What really matters

The title is clickbait as nobody really knows what is really relevant in science although some people still think that a few failed postdocs at NSC (Nature, Science, Cell) are the ultimate judges here.

Google also did not know in the 1990ies when they invented the pagerank with the now famous words “The prototype with a full text and hyperlink database of at least 24 million pages is available at http://google.stanford.edu”.

https://twitter.com/methode/status/1781357974578995315

Everybody since then believed in the authoritative power of links but according to Roger Montti they are no more relevant as at a recent conference in Bulgaria Google’s  Gary Illyes confirmed that links have lost their importance. And maybe even Google at all?


CC-BY-NC

Facts Don’t Change Our Minds Unfortunately

James Clear adds the reason

Truth and accuracy are not the only things that matter to the human mind. Humans also seem to have a deep desire to belong … Humans are herd animals. We want to fit in, to bond with others, and to earn the respect and approval of our peers. Such inclinations are essential to our survival. For most of our evolutionary history, our ancestors lived in tribes. Becoming separated from the tribe—or worse, being cast out—was a death sentence.” … Convincing someone to change their mind is really the process of convincing them to change their tribe … If you want people to adopt your beliefs, you need to act more like a scout and less like a soldier. At the center of this approach is a question Tiago Forte poses beautifully, “Are you willing to not win in order to keep the conversation going?”

Hard to accept for a scientist but probably true.


CC-BY-NC

The best paper in 2024

“Life is too short to be serious all time”, GILE Journal of Skills Development, Vol. 4 No. 1 (2024)

In this food for thought article, we introduce the ‘Donald Duck Phenomenon’ to consider ten of the more unconventional reasons for publishing in academia. These include
(i) symbolic immortality,
(ii) personal satisfaction,
(iii) a sense of pride,
(iv) serious leisure,
(v) cause credibility,
(vi) altruism,
(vii) collaboration with a friend or family member,
(viii) collaboration with a hero,
(ix) conflict or revenge, and
(x) for amusement.
The article was inspired by the lead author’s social media search for a co-author with the surname ‘Duck’. Through LinkedIn, the lead author, Associate Professor William E. Donald, who is based in the UK and specialises in Sustainable Careers and Human Resource Management, found a collaborator, Dr Nicholas Duck, who is based in Australia and specialises in Organisational Psychology. While the collaboration may appear to be somewhat ‘quackers’, per one of Donald Duck’s famous phrases “Life is too short to be serious all the time, so if you can’t laugh at yourself then call me… I’ll laugh at you, for you”. We hope that this article offers some interesting insights and acts as a way to stimulate conversation around unconventional reasons for publishing in academia.


CC-BY-NC

At this point

James claims

At this point, I feel bleak at the prospect of typing them out again. The problems with overpublication, ‘publish or perish’ culture, abusive lab environments, analytical flexibility, p-hacking, clinical trial registration games, grant front-running, intellectual capture, nonsense journals, fake journals, peer review manipulation, moral entrepreneurship, etc. precede the present discussions of paper mills and active falsification/fabrication cases…
I have tried at least four times in my memory to write out and codify how I would start an institute to combat these problems. Specifically, a formal organization under a 501c3 structure designed to address the problem.

In Germany we have the IQWIQ, an independent Institute for Quality and Efficiency in Health Care who examines the benefits and harms of medical interventions for patients. But they don’t care about all the medical nonsense studies around. And without PubPeer we wouldn’t even know the nonsense…


CC-BY-NC

From start to finish programming with ChatGPT in 60s

Create a PHP script that can read a CSV in the form start_date, end_date, event and output as ICS file

function convertDate($date)
{
    $dateTime = DateTime::createFromFormat('m/d/Y', $date);
    if ($dateTime === false) {
        return false; // Return false if date parsing fails
    }
    return $dateTime->format('Ymd');
}

// Function to escape special characters in text
function escapeText($text)
{
    return str_replace(["\n", "\r", ",", ";"], ['\n', '\r', '\,', '\;'], $text);
}

// Read CSV file
$csvFile = 'uci.csv'; // Replace with your CSV file name
$icsFile = 'uci.ics'; // Output ICS file name

$handle = fopen($csvFile, 'r');
if ($handle !== false) {
    // Open ICS file for writing
    $icsHandle = fopen($icsFile, 'w');

    // Write ICS header
    fwrite($icsHandle, "BEGIN:VCALENDAR\r\n");
    fwrite($icsHandle, "VERSION:2.0\r\n");
    fwrite($icsHandle, "PRODID:-//Your Company//NONSGML Event Calendar//EN\r\n");

    // Read CSV line by line
    while (($data = fgetcsv($handle, 1000, ',')) !== false) {
        $startDate = convertDate($data[0]);
        $endDate = convertDate($data[1]);
        print_r($data) . PHP_EOL;
        echo $startDate;
        
        if ($startDate === false || $endDate === false) {
            continue;
        }
        $event = escapeText($data[2]);

        // Write event to ICS file
        fwrite($icsHandle, "BEGIN:VEVENT\r\n");
        fwrite($icsHandle, "UID:" . uniqid() . "\r\n"); // Unique identifier
        fwrite($icsHandle, "DTSTART;VALUE=DATE:" . $startDate . "\r\n");
        fwrite($icsHandle, "DTEND;VALUE=DATE:" . $endDate . "\r\n");
        fwrite($icsHandle, "SUMMARY:" . $event . "\r\n");
        fwrite($icsHandle, "DESCRIPTION:" . $event . "\r\n");
        fwrite($icsHandle, "END:VEVENT\r\n");
    }

    // Write ICS footer
    fwrite($icsHandle, "END:VCALENDAR\r\n");

    // Close files
    fclose($icsHandle);
    fclose($handle);

    echo "ICS file generated successfully.";
} else {
    echo "Error: Unable to open CSV file.";
}

Source data are from UCI and output is here from where it can be added as a calendar. BTW created also my first “hello world” Swift/iPhone app using this source although this took a bit more time…


CC-BY-NC

The lifetime of the spectacular scientific result

Lior Pachter has an interesting observation

Low IQ scores predict excellence in data science

which goes back to an old article of Richard Guy extracting four major issues in interpreting data

  • Superficial similarities spawn spurious statements.
  • Capricious coincidences cause careless conjectures.
  • Early exceptions eclipse eventual essentials.
  • Initial irregularities inhibit incisive intuition.

Unfortunately this seems to describe the way we think and even worse – this is what the science system promotes: the spectacular, the unexpected, the fascinating news.

To continue his story, what is the lifetime of the spurious idea?  In many instances effects are declining rapidly for example in intelligence research. It took me some time to find the first paper that I remember – it was in 2001 that John & Despina wrote that the results of the first study correlate only modestly with subsequent research on the same association. This was confirmed in 2005

Of 49 highly cited original clinical research studies, 45 claimed that the intervention was effective. Of these, 7 (16%) were contradicted by subsequent studies, 7 others (16%) had found effects that were stronger than those of subsequent studies, 20 (44%) were replicated, and 11 (24%) remained largely unchallenged.

A scandal?  The list of failed studies is long, including all areas of biomedicine already back in 2015.


CC-BY-NC

Another thread to science as we know it

While AI may not break science for being backwards directed, there are already the first companies doing AI interviews.

https://www.micro1.ai/vetting-process

Could become a big problem whenever universities are also using this type of job interviews.

Just like journals who use AI for peer review

The authors of the study1, posted on the arXiv preprint server on 11 March, examined the extent to which AI chatbots could have modified the peer reviews of conference proceedings submitted to four major computer-science meetings since the release of ChatGPT. Their analysis suggests that up to 17% of the peer-review reports have been substantially modified by chatbots — although it’s unclear whether researchers used the tools to construct reviews from scratch or just to edit and improve written drafts.


CC-BY-NC

Wissenschaftler dürfen keine Aktivisten sein

Martin Schröder

Es tut der Wissenschaft nicht gut, wenn man probiert, sie auf politische Ziele festzulegen, selbst wenn diese weithin gesellschaftlich akzeptiert sind. Was ist die Alternative? Eine altmodische Idee von Max Weber. Sie heißt: Werturteilsfreiheit. Damit wollte Weber die Sozialwissenschaften gegen eine Vereinnahmung durch links und rechts bewahren. Wissenschaftler, so Weber, sollen erforschen, wie die Welt ist, nicht ihre Autorität nutzen, um anderen einzureden, wie die Welt sein sollte. Denn wo sich Werte widersprechen, kann man nicht wissenschaftlich entscheiden, welche richtiger sind. Forscherinnen und Forscher sollten sich deswegen aus politischen Diskussionen fernhalten.

oh ja, das hatte ich auch einmal im Ärzteblatt geschrieben was ich denn von Umweltepidemiologie halte, die vor 30 Jahren gegen und nun im Mainstream Nonsense Ergebnisse produziert.

Und nun auch in der neuesten ZEIT “warum eine Universität überhaupt eine politische Haltung hat”.

Also Positivismusstreit reloaded?

Nein, bestimmt nicht. Ohne einzelne Werturteile geht es natürlich nicht, sie sollten im Zweifel aber als “Conflicts of Interests” am Ende jedes wissenschaftlichen Artikels stehen. Wo die Tatsachen enden und wo die Interpretation anfängt.


CC-BY-NC

How to cite bookends references in LaTeX

attn: this is the chatGPT solution

In LaTeX, you can use the biblatex package along with a bibliography management tool like BibTeX … to manage your references. To cite references generated by Bookends, you would typically export your references from Bookends to a BibTeX (.bib) file and then include that file in your LaTeX document.

Here’s a general outline of how you can cite Bookends references in LaTeX using BibTeX:
1. Export your references from Bookends to a BibTeX (.bib) file.
2. Include the BibTeX file in your LaTeX document using \bibliography{your_bibliography_file}.
3. Cite the references in your document using \cite{} or \autocite{} commands, passing the citation key corresponding to each reference in your BibTeX file.

\documentclass{article}
\usepackage[backend=biber]{biblatex}

% Include your bibliography file
\bibliography{your_bibliography_file}

\begin{document}
Some text \autocite{citation_key}.

% Your content here

\printbibliography

\end{document}

Replace your_bibliography_file with the name of your BibTeX file (without the .bib extension), and replace citation_key with the citation key of the reference you want to cite.

After compiling your LaTeX document with the appropriate compiler (usually something like pdflatex followed by biber and then pdflatex again), LaTeX will automatically format the citations and generate the bibliography according to the style specified in your document.

Make sure to choose a citation style compatible with your field or publication requirements. You can specify the citation style in the \usepackage[style=…]{biblatex} command. Popular styles include apa, ieee, chicago, etc.


CC-BY-NC

MacOS Pages getting line numbers

Mayn journals requiring consecutive line numbering which is not a problem with MS Word, Open Office or LaTeX but with Pages.

Maybe it is possible to add a new background to PDF? Acrobat can do it (which I would not recommend), there is some crazy script out there (that did not work as well as ). My initial solution

pandoc -s input.rtfd -o output.tex --template=header_template.tex | pdflatex -output-directory=output_directory

with the header_template.tex containing

---
header-includes:
- \usepackage[left]{lineno}
- \linenumbers
- \modulolinenumbers[5]
---

did not work as pandoc cannot read the rather complex rtfd format produced by Pages. Also the next try with rtf2latex2e looked terrible, so I went back to RTF export in Libre Office where I  corrected the few Math formulas that were not recognized correctly.

Another option would have been Google Docs – they introduced line numbering recently which is probably the fastest and easiest way to do that.

 

 

Whenver it comes to more than one formula, it would be even better to move from Pages to Overleaf (online) or Texifier (local).

 

 


CC-BY-NC

Digital humanities

Eine interessante Neuschöpfung, die “Digital Humanities” – siehe eine Einführung der GH Wuppertal

Die Digital Humanities (DH) sind eine Brücken-, Schnittmengen- und Metadisziplin in Bezug auf die Geisteswissenschaften, die Informationswissenschaft und die angewandte Informatik. DH schlägt die Brücke von den Forschungsgegenständen, Fragestellungen und Methoden der geisteswissenschaftlichen Disziplinen zu ihrer formalen Bearbeitbarkeit mit digitalen (computergestützten, algorithmischen) Verfahren. Sie bildet eine Schnittmenge zwischen den Disziplinen soweit es die Entwicklung und Anwendung informatischer Lösungen für geisteswissenschaftliche Problemlagen betrifft.

und Bücher gibt es bereits ohne Ende dazu


CC-BY-NC

More from Julia Lezhneva

 

https://it.wikipedia.org/wiki/Il_trionfo_del_tempo_e_del_disinganno

 

Tu del Ciel ministro eletto,
Non vedrai più nel mio petto
Voglia infida, o vano ardor.
E se vissi ingrata a Dio,
Tu custode del cor mio
A lui porta il nuovo cor.
https://lyricstranslate.com

 

da non perdere
https://www.universal-music.de/julia-lezhneva/videos/haendel-tu-del-ciel-ministro-eletto-384068


CC-BY-NC