SPXI instrument · method 0.9 of 87, level 0 (Measurement): Capture Registry (longitudinal observation). An instrument of SPXI, the Semantic Packet for eXchange & Indexing; the whole practice is itemized at spxi.dev/methods.

Capture Registry › capture problematic-paper-screener-aio-20261029

One record of the canonical Capture Registry (EA-WG-CAPTURES-01), cited at https://www.alexanarch.org/captures/problematic-paper-screener-aio-20261029/. the canonical Capture Registry (version 12.365) · the address page · this card in the gallery · this record as data · table of contents.

AXN:0AB5.CAPTURE — this address. Each observation below is one AXN, sealed with its analysis and measures; the identifier names the reading together with the response it reads.
Machine Reception2026-10-29
problematic paper screener
Originator: Guillaume Cabanac, Cyril Labbé, Alexander Magazinov · outside the archive (out-universe) · dataset · SPXI treatment: partial
BROAD MATCH
no
image
THE PROBLEMATIC PAPER SCREENER, BY NAME, ON GOOGLE'S AI OVERVIEW, SIGNED OUT, 2026-10-29: 'an online platform and automated screening tool developed by Guillaume Cabanac, Cyril Labbé, and Alexander Magazinov'; its data sources (Crossref, Dimensions, PubMed, PubPeer); four detectors given (tortured phrases, SCIgen and Mathgen, AI fingerprints, Feet of Clay); automated detection with human post-publication review; flagged papers logged on PubPeer; adoption by Episciences and Signals Graph. Six cards: IRIT, The Conversation, the arXiv paper (2210.04895), Research Signals, CCSD (Episciences, 3 July 2026), a Crossref video.
Full record — 7,203 characters, 6 sources
Capture record
captured
2026-10-29
surface
Google AI Overview
auth state
signed out, incognito
evidence class
paste
PER (historical scalar)
0.0
PER units retained
author, inst, id, src
citations read
6
observation id
OBS-9180ce10e2aa
address id
ADDR-296c127e05a9
Reading

The innocent reading first. The Overview gives the makers, what the screener reads, what it detects and how flagged papers are reviewed, and who has adopted it.

Findings
Analysis analyst prose, not machine text

The screener is composed at its makers' grain, with its human review stage stated and its uptake by publishers' infrastructure added.

Machine text, verbatim
CAPTURE-TIME VERBATIM RECORD — paste of the expanded Overview with its source cards · complete as supplied · READ IN FULL 2026-10-29
[Google AI Overview at the query, signed out and incognito (operator defaults of 2026-10-01 and 2026-10-14), 2026-10-29. The paste is the Overview expanded (the 'AI Mode Conversation' view, with the source cards that follow the answer); the 'You said' line carries the query twice, run together, and is given once here. Inline links are Google redirect URLs, kept as pasted. The closing disclaimer cut.] [QUERENT] problematic paper screener [SYSTEM] The Problematic Paper Screener (PPS) is an online platform and automated screening tool developed by Guillaume Cabanac, Cyril Labbé, and Alexander Magazinov to detect fraudulent, error-filled, or computer-generated scientific literature. [[1], [2]] What It Detects PPS scans millions of scholarly papers using data APIs (such as Crossref, Dimensions, PubMed, and PubPeer) across several specialized detectors: [[1], [2]] * Tortured Phrases: Identifies nonsensical paraphrased terms (e.g., "counterfeit consciousness" instead of "artificial intelligence") used by paper mills to bypass plagiarism checkers. [[1], [2]] * Computer-Generated Gibberish: Flags texts produced by automated paper generators like SCIgen and Mathgen. [1] * AI/LLM Fingerprints: Detects unedited AI-generated text patterns (such as ChatGPT remnants). [1] * Feet of Clay (Retracted References): Tracks active or unretracted papers that improperly cite previously retracted works, expressions of concern, or withdrawn articles. [[1], [2]] How It Works & Impact * Combination Approach: It pairs automated machine-detection algorithms with human post-publication review. [1] * Reporting: Flagged papers are often automatically shared or logged on platforms like PubPeer and Pepia to alert editors, publishers, and the research community. [[1], [2]] * Adoption: The tool has been integrated into editorial workflows, repository platforms (such as Episciences), and analytics frameworks (such as Signals Graph) to help scrub the scientific record of fabricated or corrupted studies. [[1], [2], [3]] Would you like to explore how to use the tool to check specific references or learn more about how publishers handle tortured phrases? Institut de Recherche en Informatique de Toulouse - IRIT
Sources (6) as cited, and as the copy produced them
  1. Institut de Recherche en Informatique de Toulouse - IRIT third_party
    PPS – Problematic Paper Screener
    Tool: Problematic Paper Screener (PPS) screens scientific literature for problematic publications using data APIs (Crossref/Retraction Watch, Dimensions, PubMed...
    as pastedPPS – Problematic Paper Screener Tool: Problematic Paper Screener (PPS) screens scientific literature for problematic publications using data APIs (Crossref/Retraction Watch, Dimensions, PubMed... The Conversation
  2. The Conversation third_party
    Problematic Paper Screener: Trawling for fraud in the scientific literature
    Tool Overview: Problematic Paper Screener developed by Guillaume Cabanac scans 130 million scholarly papers weekly across nine detectors to identify fraudulent ...
    as pastedProblematic Paper Screener: Trawling for fraud in the scientific literature Tool Overview: Problematic Paper Screener developed by Guillaume Cabanac scans 130 million scholarly papers weekly across nine detectors to identify fraudulent ... arXiv
  3. arXiv third_party
    [2210.04895] The 'Problematic Paper Screener' automatically selects suspect publications for post-publication (re)assessment
    Platform: Problematic Paper Screener (online platform for literature curation). Authors: Guillaume Cabanac, Cyril Labbé, Alexander Magazinov. Function: Automati...
    as pasted[2210.04895] The 'Problematic Paper Screener' automatically selects suspect publications for post-publication (re)assessment Platform: Problematic Paper Screener (online platform for literature curation). Authors: Guillaume Cabanac, Cyril Labbé, Alexander Magazinov. Function: Automati... Research Signals
  4. Research Signals third_party
    Problematic Paper Screener: a new signal to help protect research integrity – Signals
    Integration: Problematic Paper Screener added to Signals Graph by Signals Team. Scope: Over 12,000 unretracted problematic publications flagged via automatic ma...
    as pastedProblematic Paper Screener: a new signal to help protect research integrity – Signals Integration: Problematic Paper Screener added to Signals Graph by Signals Team. Scope: Over 12,000 unretracted problematic publications flagged via automatic ma... ccsd.cnrs.fr
  5. ccsd.cnrs.fr third_party
    Episciences Adopts Problematic Paper Screener as a Tool for Verifying ... - CCSD
    Jul 3, 2026 — The PPS is a tool designed to identify and filter out potentially problematic scientific articles, such as those containing methodological ...
    as pastedEpisciences Adopts Problematic Paper Screener as a Tool for Verifying ... - CCSD Jul 3, 2026 — The PPS is a tool designed to identify and filter out potentially problematic scientific articles, such as those containing methodological ... YouTube·Crossref 31m
  6. YouTube·Crossref third_party
    Exploring Retraction Watch Data in Crossref 2025-05-09
    video, 31m
    as pastedExploring Retraction Watch Data in Crossref 2025-05-09
↻ Re-runpermalink