The DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index.
Forecasting Murder Within a Population of Probationers and Parolees: A High Stakes Application of Statistical Learning
Open accessAbstract
Summary: Forecasts of future dangerousness are often used to inform the sentencing decisions of convicted offenders. For individuals who are sentenced to probation or paroled to community supervision, such forecasts affect the conditions under which they are to be supervised. The statistical criterion for these forecasts is commonly called recidivism, which is defined as a charge or conviction for any new offence, no matter how minor. Only rarely do such forecasts make distinctions on the basis of the seriousness of offences. Yet seriousness may be central to public concerns, and judges are increasingly required by law and sentencing guidelines to make assessments of seriousness. At the very least, information about seriousness is essential for allocating scarce resources for community supervision of convicted offenders. The paper focuses only on murderous conduct by individuals on probation or parole. Using data on a population of over 60000 cases from Philadelphia’s Adult Probation and Parole Department, we forecast whether each offender will be charged with a homicide or attempted homicide within 2 years of beginning community supervision. We use a statistical learning approach that makes no assumptions about how predictors are related to the outcome. We also build in the costs of false negative and false positive charges and use half of the data to build the forecasting model, and the other half of the data to evaluate the quality of the forecasts. Forecasts that are based on this approach offer the possibility of concentrating rehabilitation, treatment and surveillance resources on a small subset of convicted offenders who may be in greatest need, and who pose the greatest risk to society.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 cited source doesn’t support the claim as written.
In the citing paper
“For instance, Berk et al. evaluated their model only on the set of defendants who have been granted parole.”
From The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables (2017) · cites this paper as [7]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This assumption does not typically hold in cases where human decisions are providing data labels [7, 21].”
From The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables (2017) · cites this paper as [7]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“While prior research has explored applications of machine learning to domains where human judgments are part of the data labeling process (crime [7, 21, 43], medical diagnosis [6, 22]), the selective labels problem is often overlooked, with evaluation of the models typically carried out by computing traditional metrics such as AUC or accuracy only on the data points for which ground truth labels”
From The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables (2017) · cites this paper as [7]
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Classification and Regression Trees.
Gordon, A. D., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984) · Biometrics · doi:10.2307/2530946 · Cited by 23,867
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 21,030
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Neighborhoods and Violent Crime: A Multilevel Study of Collective Efficacy
Sampson, R. J., Raudenbush, S. W., & Earls, F. (1997) · Science · doi:10.1126/science.277.5328.918 · Cited by 11,999
Friedman, J. H. (2002) · Computational Statistics & Data Analysis · doi:10.1016/s0167-9473(01)00065-2 · Cited by 7,067
Bias in random forest variable importance measures: Illustrations, sources and a solution
Strobl, C., Boulesteix, A., Zeileis, A., & Hothorn, T. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-25 · Cited by 3,970
Research works printed but not linked: 8
- Allen, 2007, Justice reinvestment: a new approach to crime and justice
- Anderson, 1999, Code of the Street
- Ayres, 2007, Supercrunchers: how Anything can be Predicted
- Burgess, 1928, The Working of the Indeterminant Sentence Law and the Parole System in Illinois, 205
- Gottfredson, 1987, Prediction and Classification
- Gottfredson, 1987, Prediction and Classification
- Maltz, 1984, Recidvism
- Malvestuto, 2007, Testimony to Committee on Public Safety, Council of the City of Philadelphia
Cited by
Sorted by citations
Items 101–178 of 178
The great methods bake-off: Comparing performance of machine learning algorithms
Kigerl, A., Hamilton, Z., Kowalski, M., & Mei, X. (2022) · Journal of Criminal Justice · doi:10.1016/j.jcrimjus.2022.101946 · Cited by 8
Carson, D. (2011) · Journal of Investigative Psychology and Offender Profiling · doi:10.1002/jip.133 · Cited by 8
Sherman, L. W. (2011) · doi:10.1093/acprof:oso/9780199571826.003.0029 · Cited by 8
Self-citationMore police, less prison, less crime? From peel to popper
Neyroud, P. (2011) · Criminology & Public Policy · doi:10.1111/j.1745-9133.2010.00682.x · Cited by 7
“They suggest that the work of Berk, Sherman, Barnes, Kurtz, and Ahlman (2009) might be demonstrating such a process.”
Missed Officer–Probationer Contacts and Its Influence on Rearrest
Zettler, H. R., & Medina, J. C. (2019) · Criminal Justice Policy Review · doi:10.1177/0887403419828092 · Cited by 7
The presence of alcohol consumption prior to homicide in Singapore
Yeo, D. C. K., Singham, T., & Poremski, D. (2019) · Asian Journal of Psychiatry · doi:10.1016/j.ajp.2019.07.019 · Cited by 7
Ratcliffe, J. H. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108278423.016 · Cited by 7
Predicting Violence in Merseyside: a Network-Based Approach Using No Demographic Information
Campana, P., & Giovannetti, A. (2020) · Cambridge Journal of Evidence-Based Policing · doi:10.1007/s41887-020-00053-0 · Cited by 7
“Compared to previous models predicting high vs. low-risk of offending (e.g. Berk et al. 2009), these models are far less controversial.”
ResultEvidence-Based Triage in Prosecuting Arrestees
Neyroud, P. (2015) · International Criminal Justice Review · doi:10.1177/1057567715576173 · Cited by 7
“All of the evaluated programs had a clinical model of triage (Berk et al., 2009; Kahneman, 2011; Sherman, 2013).”
BackgroundMethodInfluentialSherman, L. W. (2012) · doi:10.18235/0009924 · Cited by 7
Self-citationDocument Title: Classifying Adult Probationers by Forecasting Future Offending
Barnes, G. C., & Hyatt, J. M. (2012) · Cited by 7
Self-citationLife-Course-Persistent Offenders
Bushway, S. D. (2012) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780199747238.013.0010 · Cited by 6
Algorithmic Legal Reasoning as Racializing Assemblages
Dixon‐Román, E. J., Nyame-Mensah, A., & Russell, A. R. (2018) · Cited by 6
Predicting Recidivism of Juvenile Offenders
Kalist, D. E., Lee, D. Y., & Spurr, S. J. (2014) · The B E Journal of Economic Analysis & Policy · doi:10.1515/bejeap-2013-0188 · Cited by 6
Obeying Signals and Predicting Future Offending
Piquero, A. R. (2012) · Criminology & Public Policy · doi:10.1111/j.1745-9133.2012.00787.x · Cited by 5
“Berk et al. (2009) offered one potential example, forecasting murder among Philadelphia probationers and parolees, which offers a way of concentrating resources on those offenders with the greatest needs.”
Making the Decision to Extend Probation Supervision at a Local Agency
Medina, J. C. (2016) · Crime & Delinquency · doi:10.1177/0011128716674702 · Cited by 5
“Often, partitioning continues until there are no more splits of the data that can improve the model fit (Berk et al., 2009).”
BackgroundMethodInfluentialForecasting for Police Officer Safety: A Demonstration of Concept
Cunningham, B. C., Coldren, J. R., Carleton, B., Berk, R. A., & Bauer, V. (2024) · Cambridge Journal of Evidence-Based Policing · doi:10.1007/s41887-023-00094-1 · Cited by 10
“Young males can be especially dangerous (Berk et al., 2009).”
Self-citationMasías, V. H., Valle, M. A., Amar, J. J. A., Cervantes, M., Brunal, G., & Crespo, F. (2016) · Journal of Investigative Psychology and Offender Profiling · doi:10.1002/jip.1451 · Cited by 5
Modeling the Referral Decision in Sexual Assault Cases: An Application of Random Forests
Snodgrass, G. M., Rosay, A. B., & Gover, A. R. (2013) · American Journal of Criminal Justice · doi:10.1007/s12103-013-9210-x · Cited by 5
A fairness scale for real-time recidivism forecasts using a national database of convicted offenders
Verrey, J., Neyroud, P., Sherman, L., & Ariel, B. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11478-x · Cited by 6
Self-citationBalancing the Costs of Forecasting Errors in Parole Decisions
Berk, R. A. (2010) · Albany law review · Cited by 4
Self-citationA Multi-Site Study of Firearms Displays by Police at Use of Force Incidents
Cubitt, T. I. C., & Nix, J. (2022) · Police Quarterly · doi:10.1177/10986111221136230 · Cited by 4
“, 2021) and high-harm offense types (Berk et al., 2009; Cubitt & Morgan, 2022).”
InfluentialHyatt, J. M. (2013) · Scholarly Commons (University of Pennsylvania) · Cited by 3
Predictive analytics for policy and practice: reflections from the criminal justice system
Hughes, T. (2015) · Policy Quarterly · doi:10.26686/pq.v11i2.4537 · Cited by 3
“For example, consider the Berk et al. (2009) tool for predicting the likelihood of murder described earlier.”
MethodInfluentialMultisubstance-Using Probationers and the Odds of Arrest While in the Community
Medina, J. C., & Zettler, H. R. (2019) · International Journal of Offender Therapy and Comparative Criminology · doi:10.1177/0306624x19895975 · Cited by 3
“Calculation of the risk score accounted for the probationers’ criminal history (Berk et al., 2009).”
BackgroundMethodAn Open Source Replication of a Winning Recidivism Prediction Model
Circo, G. M., & Wheeler, A. P. (2022) · International Journal of Offender Therapy and Comparative Criminology · doi:10.1177/0306624x221133004 · Cited by 3
“A second methodological innovation is the use of more complicated modeling strategies, such as using non-linear machine learning models, to improve predictions (Berk et al., 2009).”
Forecasting Gang Homicides with Multi-level Multi-task Learning
Akhter, N., Zhao, L., Arias, E. D., Rangwala, H., & Ramakrishnan, N. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-93372-6_3 · Cited by 3
“[13] studied murder rates among probationers and parolees.”
BackgroundFleetpower: Creating Virtual Power Plants in Sustainable Smart Electricity MarketsPreprint
Kahlen, M., Ketter, W., & Gupta, A. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3062433 · Cited by 3
Machine Learning Can Predict Shooting Victimization Well Enough to Help Prevent It
Heller, S., Jakubowski, B., Jelveh, Z., & Kapustin, M. (2024) · The Review of Economics and Statistics · doi:10.1162/rest_a_01519 · Cited by 2
Offender Desistance Policing (ODP): Less Prison and More Evidence in Rehabilitating Offenders
Sherman, L. W. (2011) · ANU Open Research (Australian National University) · Cited by 2
Self-citationHernandez-Meier, J., Akert, B., Zheng, C., Guse, C. E., Layde, P. M., & Hargarten, S. W. (2019) · Injury Prevention · doi:10.1136/injuryprev-2018-042996 · Cited by 2
Coglianese, C., & Lai, A. (2022) · doi:10.51868/10 · Cited by 2
The Fall and Rise of Racial Inequality in London Homicides: a Challenge for Policing by Consent
Kumar, S., Sherman, L. W., & Strang, H. (2022) · Cambridge Journal of Evidence-Based Policing · doi:10.1007/s41887-022-00084-9 · Cited by 2
Self-citationHope, T., & Shahaf, D. (2018) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3159652.3159670 · Cited by 2
“S states in 2005 were re-arrested within 3 years [15]. Recently, statistical learning methods have been used for risk assessments attempting to predict the danger an offender would pose after release [1] to inform sentencing decisions. We use two datasets with cohorts of inmates released in 1978 (N = 9327) and 1980 (N…”
MethodMcFadzien, K., & Sherman, L. W. (2021) · Policing An International Journal · doi:10.1108/pijpsm-04-2021-0061 · Cited by 2
Self-citationCriminology: Development and Current Status of the Discipline
Wellford, C. F. (2015) · Elsevier eBooks · doi:10.1016/b978-0-08-097086-8.45052-x · Cited by 2
Smart Market-Driven Virtual Power Plants of Shared Electric Vehicles
Kahlen, M., Schroer, K., Ketter, W., & Gupta, A. (2023) · Applied innovation and technology management · doi:10.1007/978-3-031-39707-3_11 · Cited by 1
Artificial intelligence as a tool for detecting deception in 911 homicide calls
Markey, P. M., Goldman, S., Dapice, J., Saj, S., Ceynek, S., Nicolas, T., & Trollip, L. (2024) · Journal of Criminal Justice · doi:10.1016/j.jcrimjus.2024.102337 · Cited by 1
Criminal Justice Predictors of Child Sexual Abuse Live Streaming
Cubitt, T. I. C., Napier, S. S., & Brown, R. (2025) · Victims & Offenders · doi:10.1080/15564886.2025.2550641 · Cited by 1
“Random forests increasingly feature in the study of crime due to their predictive power and strength in managing complex datasets (Berk et al., 2009).”
A globally optimal algorithm for hotspot detection and ranking
Boldt, M. (2026) · Crime Science · doi:10.1186/s40163-026-00269-x · Cited by 1
“Spatio-temporal point process models (Johnson et al., 2007; Piza & Carter, 2018) also capture repeat and near-repeat effects, while generalized linear and additive models (Kennedy et al., 2011; Wang et al., 2016, 2012), Random Forests (Berk et al., 2008), and deep learning methods (Stec & Klabjan, 2018; Wang et al., 2…”
Some Important Background Material
Berk, R. A. (2018) · Springer eBooks · doi:10.1007/978-3-030-02272-3_2 · Cited by 1
Self-citationA dynamic factor model to predict homicides with firearm in the United States
Ramallo, S., Maximo Camacho, Y., Marín, M. R., & Porfiri, M. (2023) · Journal of Criminal Justice · doi:10.1016/j.jcrimjus.2023.102051 · Cited by 3
RISK ASSESSMENT OF ECONOMIC ORGANISED CRIME IN UKRAINE
Korystin, O. Y., Kardashevskyi, Y., & Baskov, V. (2024) · Baltic Journal of Economic Studies · doi:10.30525/2256-0742/2024-10-1-122-135 · Cited by 1
Can Police Prioritize Highest Risks of Harm Among 6670 Children Exposed to Domestic Abuse?
Featherstone, A. M., Barnes, G. C., & O’Connor, D. (2018) · Cambridge Journal of Evidence-Based Policing · doi:10.1007/s41887-018-0026-2 · Cited by 1
Self-citationBland, M., & Ariel, B. (2020) · Springer eBooks · doi:10.1007/978-3-030-54843-8_4 · Cited by 1
The nature, detection, and avoidance of harmful discrimination in criminal justice
O’Flaherty, B., Sethi, R., & Williams, M. C. (2023) · Journal of Policy Analysis and Management · doi:10.1002/pam.22527 · Cited by 1
Wheeler, A. P., Worden, R. E., & Silver, J. R. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3122636 · Cited by 2
Clipper, S. J., & Selby, C. (2021) · The Encyclopedia of Research Methods in Criminology and Criminal Justice · doi:10.1002/9781119111931.ch94 · Cited by 1
Oleson, J. C. (2021) · Oxford University Press eBooks · doi:10.1093/obo/9780195396607-0296 · Cited by 1
Behavioural Analytics in Policing Data-Driven Offender Management: Assessing the Evidence Base
Babuta, A. (2022) · doi:10.36828/xvqy0381 · Cited by 1
Schultheis, E. (2024) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2024-16001 · Cited by 1
Some Important Background Material
Berk, R. A. (2012) · SpringerBriefs in computer science · doi:10.1007/978-1-4614-3085-8_2
Self-citationDeveloping the actuarial prediction of violent and sexual reoffending
Howard, P. D. (2014) · University of Birmingham Institutional Research Archive (University of Birmingham)
Seed, P. T. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0905.0116
“Berk et al. (2009) present an approach they have themselves developed: “statistical learning by random forests” (SLRF) for forecasting rare events that are difficult to predict.”
The Ecology of the Reentry Process: A Gendered Analysis of Community Influences
Alper, M. E. (2014) · University Libraries (University of Maryland) · doi:10.13016/m24591
“Berk et al. (2009) forecasted the risk of homicide or attempted homicide among a sample of probationers and parolees in Philadelphia and found that the number of people residing in the offender’s zip code, median household income in the zip code, and the proportion of the population in the zip code that is African Ame…”
Seed, P. T. (2009) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1111/j.1467-985x.2009.00622_1.x
“…The use of cost information when defining critical values for prediction of rare events by using logistic regression and similar methods Berk et al. (2009) have presented an approach that they have themselves developed: ‘statistical learning by random forests’ (SLRF) for forecasting…”
MethodDelil Temelli Hüküm Olarak Onarıcı Adalet
Sherman, L. W., Strang, H., & Bekar, E. (2014) · DergiPark (Istanbul University)
Self-citationColeman, R. (2016) · University of Liverpool · doi:10.17638/03004579
Ballpark Crowdsourcing: The Wisdom of Rough Group ComparisonsPreprint
Hope, T., & Shahaf, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.04828
“S states in 2005 were re-arrested within 3 years [15]. Recently, statistical learning methods have been used for risk assessments attempting to predict the danger an offender would pose after release [1] to inform sentencing decisions. We use two datasets with cohorts of inmates released in 1978 (N = 9327) and 1980 (N…”
MethodKey Questions That Police Data Might Help Us Answer
Bland, M., & Ariel, B. (2020) · Springer eBooks · doi:10.1007/978-3-030-54843-8_3
Using Classification Trees to Link Serial Crimes
Mugford, R. (2016) · doi:10.22215/etd/2016-11258
Loeffler, C. E., & Grunwald, B. (2013) · SSRN Electronic Journal · doi:10.2139/ssrn.2375982
Bland, M., & Ariel, B. (2020) · Springer eBooks · doi:10.1007/978-3-030-54843-8_1
Duwe, G. (2015) · The Encyclopedia of Crime and Punishment · doi:10.1002/9781118519639.wbecpx211
(2017) · Les Presses de l'Université de Montréal eBooks · doi:10.4000/books.pum.11502
Bland, M., & Ariel, B. (2020) · Springer eBooks · doi:10.1007/978-3-030-54843-8_8
Machine Learning Can Predict Shooting Victimization Well Enough to Help Prevent ItPreprint
Heller, S., Jakubowski, B., Jelveh, Z., & Kapustin, M. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4140888
Delahoz-Domínguez, E., Carrillo-Naranjo, J., Camelo-Guarín, A., & Zuluaga-Ortiz, R. A. (2023) · Intelligent Data Analysis · doi:10.3233/ida-216397
Framework for Prediction of Depression Among Adolescents Using Machine Learning
Chiurunge, P., & Kandiero, A. (2023) · Advances in healthcare information systems and administration book series · doi:10.4018/978-1-6684-8337-4.ch015
Big Data: correlations and causality (criminal law aspect)
RADUTNYI, O. (2023) · INFORMATION AND LAW · doi:10.37750/2616-6798.2023.2(45).282328
Sexual risk orders as a tactic to counter sexual violence against women and girls
Whitten, D., Neyroud, E., & Neyroud, P. (2025) · Cambridge Journal of Evidence-Based Policing · doi:10.1007/s41887-024-00097-6
“For example random forests machine learning (Breiman, 2001) has demonstrable predictive efficacy (Berk et al., 2009; Oswald et al., 2018).”
Singh, N. K., Silayach, N., Ray, R. K., & Dash, D. P. (2025) · American Journal of Economics and Sociology · doi:10.1111/ajes.12627
Leveraging Technology-Driven Nudging for Decision-Making in Criminal Justice - Expert Perspectives
Jayathilake, H. M., Asadi, A. R., Akinremi, T. P., Appiah, J. K., Ibitoye, O. O., & Said, H. (2025) · Issues in Informing Science and Information Technology · doi:10.28945/5508
“However, these AI-assisted tools are underutilized, raising serious questions regarding human rights (Berk et al., 2009; Gans-Combe, 2022) .”
Three Essays on Crime and Delinquency: Immigration, Alcohol, and Probation
Han, S. (2014) · ScholarlyCommons (University of Pennsylvania)
Additional file 1 of A machine learning analysis of serious misconduct among Australian police
Cubitt, T. I. C., Wooden, K., & Roberts, K. A. (2020) · Figshare · doi:10.6084/m9.figshare.13174004
Cubitt, T. (2026) · Springer eBooks · doi:10.1007/978-3-032-14070-8_2
The impact of error on offender risk classification
Ho, A. (2013) · Rutgers University Community Repository (Rutgers University) · doi:10.7282/t3p849h1
“Richard Berk and colleagues (Sherman, Barnes, Kurtz, and Lindsay) identified new predictors to risk that, in combination, are reported to be more accurate and predictive than existing risk devices (Berk et al., 2009).”
Background
Metadata
- Authors
- Berk, R., Sherman, L., Barnes, G., Kurtz, E., & Ahlman, L.
- Affiliations
- University of Pennsylvania (US)
- University of Cambridge (GB)
- First Judicial District of Pennsylvania , Philadelphia , USA
- Corresponding author
- Berk, Richard
- Venue
- Journal of the Royal Statistical Society Series A: Statistics in Society
- Publisher
- Oxford University Press (OUP)
- Published
- 2008-07-24
- Volume
- 172
- Issue
- 1
- Pages
- 191-211
- ISSN
- 0964-1998 (ISSN-L)
- 1467-985X
- OpenAlex
- W2038763866
- Cited by
- 178
- References
- 51
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 6 · 2023: 10 · 2022: 13 · 2021: 6 · 2020: 12 · 2019: 14 · 2018: 13 · 2017: 12 · 2016: 16 · 2015: 9 · 2014: 7 · 2013: 15 · 2012: 16
- FWCI
- 24.22
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Journal of the Royal Statistical Society Series A (Statistics in Society) (publishedVersion)
- Funders
- National Science Foundation (SES-0437169)
- Topics
- Social Sciences › Sociology and Political Science › Criminal Justice and Corrections Analysis
- Social Sciences › Psychology › Clinical Psychology › Psychopathy, Forensic Psychiatry, Sexual Offending
- Social Sciences › Law › Criminal Justice and Penology
- Keywords
- probationers, parolees, recidivism, statistical learning, community supervision, sentencing guidelines, resource allocation, Philadelphia
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
