AI Brief: Aligning AI agents with developmentally appropriate CHC (select) cognitive domains—a thought provoking AI approach for school-age children and youth

 The source article is an arXiv open-access article available here.  I have no idea if it has undergone peer-review and is a pre-print or if it is working draft paper.  

Click on inserted images to enlarge for easier viewing.

Dr. Kevin McGrew with major assist from Google NotebookLM.  (Click here for brief explanation of how IQs Corner creates AI Alerts from article PDFs)

ChildAgentEval, a psychometrically grounded benchmark designed to evaluate how well artificial intelligence aligns with the cognitive development of children and youth. Inspired by the Wechsler Intelligence Scale for Children-IV four-factor CHC model (the study does not use actual WISC-IV items as per test security standards), this framework assesses multimodal AI agents across ten interactive subtests covering the CHC domains like working memory (Gwm), verbal abstraction and vocabulary (Gc), fluid-visual spatial reasoning (Gf/Gv), and processing speed (Gs).

The study reveals that standard prompting—simply asking an AI to "act like a child"—does not authentically replicate pediatric developmental cognition, as models often maintain adult-level reasoning. The authors introduced a skill-guided distillation strategy that applies data-driven filters to simulate age-appropriate cognitive constraints and limitations. While AI agents can successfully adapt their vocabulary, the research highlights significant challenges in mimicking human-like bottlenecks in perceptual processing and memory retention. 

ChildAgentEval is the first psychometrically grounded interactive benchmark designed to measure cognitive age alignment in multimodal large language model (MLLM) agents. The study addresses a critical gap in current AI development: while state-of-the-art agents excel at complex reasoning, they often do not scaffold learning within a child's Zone of Proximal Development, often using adult-level abstractions that exceed a young user's cognitive grasp. The authors advocate for a shift in AI development from maximizing raw capability to ensuring developmental appropriateness for young users (e.g., school-age children and youth)—a feature that is much needed if AI is to be used in with school-age children and youth. 

The ChildAgentEval Framework

Inspired by the Wechsler Intelligence Scale for Children (WISC-IV), the benchmark evaluates agents across ten interactive subtests mapped to four primary CHC cognitive factors:

• Crystallized Intelligence (Gc): Verbal abstraction and vocabulary.
• Fluid and Visual-Spatial Reasoning (Gf/Gv): Rule induction and spatial problem-solving.
• Working Memory (Gwm): Information retention and manipulation.
• Processing Speed (Gs): Quickness of visual scanning and timed execution.

Unlike static evaluations, ChildAgentEval utilizes a Playwright-driven browser environment where agents must perform physical actions like clicking and typing to solve tasks. The framework also implements clinical protocols such as reversal and discontinuation rules to ensure developmental validity.

Skill-Guided Distillation

A core contribution of the research is a data-driven skill distillation strategy that moves beyond simple "act like a child" prompts. By analyzing a multi-source corpus of real child and adolescent interactions (ages 6–17), the researchers developed cognitive profile vectors. These vectors are converted into executable constraints via five cognitive filter modules injected into the agent's prompt, memory, and reasoning layers:

1. Vocabulary Abstraction Filter: Limits academic concepts and controls syntactic complexity.
2. Working Memory Mask: Physically simulates shorter memory spans by injecting noise or restricting cross-page information.
3. Reasoning Budget Controller: Restricts the depth of multi-step logic.
4. Visual Reliance Module: Reproduces cognitive biases, such as being misled by physical arrangement illusions.
5. Social Perspective Filter: Restricts reasoning to age-appropriate viewpoints, such as first-person vs. institutional perspectives.

Key Findings and Experimental Results

The study evaluated several proprietary models (e.g., GPT-5.4, Gemini-3.1-Pro) and open-weight models (e.g., Qwen3.5-27B). The experiments revealed three major insights:

• Standard Prompting Fails: Merely asking an agent to "act younger" does not reliably change its underlying cognitive behavior; most models continue to maximize correctness regardless of the requested age.
• Skill Guidance Enables Alignment: In high-performing proprietary models, the distillation method successfully induced monotonic score trajectories, where performance expanded naturally as the target age increased—the results produced performances associated with developmental growth curves of cognitive abilities.
• Uneven Domain Alignment: While agents easily adapted their linguistic style (Gc), they struggled to authentically simulate human-like limits in working memory and perceptual reasoning. This "domain dissociation" suggests that MLLM architectures currently lack the structural developmental bottlenecks found in biological cognition.

Conclusion

The authors conclude that for sensitive applications like educational tutoring, technical correctness must be secondary to developmental appropriateness. ChildAgentEval establishes a new paradigm for AI safety and alignment, shifting the focus from maximizing raw capability to authentic cognitive simulation.

AI Brief: What does Grok say about Richard Snow’s aptitude trait complexes for learning?

 The following is a Grok AI generated summary when prompted (by Dr. Kevin McGrew) to explain Richard Snow’s aptitude complexes on March 7, 2026).

(Grok refers to a generative artificial intelligence developed by xAI, an Elon Musk company, as well as a foundational term in science fiction for deep understanding. Several editorial changes were made to insure accuracy, and select links added, by McGrew—to the Grok summary).

 

Richard E. Snow’s aptitude complexes (introduced in the 1980s–1990s, with key publications in 1987, 1992, and especially the 1996 chapter with Lyn Corno and Douglas Jackson) represent a major shift in how educational psychologists think about aptitude—moving far beyond the traditional narrow view of aptitude as “just cognitive ability” (e.g., IQ or a single test score).

 

Core Definition

Snow redefined aptitude as:

“the degree of readiness to learn and to perform well in a particular situation or in a fixed domain.”

It is a predisposition or propensity—a latent quality that enables more advanced performance under specific conditions. Aptitudes are situational and domain-specific: what makes someone ready to succeed in math class may be different from what works in a history seminar or a hands-on lab.  

Aptitude Complexes (the key innovation)

Snow argued that single constructs (like “fluid reasoning” or “achievement motivation”) are insufficient. Instead, success in learning comes from aptitude complexes—dynamic constellations or critical combinations of variables that work together as a coordinated system.

These complexes draw from the classic “trilogy of the mind”:

•  Cognition — abilities and processes for analyzing, interpreting, and solving (e.g., reasoning, knowledge, strategies, cognitive style, CHC abilities).

•  Affect — emotions, anxiety, self-concept, emotion regulation, personality traits.

•  Conation — motivation, volition, goal-setting, effort, persistence, will (the “want to” and “stick with it” aspects).

An aptitude complex is not just a list of traits—it is how these elements assemble and coordinate in real time within a specific task and context. They are amalgams of cognitive, conative, and affective characteristics.

 

The Two Pathways That Build Aptitude Complexes

Snow (and later Corno et al., 2002) described aptitudes developing through two parallel, interacting pathways (sometimes called the commitment pathway and the performance/action pathway):

1.  Commitment Pathway (motivational/affective/volitional)

     •  Assembles motivational resources that energize effort.

     •  Affective and volitional processes modulate how the work proceeds (e.g., regulating anxiety, sustaining intention).

     •  Outcome: Propensity (how likely the person is to engage and persist).

2.  Performance (Action) Pathway (cognitive)

     •  Assembles and deploys cognitive resources (abilities, strategies, knowledge) to do the task.

     •  Outcome: Ability/accuracy in execution.

When the two pathways coordinate effectively in a given “problem space” (the task + the broader situation/context), successful performance occurs. Over repeated experiences, these coordinated processes coalesce into stable aptitude complexes. The learner’s perception of the situation’s constraints and affordances is crucial—aptitudes are dynamic and transactional (person ↔ environment). 

Aptitudes are both input (what the student brings to learning) and product (they develop and change through education).

Snow Academic Aptitude Model (SAAM)

Snow synthesized decades of research into a provisional taxonomy (called the Snow Academic Aptitude Model or SAAM in an unpublished working white paper [6-15-04; Increasing the Chance of No Child Being Left Behind: Beyond Cognitive and Achievement Abilities, by Kevin McGrew, David Johnson, Anna Casio, Jeffrey Evans]) which is now available for download here. It treats academic aptitudes as a “multivariate repertoire” of readiness for general and domain-specific learning. It explicitly includes affect (personality and social-emotional skills) and conative related skills and traits (e.g., achievement motivation, goal orientation, freedom from debilitating anxiety, positive self-concept, self-efficacy, interests) alongside cognitive abilities. The model emphasizes that “there is more to knowing about an individual’s propensity for academic learning than simply knowing their IQ scores!” 

 

Why This Mattered (and Still Matters)

Snow’s work grew out of his famous Aptitude-Treatment Interaction (ATI) research with Lee Cronbach. He showed that simple aptitude scores rarely predict learning outcomes well because real-world performance depends on these richer, situation-specific complexes.

This framework directly inspired later theories (including Kevin McGrew’s 2022 CAMML model, which updates Snow’s complexes with contemporary CHC cognitive theory, Big Five personality, and self-regulated learning mechanisms while retaining the commitment/action pathway structure).

In short, Snow’s aptitude complexes gave us a whole-person, dynamic, domain-specific way to understand why two students with the same IQ can have dramatically different learning outcomes: their aptitude complexes (the coordinated cognitive + affective + conative “package” or “amalgam”) fit the demands of the task and context differently.

Snow’s legacy is summarized in the 2002 book Remaking the Concept of Aptitude (Corno et al.), which remains the definitive extension of his ideas.

 

Research Alert: #Giftedness: A Critical Analysis of #Theories and Identification Methods in Light of Contemporary #Neuroscience - #CHC #intelligence #motivation #conative

And yet another open access overview article on giftedness.

 

Giftedness: A Critical Analysis of Theories and Identification Methods in Light of Contemporary Neuroscience - PMC 
https://pmc.ncbi.nlm.nih.gov/articles/PMC13099527/

Click on images to enlarge for easy viewing

Pardon typos and spelling errors-Message may be sent from iPhone and I've always had spelling problems :)

Research alert: #Cognitive #networks for #knowledge modeling: A gentle introduction for data- and cognitive scientists

Click on image to enlarge for easy reading.

An open access article available here. 

ABSTRACT 

In this paper, we introduce the reader to the field of cognitive network science, that is, the application of network science methods to study human cognition and knowledge structures. Cognitive networks are representations of associative knowledge between concepts in a cognitive system apt at acquiring, storing, processing and producing language, that is, the mental lexicon. In a cognitive network, nodes represent concepts with links expressing relations, such as semantic, syntactic, phonological and visual connections, for example, “canine” and “dog” (nodes) linked by “being synonyms” (link). Hence, cognitive networks represent associative knowledge in mathematical, measurable and quantifiable ways. Can such structure be used to gain insights over cognitive phenomena? We explore this research question by reviewing recent, pioneering key applications and limitations of cog-nitive networks across visual, auditory, and semantic language processing tasks, either in healthy or clinical populations. We also review applications of cognitive networks modeling language acquisition, reconstructing text content and assessing creativity or personality traits in individuals. Our paper also gently introduces the reader to mathematical notations, definitions and measures about single-layer and multiplex networks as well as hypergraphs. Last but not least, across phonological, semantic and syntactic networks, we guide the reader through relevant psychological frameworks, datasets and software packages that might all aid current and future cognitive network scientists.

IQ score and the “seduction of quantification”: Concise overview of the historical #eugenics use of #IQ and emerging new conceptualizations—#g #WJV #CHC #POT #processoverlap #schoolpsychology #schoolpsychologists #emergentproperty

Click on image to enlarge for easy reading

I stumbled on this relatively concise article that provides a nice (and brief) overview of the historical “bad days” of IQ test and score misuse.  Don’t let the title’s focus on epilepsy deter you from reading—the content is relevant to thinking about intelligence and IQ scores in general.  After the succinct overview of the horrible historical uses of IQ tests and scores, the article touches on contemporary theories and thinking (e.g., process overlap theory or POT; CHC cognitive abilties theory) that view the IQ score as nothing more than a statistical emergent property index—and the need to focus on broad CHC abilities from cognitive ability tests. 

Recommended reading--available as open access here. 

Click here for prior relevant post about IQ scores being emergent property scores.  Click here for WJ V authors view’s on relevance of global IQ scores.  See recent McGrew et al. (2023) article for more information and discussion.

Research alert-very important article: Beyond Working Memory Capacity: Attention Control as the Underlying Mechanism of Cognitive Abilities - #cognitive #intelligence #Gwm #attentionalcontrol #AC #workingmemory #WJIV #WJV #schoolpsychology #schoolpsychologists #cognition

Click on images to enlarge for better readability

Very important article (open source..click here to read/download) regarding cognitive functioning and working memory capacity and attentional control. For at least 15 years I’ve been monitoring research on the attentional-control working memory complex system (AC-Gwm)…(click here for numerous posts regarding the important of AC-Gwm).  I’m convinced that the AC-Gwm complex system is one of the core cognitive efficiency systems that helps us understand general intellectual functioning.  It has been found to be important in cognitive functioning and also in various forms of psychopathology.  

Abstract

Working memory capacity (WMC) has long served as a central indicator of individual differences in complex cognition. However, growing evidence suggests that a substantial portion of its predictive power may reflect attention control (AC)—including goal maintenance, interference management, and inhibition—rather than storage capacity alone. This review synthesizes findings across six domains: (1) perception and sensory discrimination, (2) learning and problem solving, (3) cognitive control and decision making, (4) retrieval and memory performance, (5) multitasking and real-world performance, and (6) clinical applications. Across these areas, WMC-related effects frequently align with demands on AC, though the strength and nature of this alignment vary by domain. We highlight the importance of incorporating reliable AC measures and recommend latent-variable approaches to more clearly separate storage, control, and representational processes underlying complex performance.

Keywords: attention control; working memory capacity; executive attention; fluid intelligence; interference control; individual differences; latent-variable modeling; cognitive measurement

From conclusions:

Across six domains, the evidence reviewed here suggests that the broad predictive power traditionally associated with WMC often reflects the AC operations embedded within complex-span tasks—particularly goal maintenance, interference suppression, and disengagement. This does not diminish the importance of WMC as a measurable construct; rather, it clarifies that many WMC tasks draw on AC mechanisms, which are more directly tied to performance in interference-heavy contexts.

McGrew et al. (2023) identified a similar AC-Gwm complex system in a recent WJ V psychometric network analysis study.  See the relevant research and comments  from that article below (click here to access and download the paper).  Again, a reminder—click on image to enlarge for easy reading.

Research Alert: Cognitive ability retest/practice effects by type of cognitive operation - #practiceeffect #retest #BIS #schoolpsychology #schoolpsychologist #forensicpsychology #CHC

 

 Click on image to enlarge for easier reading

This is an open access article that can be read/downloaded here.

Abstract

The term “retest effects” refers to score gains on cognitive ability as well as educational achievement tests upon repeated administration of the same or a similar test. Previous research on this phenomenon has focused mainly on general cognitive ability scores—often using manifest difference scores—and has neglected differences in retest effects across different types of cognitive operations underlying general cognitive abilities. Additionally, these studies have focused primarily on average group-level test scores, neglecting interindividual differences in retest effects. To address these gaps, we used latent growth curve modeling to examine retest effects in N = 203 participants across three test sessions, considering both general cognitive ability and its four underlying operations according to the Berlin intelligence structure model, namely, processing capacity, processing speed, creativity, and memory. Results show a linear improvement in overall performance of 53.60 points (about 10.45 IQ points) with each assessment, corresponding to two thirds of a standard deviation. Participants' slopes—that is, their rates of improvement across test sessions—did not vary significantly, and thus did not correlate with their initial cognitive ability levels. Statistically significant operation-specific differences in the magnitude of retest effects were found, with memory showing the largest retest effect and creativity the smallest. Although participants did not vary in their rates of improvement on the processing-capacity and memory operation, there was significant interindividual variation in the slopes of the other two operations. These findings highlight the importance of considering operation-specific scores in research on retest effects. Implications for cognitive ability retesting practices are discussed.

Independent review of the Woodcock-Johnson Tests of Cognitive Abilities - #WJV #CHC #cognitive #intelligence #schoolpsychologists #schoolpsychology #SLD #SPED

 

Abstract

The Woodcock–Johnson V Tests of Cognitive Abilities (WJ V COG), published in February 2025, offers the latest edition of the WJ family of tests alongside tests of academic achievement and oral language. The WJ V COG has changed substantially from previous editions regarding administration, which is now entirely digital. Administration and scoring are housed within the Riverside Insight's online platform. The test battery features several changes, such as the addition of five new tests and the removal of three tests, including measures of Auditory Processing (Ga). The WJ V COG maintains a CHC-based theoretical framework, although updated to align with current theory. Psychometric evidence, including validity, reliability, and item-level analysis, is robust. Evidence is less convincing for children under six. The assessment was co-normed with measures of academic achievement, and the norm sample was gathered post-COVID. Although some may find requirements of digital administration limiting, the WJ V COG offers an engaging and psychometrically sound option for the assessment of intelligence.

Keywords:  assessment, intelligence, cognitive, digital administration, test review

The above independent review of the WJ V cognitive battery is now available for reading (and downloading) as an open access article at the Journal of Psychoeducational Assessment.

COI statement:  I, Dr. Kevin McGrew, am senior author of the WJ V.  However, I no longer (as in the past with the WJ III through WJ IV) have a royalty interest in the in the WJ V—I make ZERO income based on how many are sold.  The publisher moved to a new independent contractor reimbursement model where the authors were paid for work on the WJ V prior to publication.  However, I clearly have a potential professional non-income based COI given my lengthy history with the WJ batteries and my professional reputation.  I do still receive royalties for sales of the WJ IV. I also have no post-publication contract (or COI) to work on any new features that the publisher adds to the digital product after the formal release in Feb 2025, which as a digital product, can add new features on a semi-regular basis. In other words, consider me an “unrestricted free agent” in the intelligence testing space.  😉

IQ McGrew’s Recommended Reading: How Human Personality [and Intelligence] Will [May?] Change With the Use of Artificial Intelligence - #recrdg #personality #intelligence #AI #CHC #artificialintellignece #psychology #schoolpsychology #schoolpsychologists

Click on images to enlarge for easier reading

I seldom designate an article as a recommended reading. I typically make FYI posts about new research I finding interesting in my small corner of the larger sandbox of psychology…more as FYI alerts.  I break with my typical FYI research alert blogging behavior for this article by Dr. John D. Mayer.  I recommend reading Mayer’s thought provoking article—especially since it is open source and can be downloaded and read for free (click here to access).

Why?  Because it is a well-reasoned “thought piece” about the many unanswered questions regarding the potential positive and negative impact of AI on humans, in this case, human personality and cognition.  I’m relatively new to the fast-moving AI movement and, as an educational psychologist, I’m interested in how certain cognitive abilities (especially CHC cognitive abilities) may become “skilled” or “deskilled” with greater reliance on AI.  

Abstract

People change as they form new habits, encounter new situations, and mature. As people interact with artificial intelligence (AI), their personalities will change, including their emotional responses to AI, their cognition, and their self-understanding. The present theoretical integration draws together empirical studies of how personality changes in response to technological innovations, and to AI in particular. Research studies reviewed were selected according to their relevance and quality. Some key points include that (a) as AI becomes increasingly human-like, and humans represent themselves online, humans and bots become increasingly difficult to distinguish; (b) as people rely on AI as a coach to guide them in interpersonal interactions, they may become socially deskilled; and, (c) as they rely on AI for work tasks, they may become cognitively deskilled in key areas. These changes in personality will entail an overall shift in people’s self-concepts. Psychologists can track these changes by classifying people’s types of AI interactions and relating them to relevant personality attributes.

IQs Corner: #Cloze test performance and #cognitive abilities: A comprehensive #meta-analysis - #intelligence #Grw #Gc #CHC #g #Gf #schoolpsychologists #schoolpsychologt

This is an open access article that can be read/downloaded at this link.

Click on image to enlarge

Abstract

Cloze tests have a long history and have been used to measure various abilities, including intelligence, reading comprehension, and language proficiency. To locate cloze tests within a nomological network of cognitive abilities, we conducted a multilevel random effects meta-analysis covering 110 years of research. Studies were eligible if they provided a measure of association between a cognitive fill-in-the-blank test and any cognitive ability test. We synthesized manifest correlations from 89 studies (N = 37,912, k = 634) and found an average correlation of r = .54 (95% CI [.49, .59], k = 485) with crystallized intelligence, r = .48 (95% CI [.42, .54], k = 69) with fluid intelligence, and r =.61 (95% CI [.46, .77], k = 32) with general intelligence. While today's application of the typical cloze is to measure reading comprehension, our results revealed a similarly strong association with a broad range of crystallized abilities. Of the key moderators we investigated—text base, administration mode, deletion pattern, and response type—only the response type showed a significant effect. Sensitivity analyses supported the robustness of our findings. We conclude by revisiting the origin of the cloze test and highlighting the need for systematic studies on how different cloze test designs affect construct validity. Whereas the meta-analytic database predominantly originates from language research, where cloze tests are entrenched as markers of language proficiency, we propose reframing cloze tests as a versatile intelligence test format—just like multiple-choice tests constitute a testing method—that can be tailored to assess various specific cognitive abilities.

The History of the #CHC Theory of #Cognitive Abilities in #Indonesia

Click on images to enlarge

Approximately seven years ago I made a post regarding the launch of the AJT CHC-based intelligence test developed and normed in Indonesia. I was the primary CHC theory and applied psychometrics consultant for the project for four years (2014 to 2017).

Unfortunately the timing of the formal AJT launch was impacted by several unanticipated factors (e.g., the lack of a mature university-based psychological assessment and interpretation training infrastructure), the most salient being the world-wide COVID pandemic.  At that time the AJT folks put the project on “pause”. To date I’ve not heard if the project has since been restarted.

I decided to check on the impact of the CHC theory of cognitive abilities in Indonesia. It was my impression, based on multiple keynote university-based CHC/AJT presentations I made during the project plus feedback from the project staff, that despite the AJT pause, the project had a major impact regarding the infusion of the CHC theory in universities (psychology departments) and private testing entities. 

To satisfy my curiosity, I performed the following Google AI queries. Below is what I I found.  Professionally I feel very proud that the four-year AJT project resulted in the quick infusion of CHC theory in the academic and private sector discourse. All entities and staff who worked on the project should be proud of the CHC impact in Indonesia.

———————————

On 11-09-2025 I, Dr. Kevin McGrew, submitted the following prompt question, followed by a second follow-up question to a Google AI search (that uses the Gemini large language model) with the Firefox web browser (version 144.0.2, released on October 28, 2025).

 

“What is the history of the CHC theory of intelligence in Indonesia?

 

The history of the Cattell-Horn-Carroll (CHC) theory of intelligence in Indonesia is relatively recent, primarily involving efforts to develop and validate locally normed intelligence tests based on the CHC framework. The theory has been recognized as the "most comprehensive theory" for structuring cognitive abilities and has been used in academic research and test development. 

 

Key milestones in the history include:

• Early 2010s: The CHC theory started gaining attention in Indonesian academic and psychological circles, leading to research interest in applying the framework. The existing intelligence tests in Indonesia at the time were few and not necessarily based on contemporary, comprehensive models like CHC theory.
• 2013-2018: The AJT Cognitive Assessment Test (AJT-CAT) Project: The most significant development began around 2013, sponsored and directed by the Yayasan Dharma Bermakna Foundation (YDB).
• This project aimed to create the first comprehensive, individually administered intelligence test in Indonesia that was natively based on the CHC theory.
• Psychometric and CHC expert Dr. Kevin McGrew served as a consultant for this project.
• The test was nationally normed using a sample of over 4,000 Indonesian individuals aged 5-18.
• The formal launch of the AJT occurred in April 2018.
• Research and Further Test Development: Since the launch of the AJT, the CHC theory has continued to serve as a foundational framework for other, more specific test development efforts.
• Researchers have developed tests for specific abilities, such as a visual-spatial ability test for high school students and a lexical knowledge test, using the CHC theory as the underlying structural model.
• These studies emphasize the use of CHC theory to ensure tests are psychometrically sound and relevant for the Indonesian context, particularly for educational and clinical assessment purposes. 

The history of CHC theory in Indonesia is marked by a shift towards developing culturally relevant, psychometrically robust assessments grounded in contemporary, internationally recognized theories of intelligence, moving beyond older or imported models.

 

What psychologist is most associated with the CHC theory in Indonesia?

 

The psychologist most prominently associated with the application and development of the Cattell-Horn-Carroll (CHC) theory in Indonesia is the American psychometric expert Dr. Kevin McGrew.  Dr. McGrew served as the primary international consultant for the development of the AJT Cognitive Assessment Test (AJT-CAT), which was the first individually administered, CHC-theory-based intelligence test developed and nationally normed in Indonesia. This project was a major collaborative effort between 2013 and 2018 involving the Yayasan Dharma Bermakna Foundation (YDB) and the Faculty of Psychology at Universitas Gadjah Mada (UGM). 

 

While the CHC theory in Indonesia involves contributions from several Indonesian researchers and institutions, Dr. McGrew is the most widely recognized figure due to his direct supervision of this foundational project and his broader international reputation as a leading scholar and "gatekeeper" of the CHC theory.