Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances

Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances Matteo Da Pelo, Alessio Donvito, Claudio Frongia, Pietro Salis, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9575224/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract We introduce a framework called LAPITHS (Language-model Analysis through Paradigm-grounded Interpretations of Theses about Human-likenesS) and use it to show that several major claims advanced by models such as CENTAUR— proposed as an artificial Unified Model of Cognition—are not theoretically or empirically justified. LAPITHS provides a principled reference point for counteracting the current behaviouristic tendency in AI research to interpret the human-level performances of transformer-based language models as evidence of human-like underlying computation and, by extension, as signs of cognitive abilities. The novelty of LAPITHS lies in making explicit the arguments grounded in two quantitative assessments: (i) the Minimal Cognitive Grid, a theoretically motivated method for estimating the cognitive plausibility of artificial systems, and (ii) a behavioural comparison showing that results similar to those reported for CENTAUR-like models can be reproduced by other systems that do not satisfy the structural constraints typically associated with cognitive plausibility, and whose outputs do not provide independent explanatory insight into human cognition. Artificial Intelligence and Machine Learning Computational Cognitive Science Cognitive Modeling Artificial Intelligence Cognitive Plausibility Unified Theory of Cognition Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9575224","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":632344916,"identity":"66ab1941-b022-4a70-8a00-7e6a8d6194ec","order_by":0,"name":"Matteo Da Pelo","email":"","orcid":"https://orcid.org/0009-0006-5875-726X","institution":"University of Cagliari","correspondingAuthor":false,"prefix":"","firstName":"Matteo","middleName":"Da","lastName":"Pelo","suffix":""},{"id":632344917,"identity":"49c17474-9fd9-49e9-9ce8-f4ca08220393","order_by":1,"name":"Alessio Donvito","email":"","orcid":"https://orcid.org/0009-0007-7546-0342","institution":"University of Bari","correspondingAuthor":false,"prefix":"","firstName":"Alessio","middleName":"","lastName":"Donvito","suffix":""},{"id":632344918,"identity":"5e39bfa9-5d56-419c-b8c1-9a4c965e7f27","order_by":2,"name":"Claudio Frongia","email":"","orcid":"https://orcid.org/0009-0005-4305-2278","institution":"University of Cagliari","correspondingAuthor":false,"prefix":"","firstName":"Claudio","middleName":"","lastName":"Frongia","suffix":""},{"id":632344919,"identity":"f91142c5-c51c-4614-ba30-2355aa5fcb09","order_by":3,"name":"Pietro Salis","email":"","orcid":"https://orcid.org/0000-0001-6973-1440","institution":"University of Cagliari","correspondingAuthor":false,"prefix":"","firstName":"Pietro","middleName":"","lastName":"Salis","suffix":""},{"id":632344920,"identity":"a9c336b9-95d2-4225-80f4-9500c0184ac5","order_by":4,"name":"Antonio Lieto","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYDACdsYGIGnDwMAM4hkQo4UZqOUAQxpMCzF6QCoPMByGcYnQwt/M3Pj4Q8X5xO3s7A8/MBT8IaxF4jBjs8GBM7cTdzbzGEsQ57DDjG0SB9tuJ244zMNAnBb5w4ztPw62nQNqYX/8gygtBkBbGA62HQBqYTAjzhZDoF8kzpxJNgY6zMwiwcCYsBa54+0PP1RU2MluOH/88Y0Pf+QIa0EFCaRqGAWjYBSMglGAHQAAYQM5ZUoy+pcAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-8323-8764","institution":"University of Salerno","correspondingAuthor":true,"prefix":"","firstName":"Antonio","middleName":"","lastName":"Lieto","suffix":""}],"badges":[],"createdAt":"2026-04-30 09:49:12","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9575224/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9575224/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108804003,"identity":"329ecd83-d1ba-4421-9e24-27cfe4fa8058","added_by":"auto","created_at":"2026-05-08 15:14:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":515429,"visible":true,"origin":"","legend":"","description":"","filename":"MMTamingtheCentaurswithLAPITHSaframeworkforatheoreticallygroundedinterpretationofAIperformances.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9575224/v1_covered_1d4e767a-2270-455f-9aa4-d64cb9e62788.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eTaming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Salerno","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Computational Cognitive Science, Cognitive Modeling, Artificial Intelligence, Cognitive Plausibility, Unified Theory of Cognition","lastPublishedDoi":"10.21203/rs.3.rs-9575224/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9575224/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cem\u003eWe introduce a framework called LAPITHS (Language-model Analysis through Paradigm-grounded Interpretations of Theses about Human-likenesS) and use it to show that several major claims advanced by models such as CENTAUR— proposed as an artificial Unified Model of Cognition—are not theoretically or empirically justified. LAPITHS provides a principled reference point for counteracting the current behaviouristic tendency in AI research to interpret the human-level performances of transformer-based language models as evidence of human-like underlying computation and, by extension, as signs of cognitive abilities. The novelty of LAPITHS lies in making explicit the arguments grounded in two quantitative assessments: (i) the Minimal Cognitive Grid, a theoretically motivated method for estimating the cognitive plausibility of artificial systems, and (ii) a behavioural comparison showing that results similar to those reported for CENTAUR-like models can be reproduced by other systems that do not satisfy the structural constraints typically associated with cognitive plausibility, and whose outputs do not provide independent explanatory insight into human cognition.\u003c/em\u003e\u003c/p\u003e","manuscriptTitle":"Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-04 09:44:30","doi":"10.21203/rs.3.rs-9575224/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1bc34965-74e0-419a-9169-e1525372f08f","owner":[],"postedDate":"May 4th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":67307995,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-05-04T09:44:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-04 09:44:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9575224","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9575224","identity":"rs-9575224","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}