Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models Article Swipe

PDF

Matthew J. Muckley , Alaaeldin El-Nouby , Karen Ullrich , Hervé Jeǵou , Jakob Verbeek ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2301.11189

Lossy image compression aims to represent images in as few bits as possible while maintaining fidelity to the original. Theoretical results indicate that optimizing distortion metrics such as PSNR or MS-SSIM necessarily leads to a discrepancy in the statistics of original images from those of reconstructions, in particular at low bitrates, often manifested by the blurring of the compressed images. Previous work has leveraged adversarial discriminators to improve statistical fidelity. Yet these binary discriminators adopted from generative modeling tasks may not be ideal for image compression. In this paper, we introduce a non-binary discriminator that is conditioned on quantized local image representations obtained via VQ-VAE autoencoders. Our evaluations on the CLIC2020, DIV2K and Kodak datasets show that our discriminator is more effective for jointly optimizing distortion (e.g., PSNR) and statistical fidelity (e.g., FID) than the PatchGAN of the state-of-the-art HiFiC model. On CLIC2020, we obtain the same FID as HiFiC with 30-40\% fewer bits.

Related Topics

Fidelity

Lossy Compression

Computer Science

Artificial Intelligence

Electrical Engineering

Engineering

Arithmetic

Concepts

Discriminator Fidelity Lossy compression Computer science Artificial intelligence Distortion (music) Binary number Image (mathematics) Image compression Pattern recognition (psychology) Statistical model High fidelity Data compression Algorithm Mathematics Image processing Amplifier Bandwidth (computing) Computer network Electrical engineering Telecommunications Detector Engineering Arithmetic

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2301.11189
PDF: https://arxiv.org/pdf/2301.11189
OA Status: green
Cited By: 7
Related Works: 10
OpenAlex ID: https://openalex.org/W4318350438

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4318350438

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2301.11189

Digital Object Identifier
Title: Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2023

Year of publication
Publication date: 2023-01-26

Full publication date if available
Authors: Matthew J. Muckley, Alaaeldin El-Nouby, Karen Ullrich, Hervé Jeǵou, Jakob Verbeek

List of authors in order
Landing page: https://arxiv.org/abs/2301.11189

Publisher landing page
PDF URL: https://arxiv.org/pdf/2301.11189

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2301.11189

Direct OA link when available
Concepts: Discriminator, Fidelity, Lossy compression, Computer science, Artificial intelligence, Distortion (music), Binary number, Image (mathematics), Image compression, Pattern recognition (psychology), Statistical model, High fidelity, Data compression, Algorithm, Mathematics, Image processing, Amplifier, Bandwidth (computing), Computer network, Electrical engineering, Telecommunications, Detector, Engineering, Arithmetic

Top concepts (fields/topics) attached by OpenAlex
Cited by: 7

Total citation count in OpenAlex
Citations by year (recent): 2025: 3, 2024: 3, 2023: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4318350438
doi	https://doi.org/10.48550/arxiv.2301.11189
ids.doi	https://doi.org/10.48550/arxiv.2301.11189
ids.openalex	https://openalex.org/W4318350438
fwci	1.27377838
type	preprint
title	Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T12357
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9993000030517578
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Digital Media Forensic Detection
topics[1].id	https://openalex.org/T11105
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9976999759674072
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1707
topics[1].subfield.display_name	Computer Vision and Pattern Recognition
topics[1].display_name	Advanced Image Processing Techniques
topics[2].id	https://openalex.org/T13114
topics[2].field.id	https://openalex.org/fields/22
topics[2].field.display_name	Engineering
topics[2].score	0.9965000152587891
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2214
topics[2].subfield.display_name	Media Technology
topics[2].display_name	Image Processing Techniques and Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C2779803651
concepts[0].level	3
concepts[0].score	0.8183969259262085
concepts[0].wikidata	https://www.wikidata.org/wiki/Q5282088
concepts[0].display_name	Discriminator
concepts[1].id	https://openalex.org/C2776459999
concepts[1].level	2
concepts[1].score	0.7238031625747681
concepts[1].wikidata	https://www.wikidata.org/wiki/Q2119376
concepts[1].display_name	Fidelity
concepts[2].id	https://openalex.org/C165021410
concepts[2].level	2
concepts[2].score	0.7118315100669861
concepts[2].wikidata	https://www.wikidata.org/wiki/Q55564
concepts[2].display_name	Lossy compression
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.654140830039978
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.6155346035957336
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C126780896
concepts[5].level	4
concepts[5].score	0.5912734270095825
concepts[5].wikidata	https://www.wikidata.org/wiki/Q899871
concepts[5].display_name	Distortion (music)
concepts[6].id	https://openalex.org/C48372109
concepts[6].level	2
concepts[6].score	0.5722851157188416
concepts[6].wikidata	https://www.wikidata.org/wiki/Q3913
concepts[6].display_name	Binary number
concepts[7].id	https://openalex.org/C115961682
concepts[7].level	2
concepts[7].score	0.5641062259674072
concepts[7].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[7].display_name	Image (mathematics)
concepts[8].id	https://openalex.org/C13481523
concepts[8].level	4
concepts[8].score	0.5103873610496521
concepts[8].wikidata	https://www.wikidata.org/wiki/Q412438
concepts[8].display_name	Image compression
concepts[9].id	https://openalex.org/C153180895
concepts[9].level	2
concepts[9].score	0.49947500228881836
concepts[9].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[9].display_name	Pattern recognition (psychology)
concepts[10].id	https://openalex.org/C114289077
concepts[10].level	2
concepts[10].score	0.453779011964798
concepts[10].wikidata	https://www.wikidata.org/wiki/Q3284399
concepts[10].display_name	Statistical model
concepts[11].id	https://openalex.org/C113364801
concepts[11].level	2
concepts[11].score	0.4441251754760742
concepts[11].wikidata	https://www.wikidata.org/wiki/Q26674
concepts[11].display_name	High fidelity
concepts[12].id	https://openalex.org/C78548338
concepts[12].level	2
concepts[12].score	0.43250176310539246
concepts[12].wikidata	https://www.wikidata.org/wiki/Q2493
concepts[12].display_name	Data compression
concepts[13].id	https://openalex.org/C11413529
concepts[13].level	1
concepts[13].score	0.3458695411682129
concepts[13].wikidata	https://www.wikidata.org/wiki/Q8366
concepts[13].display_name	Algorithm
concepts[14].id	https://openalex.org/C33923547
concepts[14].level	0
concepts[14].score	0.2805570960044861
concepts[14].wikidata	https://www.wikidata.org/wiki/Q395
concepts[14].display_name	Mathematics
concepts[15].id	https://openalex.org/C9417928
concepts[15].level	3
concepts[15].score	0.22632291913032532
concepts[15].wikidata	https://www.wikidata.org/wiki/Q1070689
concepts[15].display_name	Image processing
concepts[16].id	https://openalex.org/C194257627
concepts[16].level	3
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q211554
concepts[16].display_name	Amplifier
concepts[17].id	https://openalex.org/C2776257435
concepts[17].level	2
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q1576430
concepts[17].display_name	Bandwidth (computing)
concepts[18].id	https://openalex.org/C31258907
concepts[18].level	1
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q1301371
concepts[18].display_name	Computer network
concepts[19].id	https://openalex.org/C119599485
concepts[19].level	1
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q43035
concepts[19].display_name	Electrical engineering
concepts[20].id	https://openalex.org/C76155785
concepts[20].level	1
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q418
concepts[20].display_name	Telecommunications
concepts[21].id	https://openalex.org/C94915269
concepts[21].level	2
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q1834857
concepts[21].display_name	Detector
concepts[22].id	https://openalex.org/C127413603
concepts[22].level	0
concepts[22].score	0.0
concepts[22].wikidata	https://www.wikidata.org/wiki/Q11023
concepts[22].display_name	Engineering
concepts[23].id	https://openalex.org/C94375191
concepts[23].level	1
concepts[23].score	0.0
concepts[23].wikidata	https://www.wikidata.org/wiki/Q11205
concepts[23].display_name	Arithmetic
keywords[0].id	https://openalex.org/keywords/discriminator
keywords[0].score	0.8183969259262085
keywords[0].display_name	Discriminator
keywords[1].id	https://openalex.org/keywords/fidelity
keywords[1].score	0.7238031625747681
keywords[1].display_name	Fidelity
keywords[2].id	https://openalex.org/keywords/lossy-compression
keywords[2].score	0.7118315100669861
keywords[2].display_name	Lossy compression
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.654140830039978
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.6155346035957336
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/distortion
keywords[5].score	0.5912734270095825
keywords[5].display_name	Distortion (music)
keywords[6].id	https://openalex.org/keywords/binary-number
keywords[6].score	0.5722851157188416
keywords[6].display_name	Binary number
keywords[7].id	https://openalex.org/keywords/image
keywords[7].score	0.5641062259674072
keywords[7].display_name	Image (mathematics)
keywords[8].id	https://openalex.org/keywords/image-compression
keywords[8].score	0.5103873610496521
keywords[8].display_name	Image compression
keywords[9].id	https://openalex.org/keywords/pattern-recognition
keywords[9].score	0.49947500228881836
keywords[9].display_name	Pattern recognition (psychology)
keywords[10].id	https://openalex.org/keywords/statistical-model
keywords[10].score	0.453779011964798
keywords[10].display_name	Statistical model
keywords[11].id	https://openalex.org/keywords/high-fidelity
keywords[11].score	0.4441251754760742
keywords[11].display_name	High fidelity
keywords[12].id	https://openalex.org/keywords/data-compression
keywords[12].score	0.43250176310539246
keywords[12].display_name	Data compression
keywords[13].id	https://openalex.org/keywords/algorithm
keywords[13].score	0.3458695411682129
keywords[13].display_name	Algorithm
keywords[14].id	https://openalex.org/keywords/mathematics
keywords[14].score	0.2805570960044861
keywords[14].display_name	Mathematics
keywords[15].id	https://openalex.org/keywords/image-processing
keywords[15].score	0.22632291913032532
keywords[15].display_name	Image processing
language	en
locations[0].id	pmh:oai:arXiv.org:2301.11189
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/2301.11189
locations[0].version	submittedVersion
locations[0].raw_type	text
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/2301.11189
locations[1].id	doi:10.48550/arxiv.2301.11189
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-journal
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.2301.11189
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5029739727
authorships[0].author.orcid	https://orcid.org/0000-0002-6525-8817
authorships[0].author.display_name	Matthew J. Muckley
authorships[0].author_position	first
authorships[0].raw_author_name	Muckley, Matthew J.
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5083505661
authorships[1].author.orcid
authorships[1].author.display_name	Alaaeldin El-Nouby
authorships[1].author_position	middle
authorships[1].raw_author_name	El-Nouby, Alaaeldin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5058031547
authorships[2].author.orcid
authorships[2].author.display_name	Karen Ullrich
authorships[2].author_position	middle
authorships[2].raw_author_name	Ullrich, Karen
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5111802678
authorships[3].author.orcid
authorships[3].author.display_name	Hervé Jeǵou
authorships[3].author_position	middle
authorships[3].raw_author_name	Jégou, Hervé
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5040312210
authorships[4].author.orcid	https://orcid.org/0000-0003-1419-1816
authorships[4].author.display_name	Jakob Verbeek
authorships[4].author_position	last
authorships[4].raw_author_name	Verbeek, Jakob
authorships[4].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/2301.11189
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T12357
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9993000030517578
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Digital Media Forensic Detection
related_works	https://openalex.org/W3210332869, https://openalex.org/W4210785996, https://openalex.org/W4327499886, https://openalex.org/W1680283075, https://openalex.org/W3162084246, https://openalex.org/W2181436147, https://openalex.org/W2056051076, https://openalex.org/W2015677580, https://openalex.org/W2115343698, https://openalex.org/W3202870363
cited_by_count	7
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	3
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	3
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2301.11189
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/2301.11189
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
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/2301.11189
primary_location.id	pmh:oai:arXiv.org:2301.11189
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/2301.11189
primary_location.version	submittedVersion
primary_location.raw_type	text
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/2301.11189
publication_date	2023-01-26
publication_year	2023
referenced_works_count	0
abstract_inverted_index.a	34, 91
abstract_inverted_index.In	86
abstract_inverted_index.On	141
abstract_inverted_index.as	8, 11, 27, 148
abstract_inverted_index.at	48
abstract_inverted_index.be	81
abstract_inverted_index.by	53
abstract_inverted_index.in	7, 36, 46
abstract_inverted_index.is	95, 119
abstract_inverted_index.of	39, 44, 56, 136
abstract_inverted_index.on	97, 108
abstract_inverted_index.or	29
abstract_inverted_index.to	4, 16, 33, 66
abstract_inverted_index.we	89, 143
abstract_inverted_index.FID	147
abstract_inverted_index.Our	106
abstract_inverted_index.Yet	70
abstract_inverted_index.and	112, 128
abstract_inverted_index.few	9
abstract_inverted_index.for	83, 122
abstract_inverted_index.has	62
abstract_inverted_index.low	49
abstract_inverted_index.may	79
abstract_inverted_index.not	80
abstract_inverted_index.our	117
abstract_inverted_index.the	17, 37, 54, 57, 109, 134, 137, 145
abstract_inverted_index.via	103
abstract_inverted_index.FID)	132
abstract_inverted_index.PSNR	28
abstract_inverted_index.aims	3
abstract_inverted_index.bits	10
abstract_inverted_index.from	42, 75
abstract_inverted_index.more	120
abstract_inverted_index.same	146
abstract_inverted_index.show	115
abstract_inverted_index.such	26
abstract_inverted_index.than	133
abstract_inverted_index.that	22, 94, 116
abstract_inverted_index.this	87
abstract_inverted_index.with	150
abstract_inverted_index.work	61
abstract_inverted_index.DIV2K	111
abstract_inverted_index.HiFiC	139, 149
abstract_inverted_index.Kodak	113
abstract_inverted_index.Lossy	0
abstract_inverted_index.PSNR)	127
abstract_inverted_index.bits.	153
abstract_inverted_index.fewer	152
abstract_inverted_index.ideal	82
abstract_inverted_index.image	1, 84, 100
abstract_inverted_index.leads	32
abstract_inverted_index.local	99
abstract_inverted_index.often	51
abstract_inverted_index.tasks	78
abstract_inverted_index.these	71
abstract_inverted_index.those	43
abstract_inverted_index.while	13
abstract_inverted_index.(e.g.,	126, 131
abstract_inverted_index.VQ-VAE	104
abstract_inverted_index.binary	72
abstract_inverted_index.images	6, 41
abstract_inverted_index.model.	140
abstract_inverted_index.obtain	144
abstract_inverted_index.paper,	88
abstract_inverted_index.30-40\%	151
abstract_inverted_index.MS-SSIM	30
abstract_inverted_index.adopted	74
abstract_inverted_index.images.	59
abstract_inverted_index.improve	67
abstract_inverted_index.jointly	123
abstract_inverted_index.metrics	25
abstract_inverted_index.results	20
abstract_inverted_index.PatchGAN	135
abstract_inverted_index.Previous	60
abstract_inverted_index.blurring	55
abstract_inverted_index.datasets	114
abstract_inverted_index.fidelity	15, 130
abstract_inverted_index.indicate	21
abstract_inverted_index.modeling	77
abstract_inverted_index.obtained	102
abstract_inverted_index.original	40
abstract_inverted_index.possible	12
abstract_inverted_index.CLIC2020,	110, 142
abstract_inverted_index.bitrates,	50
abstract_inverted_index.effective	121
abstract_inverted_index.fidelity.	69
abstract_inverted_index.introduce	90
abstract_inverted_index.leveraged	63
abstract_inverted_index.original.	18
abstract_inverted_index.quantized	98
abstract_inverted_index.represent	5
abstract_inverted_index.compressed	58
abstract_inverted_index.distortion	24, 125
abstract_inverted_index.generative	76
abstract_inverted_index.manifested	52
abstract_inverted_index.non-binary	92
abstract_inverted_index.optimizing	23, 124
abstract_inverted_index.particular	47
abstract_inverted_index.statistics	38
abstract_inverted_index.Theoretical	19
abstract_inverted_index.adversarial	64
abstract_inverted_index.compression	2
abstract_inverted_index.conditioned	96
abstract_inverted_index.discrepancy	35
abstract_inverted_index.evaluations	107
abstract_inverted_index.maintaining	14
abstract_inverted_index.necessarily	31
abstract_inverted_index.statistical	68, 129
abstract_inverted_index.compression.	85
abstract_inverted_index.autoencoders.	105
abstract_inverted_index.discriminator	93, 118
abstract_inverted_index.discriminators	65, 73
abstract_inverted_index.representations	101
abstract_inverted_index.reconstructions,	45
abstract_inverted_index.state-of-the-art	138
cited_by_percentile_year.max	97
cited_by_percentile_year.min	89
countries_distinct_count	0
institutions_distinct_count	5
sustainable_development_goals[0].id	https://metadata.un.org/sdg/10
sustainable_development_goals[0].score	0.7699999809265137
sustainable_development_goals[0].display_name	Reduced inequalities
citation_normalized_percentile.value	0.77449444
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False