Human-artificial interaction in the age of agentic AI: a system-theoretical approach
Open accessThe DOI matches its Crossref record; 49 of the 50 references it cites were found in a registry or an index.
Abstract
This paper presents a novel perspective on human-computer interaction (HCI), framing it as a dynamic interplay between human and computational agents within a networked system. Going beyond traditional interface-based approaches, we emphasize the importance of coordination and communication among heterogeneous agents with different capabilities, roles, and goals. The paper distinguishes between Multi-Agent Systems (MAS)—where agents maintain autonomy through structured cooperation—and Centaurian systems, which integrate human and AI capabilities for unified decision making. To formalize these interactions, we introduce a framework for communication spaces, structured into surface, observation, and computation layers, ensuring seamless integration between MAS and Centaurian architectures, where colored Petri nets effectively represent structured Centaurian systems and high-level reconfigurable networks address the dynamic nature of MAS. We recognize that elements such as task recommendation, feedback loops, and natural language interfaces are common in contemporary adaptive HCI. What distinguishes our framework is not the introduction of these elements per se , but the synthesis of architectural principles that systematically accommodate both autonomy-preserving and integration-seeking configurations within a shared formal foundation. Our research has practical applications in autonomous robotics, human-in-the-loop decision making, and AI-driven cognitive architectures, and provides a foundation for next-generation hybrid intelligence systems that balance structured coordination with emergent behavior.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As defined in recent frameworks, these systems are composed of modular agents each tasked with a distinct subcomponent of a broader goal and coordinated through either a centralized orchestrator or a decentralized protocol [24,145].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [145]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This emerging class of systems extends the capabilities of traditional AI Agents by enabling multiple intelligent entities to collaboratively pursue goals through structured communication [144-146], shared memory [147,148], and dynamic role assignment [22].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [145]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Adaptability: It encompasses ongoing interpersonal learning and agile feedback and tuned goals and measures via conceptual multi-agent models, formal policy operationalizations such as Petri Nets [154], and applied second burst benchmark measures that simulate unpredictable, complex, and dynamic environments [75].”
From The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges (2025) · cites this paper as [154]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As defined in recent frameworks, these systems are composed of modular agents each tasked with a distinct subcomponent of a broader goal and coordinated through either a centralized orchestrator or a decentralized protocol [23], [147].”
From AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025) · cites this paper as [147]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Agency AI Systems can remove ambiguity, enact user preferences [154], and derive next actions through self-reflection to generate signals [144].”
From The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges (2025) · cites this paper as [154]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Petri nets: Properties, analysis and applications
Murata, T. (1989) · Proceedings of the IEEE · doi:10.1109/5.24143 · Cited by 10,606 · cited 1×
“As transitions fire, tokens move among places, thus modeling the progress of a process or distributed computation [41].”
Autopoiesis and Cognition: The Realization of the Living
Maturana, H. R., & Varela, F. J. (1980) · Boston Studies in the Philosophy and History of Science · doi:10.1007/978-94-009-8947-4 · Cited by 5,815
An Introduction to MultiAgent Systems
Wooldridge, M. (2002) · Cited by 5,394
General System Theory: Foundations, Development, Applications.
Goldberg, A. I. (1969) · Archives of General Psychiatry · doi:10.1001/archpsyc.1969.01740200123021 · Cited by 2,550 · cited 1×
“These developments push beyond traditional HCI in two distinct directions that mirror fundamental patterns found in biological systems [6,7,39].”
Licklider, J. C. R. (1960) · IRE Transactions on Human Factors in Electronics · doi:10.1109/thfe2.1960.4503259 · Cited by 1,938 · cited 1×
“Theoretical foundations for such systems trace back to [37] and [23], but their practical feasibility has emerged only recently with generative AI systems capable of complementing human cognitive functions.”
Dorigo, M., Birattari, M., & Stutzle, T. (2006) · IEEE Computational Intelligence Magazine · doi:10.1109/ci-m.2006.248054 · Cited by 1,880 · cited 1×
“In the classical work by [22], a computational model was derived from how ants communicate information on trails to reach food sources by marking them through pheromones recognized by other ants.”
Alternating-time temporal logic
Alur, R., Henzinger, T. A., & Kupferman, O. (2002) · Journal of the ACM · doi:10.1145/585265.585270 · Cited by 1,394
AUGMENTING HUMAN INTELLECT: A CONCEPTUAL FRAMEWORK
ENGELBART, D. C. (1962) · doi:10.21236/ad0289565 · Cited by 1,082
A Survey of Distributed Consensus Protocols for Blockchain Networks
Xiao, Y., Zhang, N., Lou, W., & Hou, Y. T. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2969706 · Cited by 841
Cybernetics-or control and communication in the animal and the machine
Charp, S. (1949) · Journal of the Franklin Institute · doi:10.1016/0016-0032(49)90745-0 · Cited by 675
Translating Principles into Practices of Digital Ethics: Five Risks of Being Unethical
Floridi, L. (2019) · Philosophy & Technology · doi:10.1007/s13347-019-00354-x · Cited by 524
Kim, J., & Im, I. (2023) · Computers in Human Behavior · doi:10.1016/j.chb.2022.107512 · Cited by 220 · cited 1×
“[31] study the attribution of human characteristics to artificial intelligence.”
An Introduction to Population Protocols
Aspnes, J., & Ruppert, E. (2009) · Middleware for Network Eccentric and Mobile Applications · doi:10.1007/978-3-540-89707-1_5 · Cited by 208 · cited 1×
“Basic interaction protocols have been formalized for distributed computation [5], while more complex patterns have been developed for knowledge combination [4,11] and distributed problem-solving [10].”
Architectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural NetworksPreprint
Papillon, M., Sanborn, S., Hajij, M., & Miolane, N. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.10031 · Cited by 120 · cited 1×
“Message Passing Neural Networks (MPNNs) [45] are a special class of neural networks that use the aforementioned message-passing paradigm to capture interactions between entities (often represented as nodes in a graph).”
Human-machine symbiosis: A multivariate perspective for physically coupled human-machine systems
Inga, J., Rueß, M., Robens, J. H., Nelius, T., Rothfuß, S., Kille, S., Dahlinger, P., Lindenmann, A., Thomaschke, R., Neumann, G. M., et al. (2022) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2022.102926 · Cited by 103
Normative ethics, human rights, and artificial intelligence
Kumar, S., & Choudhury, S. (2022) · AI and Ethics · doi:10.1007/s43681-022-00170-8 · Cited by 88 · cited 1×
“For the latter, the reader is referred to [35,30] and [43].”
Bradshaw, J. M., Feltovich, P. J., & Johnson, M. (2017) · CRC Press eBooks · doi:10.1201/9781315557380-14 · Cited by 77 · cited 1×
“In biological systems, these are signaling pathways or neural networks; in human-machine systems, they manifest as protocols, interfaces, and shared representational spaces [14].”
How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering
Choudhuri, R., Liu, D., Steinmacher, I., Gerosa, M., & Sarma, A. (2024) · Proceedings of the IEEE/ACM 46th International Conference on Software Engineering · doi:10.1145/3597503.3639201 · Cited by 72 · cited 1×
“For example, [19] state that there were no statistical differences in participants’ productivity or self-efficacy when using ChatGPT compared to traditional resources.”
Spatio-temporal model checking of vehicular movement in public transport systems
Ciancia, V., Gilmore, S. T., Grilletti, G., Latella, D., Loreti, M., & Massink, M. (2018) · International Journal on Software Tools for Technology Transfer · doi:10.1007/s10009-018-0483-8 · Cited by 59 · cited 1×
“– Management of transportation networks requires maintaining complete information on the whereabouts of vehicles and the state of roads to be mapped on the topology of the transportation network (see [20] for a concrete example).”
A framework for neurosymbolic robot action planning using large language models
Capitanelli, A., & Mastrogiovanni, F. (2024) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2024.1342786 · Cited by 48 · cited 1×
“[16] demonstrate that LLMs can play an important role in planning actions in human-robot interactions.”
Classifying Model-View-Controller Software Applications Using Self-Organizing Maps
Guamán, D., Delgado, S., & Pérez, J. (2021) · IEEE Access · doi:10.1109/access.2021.3066348 · Cited by 47
Reasoning about Strategies: on the Satisfiability Problem
Mogavero, F., Murano, A., Perelli, G., & Vardi, M. Y. (2017) · Logical Methods in Computer Science · doi:10.23638/lmcs-13(1:9)2017 · Cited by 38 · cited 1×
“Reasoning on the possible evolutions of such systems leads to the definition of some variations of Alternating-Time Temporal Logic (see e.g., [3,2,40]).”
Knell, S., & Rüther, M. (2023) · AI and Ethics · doi:10.1007/s43681-023-00273-w · Cited by 32 · cited 1×
“Although beyond the scope of this paper, there exists a humanistic perspective [32], as well as an ethical dimension, to human-artificial interaction.”
Comparing Software Developers with ChatGPT: An Empirical Investigation
Nascimento, N., Alencar, P., & Cowan, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.11837 · Cited by 30 · cited 1×
“In the same domain, [42] evaluates ChatGPT-generated code against developer-generated code to determine which tasks are better suited for engineers and which are better handled by AI.”
Effective Generative AI: The Human-Algorithm CentaurPreprint
Saghafian, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4594780 · Cited by 30
Augmenting Cognition: Reviewing the Symbiotic Relation Between Man and Machine
de Greef, T., van Dongen, K., Grootjen, M., & Lindenberg, J. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-73216-7_51 · Cited by 27
Model-checking for Resource-Bounded ATL with production and consumption of resources
Alechina, N., Logan, B. S., Nguyen, H. N., & Raimondi, F. (2017) · Journal of Computer and System Sciences · doi:10.1016/j.jcss.2017.03.008 · Cited by 27 · cited 1×
“Reasoning on the possible evolutions of such systems leads to the definition of some variations of Alternating-Time Temporal Logic (see e.g., [3,2,40]).”
Humans, super humans, and super humanoids: debating Stephen Hawking’s doomsday AI forecast
Kumar, S., & Choudhury, S. (2022) · AI and Ethics · doi:10.1007/s43681-022-00213-0 · Cited by 25 · cited 1×
“In some ways, “virtual superhu-man” AI technologies could undermine the value of human achievements [51] or even may pose an existential threat [34].”
Beyond Human and Machine: An Architecture and Methodology Guideline for Centaurian Design
Pareschi, R. (2024) · Sci · doi:10.3390/sci6040071 · Cited by 23 · cited 4×
“When human abilities merge with artificial intelligence, the resulting configuration can evolve from traditional tool use ( Homo Faber ) to a more profound integration ( Centaurus Faber ) where each component may be instantiated by either human cognition or AI subsystems [46].”
InfluentialSelf-citationThe group mind of hybrid teams with humans and intelligent agents in knowledge-intense work
Hopf, K., Nahr, N., Staake, T., & Lehner, F. (2024) · Journal of Information Technology · doi:10.1177/02683962241296883 · Cited by 21 · cited 1×
“The result is a complex, interconnected ecosystem [27].”
Applying Algebraic Approaches for Modeling Workflows and their Transformations in Mobile Networks
Bottoni, P., Rosa, F. D., Hoffmann, K., & Mecella, M. (2006) · Mobile Information Systems · doi:10.1155/2006/704187 · Cited by 20 · cited 1×
“In [12], a formal model of the coordination mechanisms was given in terms of High-Level Petri nets.”
Self-citationHuman achievement and artificial intelligence
Karlan, B. (2023) · Ethics and Information Technology · doi:10.1007/s10676-023-09713-x · Cited by 20 · cited 1×
“For the latter, the reader is referred to [35,30] and [43].”
Ahmadi, N., & Hammond, T. (2023) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie58773.2023.10343328 · Cited by 19 · cited 1×
“For a survey of Artificial Emotional Intelligence (AEI) for cooperative social human-machine interactions see [1].”
Caci, B., & Dhou, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60128-7_45 · Cited by 17
Outperformed by AI: Interacting with Superhuman AI Changes the Way We Perceive Ourselves
Schaap, G., van de Sande, Y., & Schraffenberger, H. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3650961 · Cited by 17 · cited 1×
“In some ways, “virtual superhu-man” AI technologies could undermine the value of human achievements [51] or even may pose an existential threat [34].”
Constraint-based protocols for distributed problem solving
Borghoff, U. M., Pareschi, R., Fontana, F. A., & Formato, F. R. (1998) · Science of Computer Programming · doi:10.1016/s0167-6423(97)00011-7 · Cited by 13 · cited 1×
“Basic interaction protocols have been formalized for distributed computation [5], while more complex patterns have been developed for knowledge combination [4,11] and distributed problem-solving [10].”
Self-citationParallel Symbolic Computation PASCO '94
Hong, H. (1994) · doi:10.1142/9789814533584 · Cited by 9 · cited 1×
“Basic interaction protocols have been formalized for distributed computation [5], while more complex patterns have been developed for knowledge combination [4,11] and distributed problem-solving [10].”
Reflections on emerging HCI–AI research
Panda, S., & Roy, S. T. (2022) · AI & Society · doi:10.1007/s00146-022-01409-y · Cited by 7 · cited 1×
“With the ubiquity of AI applications, HCI research is increasingly integrating these approaches, demonstrating that AI and HCI are mutually beneficial when they collaborate [44].”
Integrating Blockchain for Enhanced Coordination and Security in Semi-Centralized Robotic Swarms
Carovilla, A., Pareschi, R., & Salzano, F. (2023) · IEEE International Workshop on Technologies for Defense and Security (TechDefense) · doi:10.1109/techdefense59795.2023.10380842 · Cited by 7 · cited 2×
“To enhance coordination and security in swarm robotic systems, [17] introduce a semi-centralized framework that integrates blockchain technology, featuring a centralized control unit that coordinates the swarm, while blockchain technology ensures secure and decentralized data storage and…”
Self-citationXiaochun, C. (2024) · Entertainment Computing · doi:10.1016/j.entcom.2024.100761 · Cited by 7 · cited 1×
“Also in the IoT context, with a focus on the gaming/sports arena, [18] sees potential for enter-tainment robots to recognize human posture through artificial intelligence.”
On Combining the Knowledge of Heterogeneous Information Repositories
Schlichter, J. H., & Borghoff, U. M. (2020) · TUGraz OPEN Library (Graz University of Technology) · doi:10.3217/jucs-002-07-0515 · Cited by 5 · cited 1×
“Basic interaction protocols have been formalized for distributed computation [5], while more complex patterns have been developed for knowledge combination [4,11] and distributed problem-solving [10].”
Self-citationUnveiling Human-AI Interaction and Subjective Perceptions About Artificial Intelligent Agents
Giudici, M., Liguori, F., Tocchetti, A., & Brambilla, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-62362-2_36 · Cited by 4 · cited 1×
“[24] present and evaluate a method for analyzing user reactions to AI using a live-streaming platform where human streamers conduct interviews that are transmitted to a specially developed GPT voice interface using a crowd-based approach.”
Borghoff, U. M., Minas, M., & Mönch, K. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-81596-6_4 · Cited by 4 · cited 1×
“[9] explore human-artificial interaction with generative AIs in a software engineering project course.”
Self-citationA System-Theoretical Multi-agent Approach to Human-Computer Interaction
Borghoff, U. M., Bottoni, P., & Pareschi, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82949-9_3 · Cited by 4 · cited 1×
“Communication spaces group interactions into three conceptual layers [8]: surface , observation , and computation .”
Self-citationNieto, B. F. (2024) · International Conference on Evaluation and Assessment in Software Engineering (EASE) · doi:10.1145/3661167.3661177 · Cited by 3 · cited 1×
“For the latter, the reader is referred to [35,30] and [43].”
Dobrean, D., & Dioşan, L. S. (2022) · Soft Computing · doi:10.1007/s00500-022-06908-0 · Cited by 2 · cited 1×
“To ensure the correct implementation of an MVC pattern, [21] pro-pose an automated technique that analyzes and detects architectural issues us-ing data from Software Development Kits (SDKs) specifically targeted at mobile code bases.”
Strategies in Spatio-Temporal Logics for Multi-agent Systems
Bottoni, P., Labella, A., & Perelli, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73709-1_18 · Cited by 2 · cited 1×
“In contrast, a logic that incorporates spatial constraints on a par with temporal ones has been recently proposed by [13].”
Self-citationKumar, M., & Choppella, V. (2023) · ACM Global Computing Education Conference (CompEd) · doi:10.1145/3617650.3624934 · Cited by 2 · cited 1×
“[33] take the opposite approach, extending pattern descriptions with a System of Systems (SoS) model to apply interactive dynamics to an MVC pattern.”
Interdependence and Vulnerability in Systems: A Review of Theory for Autonomous Human-Machine Teams
Lawless, W. F., & Sofge, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89385-9_15 · Cited by 1 · cited 1×
“[36] use interdependence theory to determine whether convergence has a positive or negative effect in a competition between human and artificial agents, as in system dynamics models.”
Research works printed but not linked: 8
- Borghoff, 1995, “Multi-agent coordination in living systems,”, Proceedings of the 1995 International Workshop on Biologically Inspired Evolutionary Systems, BIES 1995, Sony Corporation Conference Hall, Tokyo, Japan, May 30–31, 93
- Borghoff, 2025, Human-artificial interaction in the age of agentic AI: a system-theoretical approach, arXiv Preprint, arXiv:2502.14000, 10.48550/arXiv.2502.14000 · arXiv · doi:10.48550/arxiv.2502.14000
- Jensen, 1995, Coloured Petri Nets: Basic Concepts, Analysis Methods and Practical Use, Volume 2 of Monographs in Theoretical Computer Science
- Miller, 1978, Living Systems
- Riliskis, 2015, “Ravel: programming iot applications as distributed models, views, and controllers,”, 1
- Salzano, 2023, “Blockchain-based information ecosystems,”, Proceedings of the Fifth Distributed Ledger Technology Workshop (DLT 2023), Bologna, Italy, May 25–26, volume 3460 of CEUR Workshop Proceedings
- Simon, 1996, The Sciences of the Artificial
- Weiss, 2013, Multiagent Systems
Cited by
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · arXiv · doi:10.48550/arxiv.2505.10468 · Cited by 295
“As defined in recent frameworks, these systems are composed of modular agents each tasked with a distinct subcomponent of a broader goal and coordinated through either a centralized orchestrator or a decentralized protocol [24,145].”
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 671
“As defined in recent frameworks, these systems are composed of modular agents each tasked with a distinct subcomponent of a broader goal and coordinated through either a centralized orchestrator or a decentralized protocol [24,145].”
Agentic AI: a comprehensive survey of architectures, applications, and future directions
Abou Ali, M., Dornaika, F., & Charafeddine, J. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11422-4 · Cited by 165
“Trust & Transparency [142, 144] "How" decisions are made is transparent (the logic trace), but "why" a specific rule exists can be opaque.”
Bandi, A., Kongari, B., Naguru, R., Pasnoor, S., & Vilipala, S. V. (2025) · Future Internet · doi:10.3390/fi17090404 · Cited by 207
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186
Metadata
- Authors
- Borghoff, U. M., Bottoni, P., & Pareschi, R.
- Affiliations
- Universität der Bundeswehr München (DE)
- Sapienza University of Rome (IT)
- University of Molise (IT)
- Corresponding author
- Borghoff, Uwe M.
- Venue
- Frontiers in Human Dynamics
- Publisher
- Frontiers Media SA
- Published
- 2025-05-09
- Volume
- 7
- ISSN
- 2673-2726 (ISSN-L)
- OpenAlex
- W4410244386
- Cited by
- 89
- References
- 50
- Citations by year
- 2026: 67 · 2025: 22
- FWCI
- 35.29
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Human Dynamics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Archivio Istituzionale della Ricerca - Università degli Studi del Molise (submittedVersion)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Social Sciences › Business, Management and Accounting › Management Information Systems › Information Systems Theories and Implementation
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Keywords
- human-AI interaction, agentic AI, multi-agent systems, human-computer interaction, agent coordination, agent communication, communicative space, colored Petri nets, reconfigurable networks, human autonomy, hybrid intelligence, human-in-the-loop decision making, autonomous robotics, cognitive architecture
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.