Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making

Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked to use ML predictions to make high-stakes decisions. Multiple ML usability challenges can appear as result, such as lack...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on visualization and computer graphics Ročník 28; číslo 1; s. 1161 - 1171
Hlavní autori: Zytek, Alexandra, Liu, Dongyu, Vaithianathan, Rhema, Veeramachaneni, Kalyan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.01.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:1077-2626, 1941-0506, 1941-0506
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked to use ML predictions to make high-stakes decisions. Multiple ML usability challenges can appear as result, such as lack of user trust in the model, inability to reconcile human-ML disagreement, and ethical concerns about oversimplification of complex problems to a single algorithm output. In this paper, we investigate the ML usability challenges that present in the domain of child welfare screening through a series of collaborations with child welfare screeners. Following the iterative design process between the ML scientists, visualization researchers, and domain experts (child screeners), we first identified four key ML challenges and honed in on one promising explainable ML technique to address them (local factor contributions). Then we implemented and evaluated our visual analytics tool, Sibyl, to increase the interpretability and interactivity of local factor contributions. The effectiveness of our tool is demonstrated by two formal user studies with 12 non-expert participants and 13 expert participants respectively. Valuable feedback was collected, from which we composed a list of design implications as a useful guideline for researchers who aim to develop an interpretable and interactive visualization tool for ML prediction models deployed for child welfare screeners and other similar domain experts.
AbstractList Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked to use ML predictions to make high-stakes decisions. Multiple ML usability challenges can appear as result, such as lack of user trust in the model, inability to reconcile human-ML disagreement, and ethical concerns about oversimplification of complex problems to a single algorithm output. In this paper, we investigate the ML usability challenges that present in the domain of child welfare screening through a series of collaborations with child welfare screeners. Following the iterative design process between the ML scientists, visualization researchers, and domain experts (child screeners), we first identified four key ML challenges and honed in on one promising explainable ML technique to address them (local factor contributions). Then we implemented and evaluated our visual analytics tool, Sibyl, to increase the interpretability and interactivity of local factor contributions. The effectiveness of our tool is demonstrated by two formal user studies with 12 non-expert participants and 13 expert participants respectively. Valuable feedback was collected, from which we composed a list of design implications as a useful guideline for researchers who aim to develop an interpretable and interactive visualization tool for ML prediction models deployed for child welfare screeners and other similar domain experts.Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked to use ML predictions to make high-stakes decisions. Multiple ML usability challenges can appear as result, such as lack of user trust in the model, inability to reconcile human-ML disagreement, and ethical concerns about oversimplification of complex problems to a single algorithm output. In this paper, we investigate the ML usability challenges that present in the domain of child welfare screening through a series of collaborations with child welfare screeners. Following the iterative design process between the ML scientists, visualization researchers, and domain experts (child screeners), we first identified four key ML challenges and honed in on one promising explainable ML technique to address them (local factor contributions). Then we implemented and evaluated our visual analytics tool, Sibyl, to increase the interpretability and interactivity of local factor contributions. The effectiveness of our tool is demonstrated by two formal user studies with 12 non-expert participants and 13 expert participants respectively. Valuable feedback was collected, from which we composed a list of design implications as a useful guideline for researchers who aim to develop an interpretable and interactive visualization tool for ML prediction models deployed for child welfare screeners and other similar domain experts.
Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked to use ML predictions to make high-stakes decisions. Multiple ML usability challenges can appear as result, such as lack of user trust in the model, inability to reconcile human-ML disagreement, and ethical concerns about oversimplification of complex problems to a single algorithm output. In this paper, we investigate the ML usability challenges that present in the domain of child welfare screening through a series of collaborations with child welfare screeners. Following the iterative design process between the ML scientists, visualization researchers, and domain experts (child screeners), we first identified four key ML challenges and honed in on one promising explainable ML technique to address them (local factor contributions). Then we implemented and evaluated our visual analytics tool, Sibyl, to increase the interpretability and interactivity of local factor contributions. The effectiveness of our tool is demonstrated by two formal user studies with 12 non-expert participants and 13 expert participants respectively. Valuable feedback was collected, from which we composed a list of design implications as a useful guideline for researchers who aim to develop an interpretable and interactive visualization tool for ML prediction models deployed for child welfare screeners and other similar domain experts.
Author Vaithianathan, Rhema
Liu, Dongyu
Zytek, Alexandra
Veeramachaneni, Kalyan
Author_xml – sequence: 1
  givenname: Alexandra
  surname: Zytek
  fullname: Zytek, Alexandra
  email: zyteka@mit.edu
  organization: MIT, United States
– sequence: 2
  givenname: Dongyu
  surname: Liu
  fullname: Liu, Dongyu
  email: dongyu@mit.edu
  organization: MIT, United States
– sequence: 3
  givenname: Rhema
  surname: Vaithianathan
  fullname: Vaithianathan, Rhema
  email: rhema.vaithianathan@aut.ac.nz
  organization: Auckland University of Technology, New Zealand
– sequence: 4
  givenname: Kalyan
  surname: Veeramachaneni
  fullname: Veeramachaneni, Kalyan
  email: kalyan@csail.mit.edu
  organization: MIT, United States
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34587081$$D View this record in MEDLINE/PubMed
BookMark eNp9kTtv2zAUhYkiQfNofkBRoBDQpYtcXpLio1vgtkkAFx0SZxUo6cpmIlMJSQ_-96VqN0OGTIcEv8N7cc4ZOfKjR0I-Ap0BUPPt7n5-NWOUwYwDCC3FO3IKRkBJKyqP8pkqVTLJ5Ak5i_GBUhBCm_fkhItKK6rhlIy3rtkN34ul7zDEZH3n_KrIUlx2XcAYp2taY7GMtnGDS7tivrbDgH6FsRj74rdt185jsUAb_ATf-OLardblbbKPGfmBrYtu9Bl8zM8fyHFvh4gXBz0ny18_7-bX5eLP1c38clG2XJhUtlR1nUZFTdVrDtIY1hgutGipRrS6F1LoXjOhgDELvepaLiWKpuuhaQTn5-Tr_t-nMD5vMaZ642KLw2A9jttYs0ppqKhQNKNfXqEP4zb4vF3NJHCeg_pHfT5Q22aDXf0U3MaGXf0_ygzAHmjDGGPA_gUBWk911VNd9VRXfagre9QrT-uSTTmuFKwb3nR-2jsdIr5MMlXFtDD8L7F4oIM
CODEN ITVGEA
CitedBy_id crossref_primary_10_3390_diagnostics14090917
crossref_primary_10_1109_TVCG_2024_3487974
crossref_primary_10_1016_j_inffus_2024_102412
crossref_primary_10_1016_j_techfore_2023_122824
crossref_primary_10_3390_systems13020131
crossref_primary_10_3390_drones8040155
crossref_primary_10_3390_informatics9010014
crossref_primary_10_1109_TVCG_2024_3456160
crossref_primary_10_1016_j_techfore_2024_123326
crossref_primary_10_3389_fcomp_2024_1521066
crossref_primary_10_1093_cjres_rsac025
crossref_primary_10_3390_app14198884
crossref_primary_10_1007_s13198_025_02712_9
crossref_primary_10_1016_j_compbiolchem_2025_108599
crossref_primary_10_3390_make7010013
crossref_primary_10_1109_TVCG_2023_3259341
crossref_primary_10_1109_TVCG_2024_3357065
crossref_primary_10_1145_3512950
crossref_primary_10_1177_14738716241240156
Cites_doi 10.1145/2858036.2858529
10.1109/TVCG.2018.2864499
10.1109/TVCG.2019.2934629
10.1038/s41551-018-0304-0
10.1007/978-3-319-90403-0_9
10.1109/TVCG.2009.111
10.1145/3290605.3300831
10.1109/TVCG.2018.2865027
10.1145/2851581.2856492
10.1038/s42256-019-0048-x
10.2105/AJPH.2016.303545
10.1145/3290605.3300809
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TVCG.2021.3114864
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed

Technology Research Database
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0506
EndPage 1171
ExternalDocumentID 34587081
10_1109_TVCG_2021_3114864
9552849
Genre orig-research
Research Support, U.S. Gov't, Non-P.H.S
Journal Article
GrantInformation_xml – fundername: NSF
  grantid: 1761812
  funderid: 10.13039/100000001
GroupedDBID ---
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNI
RNS
RZB
TN5
VH1
AAYXX
CITATION
AAYOK
NPM
PKN
RIC
RIG
Z5M
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c349t-c07dd8e7095f8316992b93484c08eea8f4648f8247122a1f7dc366e4bdf1bb433
IEDL.DBID RIE
ISICitedReferencesCount 31
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000733959000109&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1077-2626
1941-0506
IngestDate Thu Oct 02 07:36:42 EDT 2025
Mon Jun 30 04:29:16 EDT 2025
Wed Feb 19 02:27:58 EST 2025
Tue Nov 18 22:27:42 EST 2025
Sat Nov 29 03:31:38 EST 2025
Wed Aug 27 02:49:29 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c349t-c07dd8e7095f8316992b93484c08eea8f4648f8247122a1f7dc366e4bdf1bb433
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
PMID 34587081
PQID 2613370870
PQPubID 75741
PageCount 11
ParticipantIDs pubmed_primary_34587081
proquest_miscellaneous_2578150470
crossref_primary_10_1109_TVCG_2021_3114864
proquest_journals_2613370870
crossref_citationtrail_10_1109_TVCG_2021_3114864
ieee_primary_9552849
PublicationCentury 2000
PublicationDate 2022-Jan.
2022-1-00
2022-01-00
20220101
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-Jan.
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on visualization and computer graphics
PublicationTitleAbbrev TVCG
PublicationTitleAlternate IEEE Trans Vis Comput Graph
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref12
ref15
ref11
ref10
doshi-velez (ref2) 2017
vaithianathan (ref23) 2019
fisher (ref3) 2019; 20
lundberg (ref14) 2017; 31
ref16
ref19
(ref5) 2020
kenton (ref9) 2021
vaithianathan (ref24) 2017
richardson (ref18) 1990; 2
ref25
ref20
xu (ref26) 2019
kahng (ref8) 2017; 24
strobelt (ref22) 2017; 24
ref21
ref27
lipton (ref13) 2016; 16
(ref1) 2020
(ref17) 2017
ref4
ref6
hurley (ref7) 2018
References_xml – ident: ref11
  doi: 10.1145/2858036.2858529
– volume: 31
  start-page: 10
  year: 2017
  ident: ref14
  article-title: A Unified Approach to Interpreting Model Predictions
  publication-title: Advances in neural information processing systems
– start-page: 30
  year: 2018
  ident: ref7
  publication-title: Can an Algorithm Tell When Kids Are in Danger?
– volume: 24
  start-page: 10
  year: 2017
  ident: ref8
  article-title: ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models
  publication-title: IEEE Conference on Visual Analytics Science and Technology (VAST)
– volume: 16
  start-page: 31
  year: 2016
  ident: ref13
  article-title: The Mythos of Model Interpretability
  publication-title: 2016 ICML Workshop on Human Interpretability in Machine Learning
– volume: 20
  start-page: 1
  year: 2019
  ident: ref3
  article-title: All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously
  publication-title: Journal of Machine Learning Research
– volume: 2
  start-page: 226
  year: 1990
  ident: ref18
  article-title: The Effects of a False Allegation of Child Sexual Abuse on an Intact Middle Class Family
  publication-title: IPT
– start-page: 60
  year: 2017
  ident: ref24
  publication-title: Developing Predictive Models to Support Child Maltreatment Hotline Screening Decisions Allegheny County Methodology and Implementation
– ident: ref27
  doi: 10.1109/TVCG.2018.2864499
– year: 2020
  ident: ref5
  publication-title: Machine Learning Glossary Fairness
– year: 2021
  ident: ref9
  article-title: How Cost-Benefit Analysis Process Is Performed
  publication-title: Investope-dia
– ident: ref21
  doi: 10.1109/TVCG.2019.2934629
– year: 2017
  ident: ref17
  article-title: National Highway Traffic Safety Administration (NHTSA)
  publication-title: Automated Vehicles for Safety
– ident: ref15
  doi: 10.1038/s41551-018-0304-0
– ident: ref19
  doi: 10.1007/978-3-319-90403-0_9
– year: 2019
  ident: ref23
  publication-title: Implementing a Child Welfare Decision Aide in Douglas County
– ident: ref16
  doi: 10.1109/TVCG.2009.111
– year: 2020
  ident: ref1
  article-title: Children's Bureau
  publication-title: Child Maltreatment 2018 Summary of Key Findings
– ident: ref25
  doi: 10.1145/3290605.3300831
– year: 2017
  ident: ref2
  publication-title: Towards a rigorous science of interpretable machine learning
– ident: ref12
  doi: 10.1109/TVCG.2018.2865027
– ident: ref4
  doi: 10.1145/2851581.2856492
– year: 2019
  ident: ref26
  article-title: Modeling tabular data using conditional GAN
  publication-title: Advances in neural information processing systems
– ident: ref20
  doi: 10.1038/s42256-019-0048-x
– ident: ref10
  doi: 10.2105/AJPH.2016.303545
– ident: ref6
  doi: 10.1145/3290605.3300809
– volume: 24
  start-page: 667
  year: 2017
  ident: ref22
  article-title: LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
  publication-title: Infovis
SSID ssj0014489
Score 2.5427222
Snippet Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1161
SubjectTerms Algorithms
Child welfare
Context modeling
Decision making
Domains
Iterative methods
Machine learning
Pediatrics
Prediction algorithms
Prediction models
Predictive models
Subject specialists
Usability
Visualization
XAI
Title Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making
URI https://ieeexplore.ieee.org/document/9552849
https://www.ncbi.nlm.nih.gov/pubmed/34587081
https://www.proquest.com/docview/2613370870
https://www.proquest.com/docview/2578150470
Volume 28
WOSCitedRecordID wos000733959000109&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0506
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014489
  issn: 1077-2626
  databaseCode: RIE
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELbaigMceJXHQqmMxAlh6ldim1u1UOBAhUQX7S1ynDGqqBLU3UXqv2fseKMiARKnJMrkoczn-BvPi5AX3pvWS6VZiNowHSvBbB01Uy4gmxAdD77NzSbM6aldLt3nHfJqyoUBgBx8Bq_Tbvbld0PYpKWyI1dV-Dd1u2TXGDPmak0eAzQz3BhfaJhEll48mIK7o7Ov8_doCUqBBiqy_zr14lG6QqRa8dt0lPur_J1q5inn5M7_vexdcrtQS3o8YuEe2YH-Prl1reDgPhm-nLdXF2_o4npKC8UNPe66HBGLh0gJ6WKsvLu-ovNtt5UVHSL9lGMvgZayrN_ox56mUBGGpPU7irwtLXtQMK3BPyCLk3dn8w-stFxgQWm3ZoGbrrNgkHhFq0TtnGyd0lYHbgG8jbrWNlqJU5qUXkTTBVXXoNsuirbVSj0ke_3Qw2NCoa0caOmVd5U2Ve0NqqUTUHEJNQeYEb798k0o9chTW4yLJtsl3DVJb03SW1P0NiMvp0t-jMU4_iW8n5QyCRZ9zMjBVr1NGa6rBs1IpRAOhs_I8-k0DrTkPfE9DBuUwX8bsmedZB6NsJjuvUXTkz8_8ym5KVPWRF65OSB768sNPCM3ws_1-eryENG8tIcZzb8Ae8PtVw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1ba9RAFD7UKqgP9VKta6uO4JOYNnNJZqZvZbW22C6Cu9K3MJmcSGlJpLsr9N97ZpINLajgUxJyciHfmcx35twA3jmnSyekSnytdKLqjCcmr1UirSc2wavUuzI2m9CTiTk7s1_X4MOQC4OIMfgMd8Nu9OVXrV-GpbI9m2X0N7V34G6mlOBdttbgMyBDw3YRhjoRxNN7HyZP7d70-_gz2YKCk4lK_D8P3XikykhXDb81IcUOK38nm3HSOXz0f6_7GDZ6cskOOm14AmvYPIWHN0oObkL77by8vtxns5tJLYw27KCqYkwsHRIpZLOu9u7imo1X_VbmrK3ZaYy-RNYXZv3BjhsWgkUSoq0XJPKxb9pDgmEV_hnMDj9Nx0dJ33Qh8VLZReJTXVUGNVGv2kieWytKK5VRPjWIztQqV6Y2giY1IRyvdeVlnqMqq5qXpZLyOaw3bYMvgGGZWVTCSWczpbPcaYKl4pilAvMUcQTp6ssXvq9IHhpjXBbRMkltEXArAm5Fj9sI3g-X_OzKcfxLeDOAMgj2eIxgZwVv0Q_YeUGGpJSkDjodwdvhNA214D9xDbZLkqG_G_FnFWS2OrUY7r3Sppd_fuYbuH80PT0pTo4nX7bhgQg5FHEdZwfWF1dLfAX3_K_F-fzqddTp32KH77Y
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Sibyl%3A+Understanding+and+Addressing+the+Usability+Challenges+of+Machine+Learning+In+High-Stakes+Decision+Making&rft.jtitle=IEEE+transactions+on+visualization+and+computer+graphics&rft.au=Zytek%2C+Alexandra&rft.au=Liu%2C+Dongyu&rft.au=Vaithianathan%2C+Rhema&rft.au=Veeramachaneni%2C+Kalyan&rft.date=2022-01-01&rft.issn=1077-2626&rft.eissn=1941-0506&rft.volume=28&rft.issue=1&rft.spage=1161&rft.epage=1171&rft_id=info:doi/10.1109%2FTVCG.2021.3114864&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TVCG_2021_3114864
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-2626&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-2626&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-2626&client=summon