Beyond Words: A Mathematical Framework for Interpreting Large Language Models Article Swipe
Javier González
,
Aditya V. Nori
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2311.03033
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2311.03033
Large language models (LLMs) are powerful AI tools that can generate and comprehend natural language text and other complex information. However, the field lacks a mathematical framework to systematically describe, compare and improve LLMs. We propose Hex a framework that clarifies key terms and concepts in LLM research, such as hallucinations, alignment, self-verification and chain-of-thought reasoning. The Hex framework offers a precise and consistent way to characterize LLMs, identify their strengths and weaknesses, and integrate new findings. Using Hex, we differentiate chain-of-thought reasoning from chain-of-thought prompting and establish the conditions under which they are equivalent. This distinction clarifies the basic assumptions behind chain-of-thought prompting and its implications for methods that use it, such as self-verification and prompt programming. Our goal is to provide a formal framework for LLMs that can help both researchers and practitioners explore new possibilities for generative AI. We do not claim to have a definitive solution, but rather a tool for opening up new research avenues. We argue that our formal definitions and results are crucial for advancing the discussion on how to build generative AI systems that are safe, reliable, fair and robust, especially in domains like healthcare and software engineering.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2311.03033
- https://arxiv.org/pdf/2311.03033
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4388481981
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4388481981Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2311.03033Digital Object Identifier
- Title
-
Beyond Words: A Mathematical Framework for Interpreting Large Language ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-11-06Full publication date if available
- Authors
-
Javier González, Aditya V. NoriList of authors in order
- Landing page
-
https://arxiv.org/abs/2311.03033Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2311.03033Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2311.03033Direct OA link when available
- Concepts
-
Generative grammar, Computer science, Field (mathematics), Management science, Key (lock), Strengths and weaknesses, Cognitive science, Artificial intelligence, Data science, Epistemology, Psychology, Engineering, Mathematics, Computer security, Philosophy, Pure mathematicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4388481981 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2311.03033 |
| ids.doi | https://doi.org/10.48550/arxiv.2311.03033 |
| ids.openalex | https://openalex.org/W4388481981 |
| fwci | |
| type | preprint |
| title | Beyond Words: A Mathematical Framework for Interpreting Large Language Models |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9779000282287598 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T12026 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9573000073432922 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Explainable Artificial Intelligence (XAI) |
| topics[2].id | https://openalex.org/T11636 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9394999742507935 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2718 |
| topics[2].subfield.display_name | Health Informatics |
| topics[2].display_name | Artificial Intelligence in Healthcare and Education |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C39890363 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7038522958755493 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q36108 |
| concepts[0].display_name | Generative grammar |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6211991906166077 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C9652623 |
| concepts[2].level | 2 |
| concepts[2].score | 0.4608333706855774 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q190109 |
| concepts[2].display_name | Field (mathematics) |
| concepts[3].id | https://openalex.org/C539667460 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4486595690250397 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2414942 |
| concepts[3].display_name | Management science |
| concepts[4].id | https://openalex.org/C26517878 |
| concepts[4].level | 2 |
| concepts[4].score | 0.44605544209480286 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q228039 |
| concepts[4].display_name | Key (lock) |
| concepts[5].id | https://openalex.org/C63882131 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4351918399333954 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q17122954 |
| concepts[5].display_name | Strengths and weaknesses |
| concepts[6].id | https://openalex.org/C188147891 |
| concepts[6].level | 1 |
| concepts[6].score | 0.4283912777900696 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q147638 |
| concepts[6].display_name | Cognitive science |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4078121483325958 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C2522767166 |
| concepts[8].level | 1 |
| concepts[8].score | 0.3764082193374634 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2374463 |
| concepts[8].display_name | Data science |
| concepts[9].id | https://openalex.org/C111472728 |
| concepts[9].level | 1 |
| concepts[9].score | 0.24917203187942505 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[9].display_name | Epistemology |
| concepts[10].id | https://openalex.org/C15744967 |
| concepts[10].level | 0 |
| concepts[10].score | 0.16955366730690002 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[10].display_name | Psychology |
| concepts[11].id | https://openalex.org/C127413603 |
| concepts[11].level | 0 |
| concepts[11].score | 0.1004084050655365 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[11].display_name | Engineering |
| concepts[12].id | https://openalex.org/C33923547 |
| concepts[12].level | 0 |
| concepts[12].score | 0.08265271782875061 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[12].display_name | Mathematics |
| concepts[13].id | https://openalex.org/C38652104 |
| concepts[13].level | 1 |
| concepts[13].score | 0.07603588700294495 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[13].display_name | Computer security |
| concepts[14].id | https://openalex.org/C138885662 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[14].display_name | Philosophy |
| concepts[15].id | https://openalex.org/C202444582 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q837863 |
| concepts[15].display_name | Pure mathematics |
| keywords[0].id | https://openalex.org/keywords/generative-grammar |
| keywords[0].score | 0.7038522958755493 |
| keywords[0].display_name | Generative grammar |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6211991906166077 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/field |
| keywords[2].score | 0.4608333706855774 |
| keywords[2].display_name | Field (mathematics) |
| keywords[3].id | https://openalex.org/keywords/management-science |
| keywords[3].score | 0.4486595690250397 |
| keywords[3].display_name | Management science |
| keywords[4].id | https://openalex.org/keywords/key |
| keywords[4].score | 0.44605544209480286 |
| keywords[4].display_name | Key (lock) |
| keywords[5].id | https://openalex.org/keywords/strengths-and-weaknesses |
| keywords[5].score | 0.4351918399333954 |
| keywords[5].display_name | Strengths and weaknesses |
| keywords[6].id | https://openalex.org/keywords/cognitive-science |
| keywords[6].score | 0.4283912777900696 |
| keywords[6].display_name | Cognitive science |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.4078121483325958 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/data-science |
| keywords[8].score | 0.3764082193374634 |
| keywords[8].display_name | Data science |
| keywords[9].id | https://openalex.org/keywords/epistemology |
| keywords[9].score | 0.24917203187942505 |
| keywords[9].display_name | Epistemology |
| keywords[10].id | https://openalex.org/keywords/psychology |
| keywords[10].score | 0.16955366730690002 |
| keywords[10].display_name | Psychology |
| keywords[11].id | https://openalex.org/keywords/engineering |
| keywords[11].score | 0.1004084050655365 |
| keywords[11].display_name | Engineering |
| keywords[12].id | https://openalex.org/keywords/mathematics |
| keywords[12].score | 0.08265271782875061 |
| keywords[12].display_name | Mathematics |
| keywords[13].id | https://openalex.org/keywords/computer-security |
| keywords[13].score | 0.07603588700294495 |
| keywords[13].display_name | Computer security |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2311.03033 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2311.03033 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2311.03033 |
| locations[1].id | doi:10.48550/arxiv.2311.03033 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2311.03033 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5019550860 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Javier González |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | González, Javier |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5111937381 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Aditya V. Nori |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Nori, Aditya V. |
| authorships[1].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2311.03033 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-11-08T00:00:00 |
| display_name | Beyond Words: A Mathematical Framework for Interpreting Large Language Models |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9779000282287598 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W4295769391, https://openalex.org/W2972220648, https://openalex.org/W2332667808, https://openalex.org/W1997921863, https://openalex.org/W3112960490, https://openalex.org/W2380075625, https://openalex.org/W93605524, https://openalex.org/W2021145421, https://openalex.org/W821271700, https://openalex.org/W2183009720 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2311.03033 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2311.03033 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2311.03033 |
| primary_location.id | pmh:oai:arXiv.org:2311.03033 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2311.03033 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2311.03033 |
| publication_date | 2023-11-06 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 24, 37, 60, 123, 147, 152 |
| abstract_inverted_index.AI | 6, 179 |
| abstract_inverted_index.We | 34, 141, 160 |
| abstract_inverted_index.as | 49, 113 |
| abstract_inverted_index.do | 142 |
| abstract_inverted_index.in | 45, 189 |
| abstract_inverted_index.is | 120 |
| abstract_inverted_index.on | 174 |
| abstract_inverted_index.to | 27, 65, 121, 145, 176 |
| abstract_inverted_index.up | 156 |
| abstract_inverted_index.we | 79 |
| abstract_inverted_index.AI. | 140 |
| abstract_inverted_index.Hex | 36, 57 |
| abstract_inverted_index.LLM | 46 |
| abstract_inverted_index.Our | 118 |
| abstract_inverted_index.The | 56 |
| abstract_inverted_index.and | 11, 16, 31, 43, 53, 62, 71, 73, 86, 104, 115, 133, 166, 186, 193 |
| abstract_inverted_index.are | 4, 93, 168, 182 |
| abstract_inverted_index.but | 150 |
| abstract_inverted_index.can | 9, 129 |
| abstract_inverted_index.for | 107, 126, 138, 154, 170 |
| abstract_inverted_index.how | 175 |
| abstract_inverted_index.it, | 111 |
| abstract_inverted_index.its | 105 |
| abstract_inverted_index.key | 41 |
| abstract_inverted_index.new | 75, 136, 157 |
| abstract_inverted_index.not | 143 |
| abstract_inverted_index.our | 163 |
| abstract_inverted_index.the | 21, 88, 98, 172 |
| abstract_inverted_index.use | 110 |
| abstract_inverted_index.way | 64 |
| abstract_inverted_index.Hex, | 78 |
| abstract_inverted_index.LLMs | 127 |
| abstract_inverted_index.This | 95 |
| abstract_inverted_index.both | 131 |
| abstract_inverted_index.fair | 185 |
| abstract_inverted_index.from | 83 |
| abstract_inverted_index.goal | 119 |
| abstract_inverted_index.have | 146 |
| abstract_inverted_index.help | 130 |
| abstract_inverted_index.like | 191 |
| abstract_inverted_index.such | 48, 112 |
| abstract_inverted_index.text | 15 |
| abstract_inverted_index.that | 8, 39, 109, 128, 162, 181 |
| abstract_inverted_index.they | 92 |
| abstract_inverted_index.tool | 153 |
| abstract_inverted_index.LLMs, | 67 |
| abstract_inverted_index.LLMs. | 33 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.Using | 77 |
| abstract_inverted_index.argue | 161 |
| abstract_inverted_index.basic | 99 |
| abstract_inverted_index.build | 177 |
| abstract_inverted_index.claim | 144 |
| abstract_inverted_index.field | 22 |
| abstract_inverted_index.lacks | 23 |
| abstract_inverted_index.other | 17 |
| abstract_inverted_index.safe, | 183 |
| abstract_inverted_index.terms | 42 |
| abstract_inverted_index.their | 69 |
| abstract_inverted_index.tools | 7 |
| abstract_inverted_index.under | 90 |
| abstract_inverted_index.which | 91 |
| abstract_inverted_index.(LLMs) | 3 |
| abstract_inverted_index.behind | 101 |
| abstract_inverted_index.formal | 124, 164 |
| abstract_inverted_index.models | 2 |
| abstract_inverted_index.offers | 59 |
| abstract_inverted_index.prompt | 116 |
| abstract_inverted_index.rather | 151 |
| abstract_inverted_index.compare | 30 |
| abstract_inverted_index.complex | 18 |
| abstract_inverted_index.crucial | 169 |
| abstract_inverted_index.domains | 190 |
| abstract_inverted_index.explore | 135 |
| abstract_inverted_index.improve | 32 |
| abstract_inverted_index.methods | 108 |
| abstract_inverted_index.natural | 13 |
| abstract_inverted_index.opening | 155 |
| abstract_inverted_index.precise | 61 |
| abstract_inverted_index.propose | 35 |
| abstract_inverted_index.provide | 122 |
| abstract_inverted_index.results | 167 |
| abstract_inverted_index.robust, | 187 |
| abstract_inverted_index.systems | 180 |
| abstract_inverted_index.However, | 20 |
| abstract_inverted_index.avenues. | 159 |
| abstract_inverted_index.concepts | 44 |
| abstract_inverted_index.generate | 10 |
| abstract_inverted_index.identify | 68 |
| abstract_inverted_index.language | 1, 14 |
| abstract_inverted_index.powerful | 5 |
| abstract_inverted_index.research | 158 |
| abstract_inverted_index.software | 194 |
| abstract_inverted_index.advancing | 171 |
| abstract_inverted_index.clarifies | 40, 97 |
| abstract_inverted_index.describe, | 29 |
| abstract_inverted_index.establish | 87 |
| abstract_inverted_index.findings. | 76 |
| abstract_inverted_index.framework | 26, 38, 58, 125 |
| abstract_inverted_index.integrate | 74 |
| abstract_inverted_index.prompting | 85, 103 |
| abstract_inverted_index.reasoning | 82 |
| abstract_inverted_index.reliable, | 184 |
| abstract_inverted_index.research, | 47 |
| abstract_inverted_index.solution, | 149 |
| abstract_inverted_index.strengths | 70 |
| abstract_inverted_index.alignment, | 51 |
| abstract_inverted_index.comprehend | 12 |
| abstract_inverted_index.conditions | 89 |
| abstract_inverted_index.consistent | 63 |
| abstract_inverted_index.definitive | 148 |
| abstract_inverted_index.discussion | 173 |
| abstract_inverted_index.especially | 188 |
| abstract_inverted_index.generative | 139, 178 |
| abstract_inverted_index.healthcare | 192 |
| abstract_inverted_index.reasoning. | 55 |
| abstract_inverted_index.assumptions | 100 |
| abstract_inverted_index.definitions | 165 |
| abstract_inverted_index.distinction | 96 |
| abstract_inverted_index.equivalent. | 94 |
| abstract_inverted_index.researchers | 132 |
| abstract_inverted_index.weaknesses, | 72 |
| abstract_inverted_index.characterize | 66 |
| abstract_inverted_index.engineering. | 195 |
| abstract_inverted_index.implications | 106 |
| abstract_inverted_index.information. | 19 |
| abstract_inverted_index.mathematical | 25 |
| abstract_inverted_index.programming. | 117 |
| abstract_inverted_index.differentiate | 80 |
| abstract_inverted_index.possibilities | 137 |
| abstract_inverted_index.practitioners | 134 |
| abstract_inverted_index.systematically | 28 |
| abstract_inverted_index.hallucinations, | 50 |
| abstract_inverted_index.chain-of-thought | 54, 81, 84, 102 |
| abstract_inverted_index.self-verification | 52, 114 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.5299999713897705 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |