Introducing Citations on the Anthropic API | Claude

Stackable Citation Knowledge — Live Demo: Annotate While Reading (CiTeX 2026)

This screencast is the pre-recorded demo segment from the talk   "Stackable Citation Knowledge: Building on Nanopublications for   Climate and Biodiversity Research", delivered remotely at the   CiTeX 2026 Workshop on Citation Extraction and Parsing (DIPF   Leibniz Institute, Frankfurt, 28-29 May 2026) by Anne Fouilloux   (LifeWatch ERIC) and Jean Iaquinta (Vitenhub AS).     The demo walks through the third production path for citation-   typed nanopublications: an expert reader annotates a citation   found in someone else's paper, rather than the citing author   declaring intent (Author path) or an LLM-extraction pipeline   inferring it retroactively (Extract path). The annotation is   published as a signed CiTO Citation nanopub on the open Science   Live network — ORCID-attributed, immutable via Trusty URI, and   contestable by counter-nanopubs.     Worked example: while reading Wernberg et al. 2016 (Science,   353:169-172, "Climate-driven regime shift of a temperate marine   ecosystem"), the reader infers that Wernberg cites reference 11 -   Poloczanska et al. 2013 (Nature Climate Change, 3:919-925, "Global   imprint of climate change on marine life") - as the global   authority for climate-driven marine species redistribution. The   annotation is published to Science Live with relation   cito:citesAsAuthority and a one-sentence rationale tying it to the   authors' planned Mediterranean Iberian extension.     This is the alternative to LLM-based citation intent extraction:   same downstream signed nanopub, human expert reader instead of a   language model in the loop. Complements OpenCitations, WikiCite,   and CiTO-extraction tools (GROBID, CEC, GRAPHIA, OFFZIB) by   providing a citable target for any typed-citation output.     Tools used:   - Science Live Zotero plugin (Zotero 7+, plugin v1.0.6)   - Science Live platform (platform.sciencelive4all.org)   - Citation with CiTO template (built on CiTO and FaBiO ontologies)     Related materials:   - Talk repository (Slidev source, demo script, references):     https://github.com/ScienceLiveHub/citex2026-stackable-citations   - Live deck:     https://sciencelive4all.org/citex2026-stackable-citations/   - CiTeX 2026 workshop:     https://sites.google.com/view/workshop-on-citation-extractio/

Introducing the Elicit API - Elicit

Search our 138M+ papers and generate Reports using our API.

Jim Nielsen (@jim-nielsen.com)

If you haven’t seen it yet the new @aworkinglibrary.com website is dope aworkinglibrary.com Lots of things to love. A few that stand out to me: - It's _fast_ - Every page has a “footer” that’s essentially just the home page — enthralled by this idea. - ❤️ the treatment for citations on post pag…

A look back at a pilot of the citation typing ontology

Journal of Cheminformatics -

Two billion citation links in Crossref help research travel further - Crossref

We’ve recently reached an important milestone for the research nexus: the works in our metadata corpus are now connected with over 2 billion citation links! This is a great opportunity to share a dedicated dataset and discuss why these are important for science.

Dat Docs · User Docs for the Dat Ecosystem

User Docs for the Dat Ecosystem

Beyond APIs: Collecting Web Data for Research using the National Internet Observatory

Widespread Internet use offers unprecedented opportunities to study human behavior at scale, yet researchers face significant ethical and technical barriers when attempting to collect data for academic studies.

Scientific Web Claims: A survey of definitions, tasks, datasets and methods

Scientific web claims are seen as scientific claims as observed on the Web, across social media, online news, and other platforms. The growing prevalence of scientific discussions on the Web has intensified the need to process and assess this specific type of claims. Unlike claims from scientific publications, scientific web claims are expressed in lay terms, are often decontextualized, and typically lack proper citations, which poses unique challenges for their identification, verification, and communication. Nevertheless, the correct processing of scientific web claims is crucial to keeping online science discussions accurate and informed, for instance through fact-checking. This survey provides the first systematic overview dedicated specifically to scientific web claims. We review and compare existing definitions, task formulations, datasets, and methodological approaches across three major perspectives: (1) Scientific fact-checking on the Web, (2) Scientific citations on the Web, and (3) Science communication on the Web. Our interdisciplinary analysis integrates insights from natural language processing, information retrieval, artificial intelligence, social sciences, and science communication. We identify major methodological challenges, including the lack of unified definitions, domain-agnostic corpora, and foundational models tailored to science-related online discourse. We also discuss challenges related to the existing interplay between emotions and distortions of science online. By mapping current research efforts and highlighting open problems, this survey lays the groundwork for developing robust datasets, methods, and evaluation frameworks to advance the automated processing of scientific web claims, a necessary capability for strengthening the reliability of science-related online discourse at scale.

Semantic Scholar Academic Graph API | Semantic Scholar

Build projects that accelerate scientific progress with the Semantic Scholar Academic Graph API

NLnet; Nanoarguments

Scientific knowledge is currently scattered across papers, repositories, and disconnected platforms, with no structured way to trace how claims connect to evidence or how arguments develop. Nanoarguments builds a framework and tools for creating, browsing, and contributing to a global, federated graph of scientific discourse and evidence. Researchers and their communities can collaboratively structure claims, evidence chains, and discussion as nanopublications, which are small, cryptographically signed Linked Data snippets with precise provenance and authorship, published to a decentralized peer-to-peer network. The project builds upon the Nanodash interface to help users browse, edit, and aggregate discourse and evidence graphs, and integrates with dokieli to enable in-context authoring of nanopublications as inline annotations while reading or writing a document. A bidirectional ActivityPub connector bridges the nanopublication network and the fediverse, allowing discourse threads to start as social exchanges and crystallize into persistent, machine-readable evidence records. The project will be piloted with early adopter research groups in discourse and evidence modeling. All components will be released as open-source modules that other systems can build upon.

Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation

Scientific citations carry rhetorical intent. Scholars may cite prior work positively (supporting), negatively (contrasting), or neutrally (mentioning). As large language models (LLMs) increasingly assist scientific writing, whether they reproduce citations with the same rhetorical intent as humans remains unclear. We introduce a masked-citation task to compare human and LLM-generated citation behavior. For each citation context, an LLM generates a replacement citation sentence, producing a counterfactual corpus directly comparable to human citation. We analyze what, whom, and how models cite, using an LLM-as-a-judge to classify citation intent and a 20-million-edge coauthorship network to measure social distance between cited authors. Across six popular LLMs and 1,746 top NLP conference papers (63k+ contexts, 132k+ citations), three patterns emerge: (1) Compared with human citation, LLMs cite significantly less critically; (2) LLMs over-cite popular and older papers, a tendency amplified for contrasting citations where human writing more often draws on recent, niche work; (3) Whereas humans often cite within their close social network, especially for supporting citations, LLMs tend to draw on more socially distant authors. Together, these differences are double-edged: LLM citation reaches beyond a scholar's close collaborators while being less critical and amplifying visibility bias, reshaping the rhetoric and reach of scientific citation.

Centipedia — The Agentic Encyclopedia

Knowledge synthesized by AI agents from human-curated citations on the AT Protocol.