Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?
Open accessThe DOI matches its Crossref record; 26 of the 27 references it cites were found in a registry or an index.
Abstract
Language models trained on billions of tokens have recently led to unprecedented results on many NLP tasks. This success raises the question of whether, in principle, a system can ever “understand” raw text without access to some form of grounding. We formally investigate the abilities of ungrounded systems to acquire meaning. Our analysis focuses on the role of “assertions”: textual contexts that provide indirect clues about the underlying semantics. We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence. We find that assertions enable semantic emulation of languages that satisfy a strong notion of semantic transparency. However, for classes of languages where the same expression can take different values in different contexts, we show that emulation can become uncomputable. Finally, we discuss differences between our formal model and natural language, exploring how our results generalize to a modal setting and other semantic relations. Together, our results suggest that assertions in code or language do not provide sufficient signal to fully emulate semantic representations. We formalize ways in which ungrounded language models appear to be fundamentally limited in their ability to “understand”.
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
“[85] propose a proof that no isomorphism can exist between an ungrounded LM and a formal semantic representation of meaning.”
From Symbols and grounding in large language models (2023) · cites this paper as [85]
Experimental — accuracy not yet measured
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 1×
“Recently, language models trained on huge datasets of raw text have pushed the limits of natural language processing (Devlin et al., 2019; Raffel et al., 2019; Brown et al., 2020, among others).”
BackgroundLanguage Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Grice, H. P. (1975) · Speech Acts · doi:10.1163/9789004368811_003 · Cited by 23,221 · cited 1×
“Indeed, this is one of Grice’s Maxims (Grice, 1975): a set of basic principles proposed to govern the pragmatics of natu-ral language.”
BackgroundExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 1×
“Recently, language models trained on huge datasets of raw text have pushed the limits of natural language processing (Devlin et al., 2019; Raffel et al., 2019; Brown et al., 2020, among others).”
BackgroundI.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290 · cited 1×
“Turing (1950) constitutes an early behaviorist perspective; more recent approaches tend to emphasize not just an ex-ternal view of a system’s behavior, but also “how it is achieved” (Levesque, 2014).”
BackgroundOn computable numbers, with an application to the entscheidungsproblem
Turing, A. M. (1937) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s2-42.1.230 · Cited by 8,283
Computing Machinery and Intelligence (1950)
Turing, A. (2004) · The Essential Turing · doi:10.1093/oso/9780198250791.003.0017 · Cited by 6,118
Harris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222 · cited 1×
“Understanding can be behaviorally diagnosed in neural models by evaluating them on benchmarks (Wang et al., 2018).”
BackgroundLearning regular sets from queries and counterexamples
Angluin, D. (1987) · Information and Computation · doi:10.1016/0890-5401(87)90052-6 · Cited by 2,114
Research works printed but not linked: 5
- Noam Chomsky. 1965. Aspects of the Theory of Syntax , volume 11. MIT press.
- Laurence R. Horn and Heinrich Wansing. 2020. Negation. In Edward N. Zalta, editor, The Stanford Encyclopedia of Philosophy , spring 2020 edition. Metaphysics Research Lab, Stanford University.
- Ian Pratt-Hartmann and Allan Third. 2006. More fragments of language. Notre Dame J. Formal Logic , 47(2):151-177. · DOI
- Kai Von Fintel and Irene Heim. 2011. Intensional semantics. Unpublished Lecture Notes .
- Alfred North Whitehead and Bertrand Russell. 1925-1927. Principia Mathematica . Cambridge University Press.
Cited by
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Text Data Augmentation for Deep Learning
Shorten, C., Khoshgoftaar, T. M., & Furht, B. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00492-0 · Cited by 1,740
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
West, P., Bhagavatula, C., Hessel, J., Hwang, J., Jiang, L., Le Bras, R., Lu, X., Welleck, S., & Choi, Y. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.341 · Cited by 156
“Prior works have suggested that pre-trained language models possess limited understanding of commonsense knowledge (Merrill et al., 2021; Talmor et al., 2021; Davis and Marcus, 2017) despite (1)We will share this following the anonymity period.”
BackgroundSymbols and grounding in large language models
Pavlick, E. (2023) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2022.0041 · Cited by 95
“[85] propose a proof that no isomorphism can exist between an ungrounded LM and a formal semantic representation of meaning.”
BackgroundDoes ChatGPT have semantic understanding? A problem with the statistics-of-occurrence strategy
Titus, L. M. (2024) · Cognitive Systems Research · doi:10.1016/j.cogsys.2023.101174 · Cited by 82
Synchromesh: Reliable code generation from pre-trained language models
Poesia, G., Polozov, O., Le, V., Tiwari, A., Soares, G., Meek, C., & Gulwani, S. (2022) · arXiv · doi:10.48550/arxiv.2201.11227 · Cited by 72
“This is in line with theoretical results in Merrill et al. (2021) showing that programming language semantics cannot be fully inferred from ungrounded data.”
ResultContrastive language and vision learning of general fashion concepts
Chia, P. J., Attanasio, G., Bianchi, F., Terragni, S., Magalhães, A. R., Goncalves, D., Greco, C., & Tagliabue, J. (2022) · Scientific Reports · doi:10.1038/s41598-022-23052-9 · Cited by 130
“Finally, the literature on compositionality spans centuries: limiting ourselves only to recent work, grounding has been explored in connection with ef-ficient learning (Yu et al., 2018; Chevalier-Boisvert et al., 2019), and “true understanding” (Bender and Koller, 2020; Merrill et al., 2021).”
BackgroundCan Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Abdou, M., Kulmizev, A., Hershcovich, D., Frank, S., Pavlick, E., & Søgaard, A. (2021) · arXiv · doi:10.48550/arxiv.2109.06129 · Cited by 70
“The first two evaluate the effect of a color term occurring more or less often as an adjectival modifier, while the latter tests the hypothesis that assertions such as The banana is yellow could provide indirect grounding (Merrill et al., 2021), thereby leading to higher alignment.”
BackgroundCan Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Abdou, M., Kulmizev, A., Hershcovich, D., Frank, S., Pavlick, E., & Søgaard, A. (2021) · Proceedings of the 25th Conference on Computational Natural Language Learning · doi:10.18653/v1/2021.conll-1.9 · Cited by 64
“The first two evaluate the effect of a color term occurring more or less often as an adjectival modifier, while the latter tests the hypothesis that assertions such as The banana is yellow could provide indirect grounding (Merrill et al., 2021), thereby leading to higher alignment.”
BackgroundEmergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Li, K., Hopkins, A. K., Bau, D., Viégas, F., Pfister, H., & Wattenberg, M. (2022) · arXiv · doi:10.48550/arxiv.2210.13382 · Cited by 61
Schetinger, V., Bartolomeo, S. D., El‐Assady, M., McNutt, A. M., Miller, M., Passos, J. P. A., & Adams, J. L. (2023) · Computer Graphics Forum · doi:10.1111/cgf.14841 · Cited by 83
The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail
Bowman, S. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.516 · Cited by 44
LMMS reloaded: Transformer-based sense embeddings for disambiguation and beyond
Loureiro, D., Jorge, A., & Camacho-Collados, J. (2022) · Artificial Intelligence · doi:10.1016/j.artint.2022.103661 · Cited by 43
“Effectively, there are known limitations to meaning representation based on language modelling objectives alone (Bender & Koller, 2020; Merrill et al., 2021).”
BackgroundAND does not mean OR: Using Formal Languages to Study Language Models’ Representations
Traylor, A., Feiman, R., & Pavlick, E. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) · doi:10.18653/v1/2021.acl-short.21 · Cited by 19
“Our evaluation method– which asks whether word embeddings cluster according to their truth-conditional meaning– is related to recent work which defines text-only models as “grounded” if the learned embedding space is isomorphic to the similarity function defined over a ground-truth meaning representation (Merrill et a…”
BackgroundMethodOn the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations
Schwartz, R., & Stanovsky, G. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.168 · Cited by 35
Self-citationWhat Do NLP Researchers Believe? Results of the NLP Community Metasurvey
Michael, J., Holtzman, A., Parrish, A., Mueller, A., Wang, A., Chen, A., Madaan, D., Nangia, N., Pang, R. Y., Phang, J., et al. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.903 · Cited by 65
Schuster, S., & Linzen, T. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.71 · Cited by 15
AI to Train AI: Using ChatGPT to Improve the Accuracy of a Therapeutic Dialogue System
Gabor-Siatkowska, K., Sowański, M., Rzatkiewicz, R., Stefaniak, I., Kozłowski, M., & Janicki, A. (2023) · Electronics · doi:10.3390/electronics12224694 · Cited by 20
KILM: Knowledge Injection into Encoder-Decoder Language Models
Xu, Y., Namazifar, M., Hazarika, D., Padmakumar, A., Liu, Y., & Hakkani-Tür, D. Z. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.275 · Cited by 37
Unit Testing for Concepts in Neural Networks
Lovering, C., & Pavlick, E. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00514 · Cited by 12
“…mappings between humans’ and neural networks’ conceptual spaces, e.g., by defining measures of compositionality or groundedness based on how well similarity in vector space reflects similarity according to a symbolic representation (Andreas, 2019; Chrupała and Alishahi, 2019; Merrill et al., 2021).”
BackgroundEmergent language: a survey and taxonomy
Peters, J., de Puiseau, C. W., Tercan, H., Gopikrishnan, A., de Carvalho, G. A. L., Bitter, C., & Meisen, T. (2025) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-025-09691-y · Cited by 37
Entity Tracking in Language Models
Kim, N., & Schuster, S. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.213 · Cited by 159
Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling
Prange, J., Schneider, N., & Kong, L. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.325 · Cited by 18
“14See also Merrill et al. (2021) for formal proofs.”
BackgroundTransparency Helps Reveal When Language Models Learn Meaning
Wu, Z., Merrill, W., Peng, H. M., Beltagy, I., & Smith, N. A. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00565 · Cited by 19
“3 2.4 ℵ -emulation: Learning Meaning Merrill et al. (2021) say that a class of languages L is ℵ -emulatable if, intuitively, a learner µ L with ℵ L -access produces context-independent representations that allow another function δ to check the equivalence of any two expressions under any context without further ℵ L -a…”
BackgroundMethodInfluentialSelf-citationEntailment Semantics Can Be Extracted from an Ideal Language Model
Merrill, W., Warstadt, A., & Linzen, T. (2022) · Conference on Computational Natural Language Learning · doi:10.18653/v1/2022.conll-1.13 · Cited by 16
Self-citationT5QL: Taming language models for SQL generation
Arcadinho, S., Aparício, D., Veiga, H., & Alegria, A. (2022) · Workshop on Generation, Evaluation and Metrics (GEM) · doi:10.18653/v1/2022.gem-1.23 · Cited by 14
What Do Language Models Hear? Probing for Auditory Representations in Language Models
Ngo, J., & Kim, Y. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.297 · Cited by 5
Loconte, R., Orrù, G., Tribastone, M., Pietrini, P., & Sartori, G. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e38911 · Cited by 17
Israeli, A., Kremiansky, A., & Tsur, O. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3512238 · Cited by 4
“This result demonstrates the often overlooked limitations of neural networks and language models [54].”
BackgroundEMBEDD-ER: EMBEDDing Educational Resources Using Linked Open Data
Bazouzi, A., Foursov, M., Capitaine, H. L., & Miklós, Z. (2023) · International Conference on Computer Supported Education · doi:10.5220/0012045300003470 · Cited by 5
Porada, I., Sordoni, A., & Cheung, J. C. K. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.337 · Cited by 11
“To evaluate relative performance, we also generate a control entity (CE) for each example by randomly sampling a WordNet sibling of the superstatement hypernym as a pseudo-negative (e.g., “A robin is a .””
MethodCommonsense Knowledge Transfer for Pre-trained Language Models
Zhou, W., Bras, R. J. L., & Choi, Y. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.368 · Cited by 12
What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured
Henlein, A., & Mehler, A. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.425 · Cited by 8
Pace-Sigge, M. T. (2025) · Journal of Corpora and Discourse Studies · doi:10.18573/jcads.129 · Cited by 2
“(Merrill et al., 2021, p. 1055) Therefore, as a task is relatively straight-forward and is combined with prompts which are sufficiently unambiguous, an LLM will produce a passable representation of a coherent text.”
Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models
Li, R., Murray, G., & Carenini, G. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.634 · Cited by 8
Natural Language Processing RELIES on Linguistics
Opitz, J., Wein, S., & Schneider, N. (2025) · Computational Linguistics · doi:10.1162/coli_a_00560 · Cited by 10
“…about how to interpret what NLP models are capable of representing—like how to define machine ‘understanding’ (Dunietz et al., 2020; Ray Choudhury et al., 2022) and whether grounding is required for a model to capture meaning (e.g., Bender and Koller, 2020; Merrill et al., 2021; Pavlick, 2023).”
Language Models Understand Us, Poorly
Moore, J. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.16 · Cited by 6
Learning to translate by learning to communicate
Downey, C. M., Zhou, X., Liu, Z., & Steinert‐Threlkeld, S. (2023) · Workshop on Multilingual Representation Learning (MRL) · doi:10.18653/v1/2023.mrl-1.17 · Cited by 7
On Degrees of Freedom in Defining and Testing Natural Language Understanding
Sugawara, S., & Tsugita, S. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.861 · Cited by 3
Toward context-based text-to-3D scene generation
Henlein, A. (2022) · Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt) · doi:10.21248/gups.73448 · Cited by 1
Zaawansowane procedury NLP jako przesłanka rekonstrukcji idei wiedzy
Maciąg, R. (2022) · Zarządzanie w Kulturze · doi:10.4467/20843976zk.22.003.15869 · Cited by 2
“Takie procedury, bardzo liczne i wyrafinowane, muszą mieć istotny wpływ na formowanie się ostatecznej struktury semantycznej (Helwe et al. 2021; Kozlowski et al. 2019; Merrill et al. 2021; Qiu, Xu 2022; Traylor et al. 2021; Yoshida, Oseki 2022).”
BackgroundPrange, J., & Chersoni, E. (2023) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2023.starsem-1.40 · Cited by 1
Do Language Models Know Who Did What to Whom?
Denning, J. M., Guo, X., Snefjella, B., & Blank, I. (2026) · Open Mind · doi:10.1162/opmi.a.365 · Cited by 4
“Some critics claim that LLMs do not have “grounded” knowledge that links linguistic meaning to non-linguistic experience (Bender and Koller, 2020; Bisk et al., 2020; Merrill et al., 2021); others claim that LLMs lack common sense, i.e., intuitive theories about how the world works (Sinha et al., 2019; Ullman, 2023); y…”
InfluentialProbing Emergent World Representations in Go Life-and-Death Problems
Yang, Z., Meng, Z., & Wen, Z. (2026) · AI · doi:10.3390/ai7050170
“LLMs trained on next-token prediction tasks [13] have demonstrated surprising abilities to solve problems far beyond their training data, including logical reasoning, symbolic manipulation, and strategic planning [14].”
Khairova, N., Redozub, I., Dignum, V., & Rizun, N. (2026) · Social Sciences · doi:10.3390/socsci15060341
Evelo, B., Fowlie, M., & Paperno, D. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.742
“When discussing how sense vs. reference relate to LLMs, some authors (Merrill et al., 2021; Allen, 2024) theorize about LLMs learning or implementing extensional vs intensional models from text, while other (Bouyamourn, 2023) connect intension-ality to paraphrasing, a task which LLMs excel at since…”
Lan, Z., & Yang, J. (2026) · IEEE Access · doi:10.1109/access.2026.3740087 · Cited by 1
“Merrill et al. [13] formalize a similar limitation by showing that textual signals can emulate aspects of semantic structure without guaranteeing full semantic recovery.”
Metadata
- Authors
- Merrill, W., Goldberg, Y., Schwartz, R., & Smith, N. A.
- Affiliations
- Allen Institute for Artificial Intelligence (US)
- Bar-Ilan University (IL)
- University of Washington (US)
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2021
- Volume
- 9
- Pages
- 1047-1060
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3156509887
- Semantic Scholar
- 2bb1e1a5b9a16f6828fe94736cea5dab264533a6
- Cited by
- 44
- References
- 27
- Citations by year
- 2026: 6 · 2025: 3 · 2024: 1 · 2023: 14 · 2022: 16 · 2021: 4
- FWCI
- 34.56
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- Allen Institute for Artificial Intelligence
- Topics
- Social Sciences › Arts and Humanities › Language and Linguistics › Syntax, Semantics, Linguistic Variation
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- meaning acquisition, assertion, semantic transparency, uncomputability, semantic relations, equivalence, modal logic, formal semantics, language comprehension
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.