THE INTERNET IS THINKING
Earlier sources: AI research
AI research investigates learning algorithms, model behavior, evaluation, and the limits of intelligent systems. Follow original papers and research artifacts; preprints may change and are not necessarily peer reviewed.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗48 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- arXiv · Published · First archived
FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents ↗
Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution's own standard. In FinAutoRubric, experts specify reusable evaluation guidance, while agents and code carry out query-specific rubric generation, review, and validation. This expert guidance governs every agent, as prompts and as rules that code enforces, and a Task Bank of reusable criteria carries it across tasks. In long-horizo…
- Hacker News · Posted on Hacker News · First archived
How Pew Research Center is – and is not – using AI in our work ↗
Hacker News discussion.
- arXiv · Published · First archived
Can Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping Research ↗
Meta-analysis is the synthesis of information from multiple sources to arrive at an overarching conclusion. There is a large need for meta-analysis in agricultural research to synthesize what is known and analyze overarching patterns. Extracting data from published literature is, however, labor-intensive, time-consuming, and tedious, and is impeded by a lack of standardization in research design, units of measurement, and terminology. These challenges are particularly evident in the domain of crop species mixtures, also called intercropping. With the growing capabilities of LLMs, many recent a…
- GitHub · Repository created · First archived
tomaszboloz/SEOmi ↗
Native macOS and Windows workspace for technical SEO audits, site crawling, semantic maps, keyword research, rank tracking, DataForSEO, Search Console, and AI visibility.
- Hacker News · Posted on Hacker News · First archived
Show HN: ParkourNote – A research workspace, built solo in a month with Claude ↗
Hi HN, I'm sushi. I built ParkourNote, a personal knowledge management app that currently focuses on research: finding papers, reading PDFs, asking AI about them, and writing. A few things it does: Describe a topic, and an agent creates a project, searches arXiv, and imports relevant papers The PDF reader previews citations on hover, overlays translations on the page, and shows original and translated text side by side The agent sees the page you…
- OpenAlex · Published · First archived
From Trial-and-Error to Learn-by-Experiment: The Future of Materials Research in Perovskite and Organic Photovoltaics ↗
The next major change in perovskite and organic photovoltaic research may not come from a new material or device architecture, but from a new way of doing and analyzing experiments. Conventional trial-and-error optimization, often a onevariable-at-a-time (OVAT) approach, typically varies a limited number of parameters sequentially, making it difficult to resolve interactions within the increasingly complex processing spaces of complex, multilayer solar cells and demands a large number of experiments. We argue that robotic experimentation combined with machine learning can fundamentally alter t…
- OpenAlex · Published · First archived
Design implications from research trends in generative AI for mathematics learning in higher education: A bibliometric study ↗
This study investigates the development and thematic evolution of research on generative artificial intelligence (AI) in higher-education mathematics through a bibliometric analysis of 256 Scopus-indexed publications from 1985 to 2025. Utilizing VOSviewer and Bibliometrix, the analysis examines publication and citation trends, research collaboration, influential contributors, and thematic structures within the field. The findings demonstrate a substantial increase in both publication volume and citation frequency, particularly in recent years, indicating heightened scholarly interest in genera…
- OpenAlex · Published · First archived
From Digital Twin to AI-Integrated Control: A Review and Research Agenda for Large-Scale PEM Electrolyzer Plant Management ↗
Large-scale green hydrogen production via PEM electrolysis demands control strategies that surpass the limitations of traditional distributed control systems (DCSs). Digital twin (DT) technology has been introduced as a structured design framework for predictive maintenance and operational optimization across hydrogen production pathways, from steam methane reforming and green ammonia to next-generation PEM electrolyzer. A critical constraint exists; passive DT architectures cannot autonomously close the control loop. The resulting prediction–action latency gap introduces delays of 28–120 min…
- Hacker News · Posted on Hacker News · First archived
Show HN: Updated Ceptile AI Search Improved Answers and Research ↗
We have recently updated Ceptile's AI answers and use of web sources. Now, It can go deeper and find more accurate answers and results than before. Now, it has become more powerful to give real-time answers. We have also fixed previous bugs. You can submit your review on our mail at support@ceptile.com. We have also upgraded our backend. You can try the AI search at ceptile.com. Watch 2 minutes demo on Youtube: https://www.youtube.com/watch?v=OR4…
- arXiv · Published · First archived
EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research ↗
Self-evolving agents aim to turn research feedback into reusable skills, tools, and research rules. Whether these accumulated capabilities continue to improve later research requires controlled evaluation. Long-horizon alpha discovery provides a state-dependent setting: once a new factor enters the portfolio, the predictive information already covered changes, so the value of the same candidate or experience may change over time. We introduce EverMine, an empirical framework for studying self-evolving research capabilities in long-horizon alpha discovery. EverMine decomposes the research state…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI research
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.