seriously, how do so many people put up with that? And yeah, everyone who's happy with it probably shouldn't try #Kagi, otherwise they'll end up spe…

Trump Is Launching an AI Search Engine Powered by Perplexity https://www.404media.co/trump-is-launching-an-ai-search-engine-powered-by-perplexity/

Perplexity launches Search API, giving developers direct access to the same web index that powers the startup's answer engine (Michael Nuñez/Venturebeat)
https://venturebeat.com/ai/perplexity-launches-massive-search-api-to-take-on-googles-do…

Is Google about to destroy the web?
#Internet

Role-Augmented Intent-Driven Generative Search Engine Optimization
Xiaolu Chen, Haojie Wu, Jie Bao, Zhen Chen, Yong Liao, Hu Huang
https://arxiv.org/abs/2508.11158 https://

Role-Augmented Intent-Driven Generative Search Engine Optimization
Generative Search Engines (GSEs), powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), are reshaping information retrieval. While commercial systems (e.g., BingChat, Perplexity.ai) demonstrate impressive semantic synthesis capabilities, their black-box nature fundamentally undermines established Search Engine Optimization (SEO) practices. Content creators face a critical challenge: their optimization strategies, effective in traditional search engines, are misaligne…

Truth Social launches a Perplexity-powered AI search feature that consistently references Trump-supporting media including Fox News and The Washington Times (Jess Weatherbed/The Verge)
https://www.theverge.com/news/753863/trump-truth-social-ai-s…

Truth Social’s new AI search engine basically just pushes Fox News
Donald Trump’s media company is beta-testing a new AI search feature on Truth Social that’s seemingly biased towards conservative media sources.

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- DRIM-ANN: An Approximate Nearest Neighbor Search Engine based on Commercial DRAM-PIMs
Chen, Han, Liu, Liang, Yu, Dai, Yuan, Wang, Zhang, Li, Li

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/3]:
- Generative Engine Optimization: How to Dominate AI Search
Mahe Chen, Xiaoxuan Wang, Kaiwen Chen, Nick Koudas

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/5]:
- Generative Engine Optimization: How to Dominate AI Search
Mahe Chen, Xiaoxuan Wang, Kaiwen Chen, Nick Koudas

cora: CORA citations (1998)
Citations among papers indexed by CORA, from 1998, an early computer science research paper search engine. If a paper i cites a paper j also in this data set, then a directed edge connects i to j. (Papers not in the data set are excluded.) Self-loops may be present. The dates of these snapshots are uncertain.
This network has 23166 nodes and 91500 edges.
Tags: Informational, Citation, Unweighted

At this year's Berlin Buzzwords, Adrien Grand and Luca Cavanna shared their fascinating journey to the release of version 10.0 of the popular Java search engine, Apache Lucene. They discussed the challenges and successes they encountered along the way, the team effort required to achieve this milestone, and much more.
Watch the full session: https://youtu.be/GRhzgCEL_ac?si=WEnUqlFLbZD5SUew
Berlin Buzzwords returns on 7-9 June 2026! Get 36% off with our Trust Us Ticket: https://tickets.plainschwarz.com/bbuzz26/c/8Hvk0ZvJA/

Generative Engine Optimization: How to Dominate AI Search
Mahe Chen, Xiaoxuan Wang, Kaiwen Chen, Nick Koudas
https://arxiv.org/abs/2509.08919 https://arxiv…

Generative Engine Optimization: How to Dominate AI Search
The rapid adoption of generative AI-powered search engines like ChatGPT, Perplexity, and Gemini is fundamentally reshaping information retrieval, moving from traditional ranked lists to synthesized, citation-backed answers. This shift challenges established Search Engine Optimization (SEO) practices and necessitates a new paradigm, which we term Generative Engine Optimization (GEO). This paper presents a comprehensive comparative analysis of AI Search and traditional web search (Google). Thro…

@… thanks for linking to the September email,
Plan for "distribution set" deprecation
Do you know of a search engine that can reliably find archived FreeBSD email? Google somehow lost the ability long ago.

Characterizing Web Search in The Age of Generative AI
Elisabeth Kirsten, Jost Grosse Perdekamp, Mihir Upadhyay, Krishna P. Gummadi, Muhammad Bilal Zafar
https://arxiv.org/abs/2510.11560

Characterizing Web Search in The Age of Generative AI
The advent of LLMs has given rise to a new type of web search: Generative search, where LLMs retrieve web pages related to a query and generate a single, coherent text as a response. This output modality stands in stark contrast to traditional web search, where results are returned as a ranked list of independent web pages. In this paper, we ask: Along what dimensions do generative search outputs differ from traditional web search? We compare Google, a traditional web search engine, with four g…

Google begins rolling out Asset Studio in beta, letting advertisers generate and edit images, videos, and voiceovers directly in the Google Ads interface (Anu Adegbola/Search Engine Land)
https://searchengineland.com/google-ads-asset-studio-beta-461165

Superconductivity in atom-intercalated quaternary hydrides under ambient pressure
Bo-Wen Yao, Zhenfeng Ouyang, Xiao-Qi Han, Chang-Jiang Wu, Peng-Jie Guo, Ze-Feng Gao, Zhong-Yi Lu
https://arxiv.org/abs/2508.10912

Superconductivity in atom-intercalated quaternary hydrides under ambient pressure
Hydrogen-rich materials are the most promising candidates for high-temperature conventional superconductors under ambient pressure. Multinary hydrides have abundant structural configurations and are more promising to find high-temperature superconductors at ambient pressure, but searching for multinary materials in complex phase space is a great challenge. In this work, we used our developed AI search engine (InvDesFlow) to perform extensive investigations regarding ambient stable superconducti…

So what do you do when your "privacy search engine" gets in bed with Microsoft?
Google, you are now the lesser evil!
Humanity: 🤦‍♂️ 🤦‍♀️ 🤦
#Google #Microsoft #Joke

DS4RS: Community-Driven and Explainable Dataset Search Engine for Recommender System Research
Xinyang Shao, Tri Kurniawan Wijaya
https://arxiv.org/abs/2508.10238 https://…

DS4RS: Community-Driven and Explainable Dataset Search Engine for Recommender System Research
Accessing suitable datasets is critical for research and development in recommender systems. However, finding datasets that match specific recommendation task or domains remains a challenge due to scattered sources and inconsistent metadata. To address this gap, we propose a community-driven and explainable dataset search engine tailored for recommender system research. Our system supports semantic search across multiple dataset attributes, such as dataset names, descriptions, and recommendatio…

cora: CORA citations (1998)
Citations among papers indexed by CORA, from 1998, an early computer science research paper search engine. If a paper i cites a paper j also in this data set, then a directed edge connects i to j. (Papers not in the data set are excluded.) Self-loops may be present. The dates of these snapshots are uncertain.
This network has 23166 nodes and 91500 edges.
Tags: Informational, Citation, Unweighted

In a September 5 filing in the US v. Google ad tech trial, Google said "the open web is already in rapid decline", contradicting Google's recent statements (Barry Schwartz/Search Engine Roundtable)
https://www.seroundtable.com/google-open-web-is-in-r…

New Google Court Doc: Open Web Is In Rapid Decline
Google's CEO, Sundar Pichai, said in May that web publishing is not dying. Nick Fox, VP of Search at Google, said in May that the web is thriving. But in a court document filed by Google on late Fri

In a September 5 filing in the US v. Google ad tech trial, Google said "the open web is already in rapid decline", contradicting Google's recent statements (Barry Schwartz/Search Engine Roundtable)
https://www.seroundtable.com/google-open-web-is-in-r…

New Google Court Doc: Open Web Is In Rapid Decline
Google's CEO, Sundar Pichai, said in May that web publishing is not dying. Nick Fox, VP of Search at Google, said in May that the web is thriving. But in a court document filed by Google on late Fri

What Generative Search Engines Like and How to Optimize Web Content Cooperatively
Yujiang Wu, Shanshan Zhong, Yubin Kim, Chenyan Xiong
https://arxiv.org/abs/2510.11438 https://

What Generative Search Engines Like and How to Optimize Web Content Cooperatively
By employing large language models (LLMs) to retrieve documents and generate natural language responses, Generative Engines, such as Google AI overview and ChatGPT, provide significantly enhanced user experiences and have rapidly become the new form of search. Their rapid adoption also drives the needs of Generative Engine Optimization (GEO), as content providers are eager to gain more traction from them. In this paper, we introduce AutoGEO, a framework to automatically learn generative engine …

cora: CORA citations (1998)
Citations among papers indexed by CORA, from 1998, an early computer science research paper search engine. If a paper i cites a paper j also in this data set, then a directed edge connects i to j. (Papers not in the data set are excluded.) Self-loops may be present. The dates of these snapshots are uncertain.
This network has 23166 nodes and 91500 edges.
Tags: Informational, Citation, Unweighted

Emergence of Active Inference from a Chemical Oscillator: A Constructive Approach to Pre-genetic Homeostasis
Takeshi Ishida
https://arxiv.org/abs/2508.06323 https://

Emergence of Active Inference from a Chemical Oscillator: A Constructive Approach to Pre-genetic Homeostasis
How could primordial life, before the evolution of genetic systems, adapt to fluctuating environments and achieve homeostasis? This study proposes a minimal, chemically plausible model where homeostasis emerges from a simple chemical reaction network. It utilizes an internal Lotka-Volterra chemical oscillator as a "search engine" to periodically vary a protocell's pigmentation. The system then optimizes its internal state by evaluating the temporal correlation between these internal fluctuation…

Source: Perplexity has secured commitments from investors for $200M in new funding at a $20B valuation (The Information)
https://www.theinformation.com/briefings/perplexity-finalizes-20-billion-valuation-round

Perplexity Finalizes $20 Billion-Valuation Round 
Perplexity, which runs an artificial intelligence-powered search engine, has secured commitments from investors for $200 million in new funding at a $20 billion valuation, according to a person with knowledge of the matter. The new capital comes less than two months after the three-year-old startup raised money at a $18 billion valuation. The frequent but relatively modest financings, at

LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce
Yipeng Zhang, Bowen Liu, Xiaoshuang Zhang, Aritra Mandal, Zhe Wu, Canran Xu
https://arxiv.org/abs/2509.05570

LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce
User queries in e-commerce search are often vague, short, and underspecified, making it difficult for retrieval systems to match them accurately against structured product catalogs. This challenge is amplified by the one-to-many nature of user intent, where a single query can imply diverse and competing needs. Existing methods, including neural query expansion and prompting-based LLM approaches, fall short in real-world settings: they struggle to capture nuanced user intent, often generate outp…

Instacart integrates its retail data with TikTok Ads Manager, letting consumer packaged goods advertisers target audiences and measure conversions within TikTok (Anu Adegbola/Search Engine Land)
https://searchengineland.com/instacart-tiktok-ads-manager-463072

Instacart brings retail media targeting to TikTok Ads Manager
The partnership lets CPG advertisers use Instacart’s retail data to target high-intent shoppers and track purchases directly within TikTok.

Demographically-Inspired Query Variants Using an LLM
Marwah Alaofi, Nicola Ferro, Paul Thomas, Falk Scholer, Mark Sanderson
https://arxiv.org/abs/2508.17644 https://

Demographically-Inspired Query Variants Using an LLM
This study proposes a method to diversify queries in existing test collections to reflect some of the diversity of search engine users, aligning with an earlier vision of an 'ideal' test collection. A Large Language Model (LLM) is used to create query variants: alternative queries that have the same meaning as the original. These variants represent user profiles characterised by different properties, such as language and domain proficiency, which are known in the IR literature to influence quer…

YouTube launches the Activation Partners program to connect advertisers and agencies with a curated network of experts specializing in YouTube campaigns (Anu Adegbola/Search Engine Land)
https://searchengineland.com/youtube-activation-partners-program-463025

YouTube launches Activation Partners program
YouTube’s new program links advertisers and agencies with vetted third-party experts in media buying and campaign management.

Efficient Patent Searching Using Graph Transformers
Krzysztof Daniell, Igor Buzhinsky, Sebastian Bj\"orkqvist
https://arxiv.org/abs/2508.10496 https://

Efficient Patent Searching Using Graph Transformers
Finding relevant prior art is crucial when deciding whether to file a new patent application or invalidate an existing patent. However, searching for prior art is challenging due to the large number of patent documents and the need for nuanced comparisons to determine novelty. An accurate search engine is therefore invaluable for speeding up the process. We present a Graph Transformer-based dense retrieval method for patent searching where each invention is represented by a graph describing its…