You are reading a research paper published on EntryLib as separate claims, each with its evidence. How to read this page

Version 1 · 14 November 2026 · Management Science and Operations Research

This is version 1. The current version is 2.

Evaluating forecasts and classifiers: which measures, scoring rules and tests to use

Responsible researcher: Ivan Svetunkov (0000-0001-7826-0281)

CC-BY-4.0 · Keywords: forecast evaluation, scoring rules, error measures, classifier evaluation, literature review · Extensions: review 0.1

Contributions
  • Claude Code · literature summary (AI agent): Investigation, Writing – original draft
  • Ivan Svetunkov (0000-0001-7826-0281): Conceptualization, Supervision, Validation

Made with claimset-lab.

Text file for AI

Text file: the whole paper as plain text, to attach when your assistant cannot open the address.

The message

Read https://entrylib.org/p/[email protected], a research paper written as claims with their evidence. Give me a brief summary of its main findings and how well each is supported. If you cannot open the link, tell me instead of guessing. Then wait for my questions.

Summary

How should a study measure and compare predictions? This review states what the methodological literature establishes and the rules it draws from it. A measure has to match what a prediction targets: squared error (RMSE) for forecasts of the mean, absolute error (MAE) for the median, the pinball loss for a quantile, the interval score with coverage for intervals, CRPS or the log score for distributions, and log loss or the Brier score for class probabilities. MAPE rewards forecasts that are too low, sMAPE prefers forecasts that are too high, and AUC and accuracy do not judge probabilities. Errors of series on different scales should be scaled per series before they are averaged, never summed as they are. The mean, median and quartiles of a scaled measure summarise accuracy over many series; rank-based tests (Friedman with Nemenyi, MCB) and the Diebold-Mariano test tell whether similar methods differ statistically.

Highlights

Context

Extends Gneiting (2011) · from C1
Gneiting (2011) shows that a scoring function must be consistent for the functional a point forecast targets for the evaluation to reward that forecast.
Extends Gneiting (2011) · from C2
Gneiting (2011) shows that squared error is consistent for the mean.
Extends https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf · from C3
The M5 competition scored point forecasts by the RMSSE, chosen because squared errors are optimised for the mean and the scaling makes series comparable.
Extends Gneiting (2011) · from C4
Gneiting (2011) shows that absolute error is consistent for the median.
Extends Gneiting (2011) · from C5
Gneiting (2011) shows that the absolute percentage error is consistent for the median of order -1, which supports underforecasts.
Extends Goodwin and Lawton (1999) · from C6
Goodwin and Lawton (1999) show that the symmetric MAPE is not symmetric in its treatment of positive and negative errors of the same size.
Extends Hyndman and Koehler (2006) · from C7
Hyndman and Koehler (2006) propose the MASE as the standard measure across series.
Extends https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf · from C8
The M5 guide states that on intermittent series absolute errors favour forecasts close to zero.
Extends Gneiting (2011) · from C9
Gneiting (2011) shows that a scoring function is consistent for a quantile if and only if it is generalized piecewise linear.
Extends Gneiting and Raftery (2007) · from C10
Gneiting and Raftery (2007) show that the interval score is proper for central prediction intervals.
Extends Gneiting and Raftery (2007) · from C11
Gneiting and Raftery (2007) propose the interval score because it addresses width as well as coverage.
Extends Gneiting and Raftery (2007) · from C12
Gneiting and Raftery (2007) show that the CRPS and the logarithmic score are proper.
Extends Gneiting et al. (2007) · from C13
Gneiting, Balabdaoui and Raftery (2007) evaluate predictive distributions by maximising sharpness subject to calibration.
Extends Kolassa (2016) · from C14
Kolassa (2016) evaluates predictive count distributions with proper scoring rules and a randomised probability integral transform.
Extends Gneiting and Raftery (2007) · from C15
Gneiting and Raftery (2007) show that the Brier and logarithmic scores are strictly proper.
Extends Hand (2009) · from C17
Hand (2009) shows that the AUC measures different classifiers with different misclassification cost distributions.
Extends Saito and Rehmsmeier (2015) · from C18
Saito and Rehmsmeier (2015) show that the precision-recall plot is more informative than the ROC plot on imbalanced data.
Extends Kolassa (2020) · from C19
Kolassa (2020) shows that different error measures are minimised by different summaries of one predictive density.
Extends https://jmlr.org/papers/v7/demsar06a.html · from C20
Demsar (2006) notes that averages over data sets are susceptible to outliers.
Extends https://jmlr.org/papers/v7/demsar06a.html · from C21
Demsar (2006) recommends the Friedman test with post-hoc tests to test whether several classifiers differ over many data sets.
Extends Koning et al. (2005) · from C22
Koning et al. (2005) test the M3 results with multiple comparisons with the best on ranks.
Extends Diebold and Mariano (1995) · from C23
Diebold and Mariano (1995) propose a test of equal accuracy of two forecasts.
Extends Kolassa (2020) · from C24
Kolassa (2020), on the M4 measures, argues that the best point forecast depends on the error measure.
Extends Hyndman and Koehler (2006) · from C25
Hyndman and Koehler (2006) state that scale-dependent measures should not be used to compare across data sets on different scales.
Extends Hyndman and Koehler (2006) · from C26
Hyndman and Koehler (2006) propose scaled errors as the standard approach for comparing accuracy across series on different scales.
Extends https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf · from C27
The M5 competition scored quantile forecasts with the pinball loss scaled per series.
Extends Makridakis et al. (2020) · from C28
The M4 competition scored prediction intervals with the mean scaled interval score.
Extends Gneiting (2011) · from C29
Gneiting (2011) shows that squared error is consistent for the mean.
Extends Gneiting (2011) · from C30
Gneiting (2011) shows that the scoring function must be consistent for the functional a point forecast targets for the evaluation to reward that forecast.
Extends Gneiting (2011) · from C31
Gneiting (2011) shows that absolute error is consistent for the median.
Extends Gneiting (2011) · from C32
Gneiting (2011) shows that the absolute percentage error is consistent for the median of order -1, which supports underforecasts.
Extends Goodwin and Lawton (1999) · from C33
Goodwin and Lawton (1999) show that the symmetric MAPE treats positive and negative errors of the same size differently.
Extends Gneiting (2011) · from C34
Gneiting (2011) shows that a scoring function is consistent for a quantile if and only if it is generalized piecewise linear.
Extends Gneiting and Raftery (2007) · from C35
Gneiting and Raftery (2007) propose the interval score, proper for central intervals, which addresses width as well as coverage.
Extends Gneiting and Raftery (2007) · from C36
Gneiting and Raftery (2007) show that the CRPS is proper.
Extends Gneiting and Raftery (2007) · from C37
Gneiting and Raftery (2007) show that the logarithmic score is strictly proper.
Extends Gneiting and Raftery (2007) · from C38
Gneiting and Raftery (2007) show that the Brier score is proper.
Extends Gneiting et al. (2007) · from C39
Gneiting, Balabdaoui and Raftery (2007) evaluate predictive distributions by maximising sharpness subject to calibration.
Extends Kolassa (2016) · from C40
Kolassa (2016) assesses predictive count distributions with a randomised probability integral transform.
Extends https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf · from C41
The M5 guide states that on intermittent series absolute errors favour forecasts close to zero.
Extends Hand (2009) · from C42
Hand (2009) shows that the AUC measures different classifiers with different misclassification cost distributions.
Extends Saito and Rehmsmeier (2015) · from C43
Saito and Rehmsmeier (2015) show that the precision-recall plot is more informative than the ROC plot on imbalanced data.
Extends Hyndman and Koehler (2006) · from C44
Hyndman and Koehler (2006) state that scale-dependent measures should not be used to compare across data sets on different scales.
Extends Athanasopoulos and Kourentzes (2023) · from C45
Athanasopoulos and Kourentzes (2023) show how unscaled errors summed over series are dominated by the series with the largest values.
Extends Hyndman and Koehler (2006) · from C46
Hyndman and Koehler (2006) propose scaled errors as the standard approach for comparing accuracy across series on different scales.
Extends https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf · from C47
The M5 guide defines the RMSSE and scores point forecasts with it.
Extends https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf · from C48
The M5 guide defines the scaled pinball loss and scores quantile forecasts with it.
Extends Makridakis et al. (2020) · from C49
The M4 competition scored prediction intervals with the mean scaled interval score.
Extends https://jmlr.org/papers/v7/demsar06a.html · from C50
Demsar (2006) notes that averages over data sets are susceptible to outliers.
Extends https://jmlr.org/papers/v7/demsar06a.html · from C51
Demsar (2006) recommends the Friedman test with post-hoc tests for comparing several classifiers over many data sets.
Extends Koning et al. (2005) · from C52
Koning et al. (2005) test the M3 results with multiple comparisons with the best on ranks.
Extends Diebold and Mariano (1995) · from C53
Diebold and Mariano (1995) propose a test of equal accuracy of two forecasts.

Definitions

Methods 4

D25 Friedman test: A non-parametric test of whether several methods differ, applied to their ranks on each of several data sets. Source: https://jmlr.org/papers/v7/demsar06a.html.

D26 Nemenyi test: A post-hoc test after the Friedman test that compares every pair of methods by their mean ranks against a critical difference. Source: https://jmlr.org/papers/v7/demsar06a.html.

D27 MCB: Multiple comparisons with the best: a test, on mean ranks over series, of which methods differ significantly from the best-ranked one. Source: Koning et al. (2005).

D28 Diebold-Mariano test: A test of equal expected loss of two competing forecasts of the same series, based on the mean loss differential and its long-run variance. Source: Diebold and Mariano (1995).

Data 1

D24 intermittent series: A time series with many zero values, such as the sales of a slow-moving item. Source: Kolassa (2016).

Variables and measures 14

D5 RMSE: Root mean squared error: the square root of the mean of the squared differences between outcomes and point forecasts. Source: Hyndman and Koehler (2006).

D6 RMSSE: Root mean squared scaled error: the RMSE of a series' forecasts divided by the in-sample RMSE of the one-step naive forecast of that series, so that series on different scales can be averaged. Source: Makridakis et al. (2022a).

D7 MAE: Mean absolute error: the mean of the absolute differences between outcomes and point forecasts. Source: Hyndman and Koehler (2006).

D8 MASE: Mean absolute scaled error: the MAE of a series' forecasts divided by the in-sample MAE of the one-step naive forecast of that series. Source: Hyndman and Koehler (2006).

D9 MAPE: Mean absolute percentage error: the mean of the absolute differences between outcomes and point forecasts, each divided by the outcome. Source: Hyndman and Koehler (2006).

D10 sMAPE: Symmetric mean absolute percentage error: the mean of the absolute differences between outcomes and point forecasts, each divided by the mean of the absolute outcome and the absolute forecast. Source: Goodwin and Lawton (1999).

D12 pinball loss: The quantile (asymmetric piecewise linear) loss at level tau: tau times the error when the outcome is above the forecast, and (1 - tau) times the absolute error when it is below. Source: Gneiting (2011).

D13 interval score: The score of a central (1 - alpha) prediction interval: its width plus 2/alpha times the distance by which the outcome falls outside it. Source: Gneiting and Raftery (2007).

D14 coverage: The share of outcomes that fall inside the prediction intervals, compared with their nominal level. Source: Gneiting and Raftery (2007).

D15 CRPS: Continuous ranked probability score: the integral over thresholds of the squared difference between the forecast's cumulative distribution function and the step function at the outcome. Source: Gneiting and Raftery (2007).

D16 log score: The logarithmic score: the negative logarithm of the forecast density (or probability) at the outcome. Source: Gneiting and Raftery (2007).

D17 Brier score: The mean squared difference between forecast probabilities of a class and the outcome coded 1 if the class occurred and 0 otherwise. Source: BRIER (1950).

D21 accuracy: The share of cases whose predicted class, after thresholding the predicted probabilities, equals the observed class.

D22 AUC: The area under the ROC curve: the probability that a randomly chosen case of the positive class receives a higher score than a randomly chosen case of the negative class. Source: Hand (2009).

Concepts 9

D1 consistent scoring function: A scoring function (an error measure for point forecasts) is consistent for a functional of the predictive distribution, such as the mean, the median or a quantile, when its expected value is lowest when the point forecast equals that functional. Source: Gneiting (2011).

D2 proper scoring rule: A scoring rule for probabilistic forecasts is proper when its expected value is best when the forecast distribution equals the distribution of the outcome, and strictly proper when it is best only then. Source: Gneiting and Raftery (2007).

D3 point forecast of the mean: A single-valued forecast meant to equal the mean (expected value) of the outcome's distribution given the information available. Source: Gneiting (2011).

D4 point forecast of the median: A single-valued forecast meant to equal the median of the outcome's distribution given the information available. Source: Gneiting (2011).

D11 median of order -1: The beta-median with beta = -1: the point forecast that minimises the expected absolute percentage error; for positive outcomes it lies below the median. Source: Gneiting (2011).

D18 probability integral transform: The value of the forecast's cumulative distribution function at the outcome; for a calibrated forecast its values are uniformly distributed. Source: Gneiting et al. (2007).

D19 calibration: Statistical consistency between forecast distributions and outcomes: events forecast with a given probability occur with that frequency. Source: Gneiting et al. (2007).

D20 sharpness: The concentration of the forecast distributions, a property of the forecasts alone; among calibrated forecasts, sharper ones are better. Source: Gneiting et al. (2007).

D23 precision-recall curve: The curve of precision (the share of predicted positives that are positive) against recall (the share of positives predicted as positive) over the classification thresholds. Source: Saito and Rehmsmeier (2015).

Principal claims

SupportS 79C1 · methodological · novelty: extends earlier work, by the authors

Point forecasts should be evaluated with a consistent scoring function for the functional they target, such as the mean, the median or a quantile.

SupportS 79C2 · methodological · novelty: extends earlier work, by the authors

Point forecasts of the mean should be evaluated with squared error, as in RMSE.

SupportS 79C3 · methodological · novelty: extends earlier work, by the authors

When point forecasts of the mean are compared over series on different scales, each series' RMSE should be scaled by the in-sample RMSE of its one-step naive forecast, as in RMSSE.

SupportS 80C4 · methodological · novelty: extends earlier work, by the authors

MAE and MASE should not be the main measure for point forecasts of the mean.

SupportS 80C5 · methodological · novelty: extends earlier work, by the authors

MAPE should not be the measure for point forecasts of the mean or the median.

SupportS 79C6 · methodological · novelty: extends earlier work, by the authors

sMAPE should not be the measure for point forecasts.

SupportS 80C7 · methodological · novelty: extends earlier work, by the authors

Point forecasts of the median should be evaluated with absolute error, as in MAE or, across series on different scales, MASE.

SupportS 79C8 · methodological · novelty: extends earlier work, by the authors

On intermittent series, absolute-error measures should not be used alone.

SupportS 80C9 · methodological · novelty: extends earlier work, by the authors

Quantile forecasts should be evaluated with the pinball loss at the quantile's level, averaged over the levels when there are several.

SupportS 80C10 · methodological · novelty: extends earlier work, by the authors

Prediction intervals should be evaluated with the interval score, reported together with their coverage against the nominal level.

SupportS 80C11 · methodological · novelty: extends earlier work, by the authors · in question: close match on EntryLib not acknowledged

Coverage alone should not be the measure of prediction intervals.

SupportS 80C12 · methodological · novelty: extends earlier work, by the authors

Predictive distributions should be evaluated with a proper scoring rule, such as the CRPS or the log score.

SupportS 80C13 · methodological · novelty: extends earlier work, by the authors

The evaluation of predictive distributions should check their calibration and report their sharpness.

SupportS 74C14 · methodological · novelty: extends earlier work, by the authors

Predictive distributions of counts, such as forecasts of intermittent sales, should be evaluated with proper scoring rules and a randomised probability integral transform.

SupportS 79C15 · methodological · novelty: extends earlier work, by the authors

Forecast probabilities of classes should be evaluated with a proper scoring rule, such as the log score or the Brier score.

SupportS 67C16 · methodological · novelty: new, by the authors

Accuracy should not be the measure of forecast class probabilities.

SupportS 64C17 · methodological · novelty: extends earlier work, by the authors

AUC should not be the measure of forecast class probabilities.

SupportS 81C18 · methodological · novelty: extends earlier work, by the authors

With rare positive cases, the precision-recall curve should be reported rather than the ROC curve alone.

SupportS 79C19 · methodological · novelty: extends earlier work, by the authors

When the compared methods target different functionals, one the mean and another the median, each should be evaluated with a measure consistent for its own target, or the methods made to target the same functional.

SupportS 80C20 · methodological · novelty: extends earlier work, by the authors

When methods are compared over many series, their accuracy should be summarised by the mean, the median and the quartiles of a scaled measure across the series, such as RMSSE or MASE.

SupportS 81C21 · methodological · novelty: extends earlier work, by the authors

To tell whether several methods whose aggregate accuracy is similar differ statistically significantly over many series or data sets, their ranks on each series should be tested with the Friedman test followed by Nemenyi test post-hoc comparisons.

SupportS 75C22 · methodological · novelty: extends earlier work, by the authors

To tell which methods differ statistically significantly from the best one over many series, multiple comparisons with the best (MCB) on ranks should be used.

SupportS 75C23 · methodological · novelty: extends earlier work, by the authors

The accuracy of two forecasts of the same series should be compared with the Diebold-Mariano test.

SupportS 79C24 · methodological · novelty: extends earlier work, by the authors

That a competition or a well-known study used an error measure should not be the reason for choosing it.

SupportS 74C25 · methodological · novelty: extends earlier work, by the authors

Scale-dependent error measures, such as RMSE and MAE, should not be summed or averaged across series on different scales.

SupportS 79C26 · methodological · novelty: extends earlier work, by the authors

To aggregate the accuracy of point forecasts over series on different scales, each series' errors should first be scaled by a quantity of that series that does not depend on the compared forecasts, such as the in-sample error of its one-step naive forecast in MASE or RMSSE, before the scaled errors are averaged.

SupportS 79C27 · methodological · novelty: extends earlier work, by the authors

When quantile forecasts are compared over series on different scales, each series' pinball loss should be scaled by a quantity of that series.

SupportS 74C28 · methodological · novelty: extends earlier work, by the authors

When prediction intervals are compared over series on different scales, each series' interval score should be scaled by a quantity of that series.

Supporting claims

SupportS 93C29 · methodological · novelty: extends earlier work, by the authors

Squared error is a consistent scoring function for the mean.

SupportS 92C30 · methodological · novelty: extends earlier work, by the authors

Which point forecast has the lowest expected score depends on the scoring function: a consistent scoring function for a functional, such as the mean or a quantile, is lowest in expectation for the forecast that equals that functional of the outcome's distribution.

SupportS 93C31 · methodological · novelty: extends earlier work, by the authors

Absolute error is a consistent scoring function for the median.

SupportS 93C32 · methodological · novelty: extends earlier work, by the authors

The absolute percentage error averaged by MAPE is consistent for the median of order -1, a functional that supports severe underforecasts compared with the mean or the median.

SupportS 92C33 · methodological · novelty: extends earlier work, by the authors

For the same outcome, sMAPE penalises a forecast below the outcome more heavily than a forecast above it.

SupportS 93C34 · methodological · novelty: extends earlier work, by the authors

The pinball loss at a level is a consistent scoring function for the quantile at that level.

SupportS 93C35 · methodological · novelty: extends earlier work, by the authors

The interval score is a proper scoring rule for central prediction intervals that addresses both their width and their coverage.

SupportS 93C36 · methodological · novelty: extends earlier work, by the authors

The CRPS is a proper scoring rule for predictive distributions of continuous outcomes.

SupportS 93C37 · methodological · novelty: extends earlier work, by the authors

The log score is a strictly proper scoring rule.

SupportS 92C38 · methodological · novelty: extends earlier work, by the authors

The Brier score is a proper scoring rule for forecast probabilities of classes.

SupportS 93C39 · methodological · novelty: extends earlier work, by the authors

Predictive distributions are assessed by maximising their sharpness subject to their calibration.

SupportS 78C40 · methodological · novelty: extends earlier work, by the authors

The calibration of predictive distributions of counts can be assessed with a randomised probability integral transform.

SupportS 93C41 · methodological · novelty: extends earlier work, by the authors

On intermittent series, absolute-error measures give their best scores to forecasts close to zero.

SupportS 67C42 · methodological · novelty: extends earlier work, by the authors

The AUC is equivalent to averaging the misclassification loss over a distribution of misclassification costs that depends on the classifier.

SupportS 94C43 · methodological · novelty: extends earlier work, by the authors

On imbalanced data, the precision-recall curve is more informative than the ROC curve for evaluating binary classifiers.

SupportS 93C44 · methodological · novelty: extends earlier work, by the authors

Scale-dependent error measures, such as RMSE and MAE, cannot be compared across series on different scales.

SupportS 78C45 · methodological · novelty: extends earlier work, by the authors

When the errors of series on different scales are summed or averaged without scaling, the series with the largest values dominate the result.

SupportS 93C46 · methodological · novelty: extends earlier work, by the authors

Scaled errors, as in MASE, are independent of the scale of the data and can be averaged over series on different scales.

SupportS 93C47 · methodological · novelty: extends earlier work, by the authors

The M5 accuracy competition scored point forecasts with the RMSSE: each series' squared errors divided by the in-sample mean squared error of its one-step naive forecast.

SupportS 93C48 · methodological · novelty: extends earlier work, by the authors

The M5 uncertainty competition scored quantile forecasts with the scaled pinball loss: each series' pinball loss divided by the in-sample mean absolute error of its one-step naive forecast.

SupportS 78C49 · methodological · novelty: extends earlier work, by the authors

The M4 competition scored prediction intervals with the mean scaled interval score: the interval score of each series scaled by an in-sample error of that series.

SupportS 94C50 · methodological · novelty: extends earlier work, by the authors

Averages of a performance measure over many data sets are susceptible to outliers.

SupportS 94C51 · methodological · novelty: extends earlier work, by the authors

The Friedman test, followed by the Nemenyi test, compares several methods over many data sets by their ranks on each data set, assuming only limited commensurability of the measure across data sets.

SupportS 78C52 · methodological · novelty: extends earlier work, by the authors

MCB on ranks was used to test the differences between the methods of the M3 competition.

SupportS 78C53 · methodological · novelty: extends earlier work, by the authors

The Diebold-Mariano test of equal accuracy of two forecasts allows forecast errors that are serially correlated and not normally distributed.

Evidence

W1 · argument · deductive · premises C30

A forecast is built to target one functional, and only a scoring function consistent for that functional is lowest in expectation for it; a scoring function consistent for another functional ranks forecasts by how close they come to that other functional.

W2 · argument · deductive · premises C29, C30

Squared error is consistent for the mean, so its expected value is lowest for the forecast that equals the mean; the RMSE, the square root of the mean squared error, ranks forecasts in the same order.

W3 · argument · deductive · premises C47, C29, C46

Dividing a series' squared errors by a fixed positive number, the in-sample mean squared error of its one-step naive forecast, does not change which forecast minimises their expected value, so the RMSSE keeps the target of the RMSE, the mean, and the scaled values of different series can be averaged, as in the M5 accuracy competition.

W4 · argument · deductive · premises C31, C29

Absolute error, which MAE averages and MASE scales, is consistent for the median, not the mean; on skewed outcomes the two differ, and these measures then rank a median forecast above a forecast that is correct for the mean.

W5 · argument · deductive · premises C32

MAPE is consistent for the median of order -1, which supports severe underforecasts compared with the mean or the median; it therefore rewards forecasts that are too low for either target.

W6 · argument · deductive · premises C33

sMAPE penalises forecasts below the outcome more heavily than forecasts above it, so it rewards forecasts that are too high; and it divides by the mean of the absolute outcome and the absolute forecast, which is zero when both are zero, so it is then undefined.

W7 · argument · deductive · premises C31, C46

Absolute error is consistent for the median, so its expected value is lowest for the median forecast; MASE divides each series' absolute errors by a fixed in-sample quantity, which keeps that target and lets series on different scales be averaged.

W8 · argument · deductive · premises C41, C31

On intermittent series the median of the outcome can be zero, and absolute error, consistent for the median, then gives its best score to a forecast of zero in every period; a measure of the mean or of the whole distribution shows what such a forecast misses.

W9 · argument · deductive · premises C34

The pinball loss at a level is consistent for the quantile at that level, so its expected value is lowest for the correct quantile; averaging over the levels gives each quantile the same weight.

W10 · argument · deductive · premises C35

The interval score is proper for central intervals and addresses width as well as coverage; coverage against the nominal level shows how far the intervals' calibration departs from what they claim.

W11 · argument · deductive · premises C35

Coverage counts only whether each outcome falls inside its interval; widening an interval never lowers its coverage, so coverage alone cannot penalise needless width, which the interval score does.

W12 · argument · deductive · premises C36, C37

The CRPS and the log score are proper: their expected values are best for the true distribution, so they never reward a forecaster for reporting a distribution other than the one believed.

W13 · argument · deductive · premises C39

Predictive distributions are assessed by maximising their sharpness subject to calibration; checking calibration, with the probability integral transform or coverage at several levels, and reporting sharpness show how a forecast fails, which a single score does not.

W14 · argument · deductive · premises C40, C36, C37

The probability integral transform of a discrete distribution takes few values and is not uniform even when the forecast is calibrated, so the calibration of count forecasts is checked with the randomised transform; proper scoring rules apply to count distributions as to any other.

W15 · argument · deductive · premises C38, C37

The Brier score is proper and the log score strictly proper, so both are best in expectation for the true probabilities of the classes.

W16 · argument · deductive · premises C38, C37

Accuracy uses a forecast probability only through which side of a threshold it falls, and counts every misclassification as the same loss; two forecasts with different probabilities but the same thresholded labels score the same, and unequal costs of errors are not reflected. The Brier and log scores, which are proper, reward the probabilities themselves.

W17 · argument · deductive · premises C42

The AUC averages the misclassification loss over a cost distribution that depends on the classifier, so different classifiers are compared with different weightings of the costs of errors; and it depends only on how the scores rank cases, not on whether the probabilities are right.

W18 · argument · deductive · premises C43

On imbalanced data the ROC curve can be deceptive about how reliable a classifier is, and the precision-recall curve is the more informative of the two; reporting it shows what the ROC curve can hide.

W19 · argument · deductive · premises C30

Each scoring function is lowest in expectation for the functional it is consistent for, so one measure favours the methods that target that functional; comparing methods that target different functionals with one measure compares their targets, not their skill.

W20 · argument · deductive · premises C46, C50

A scaled measure can be averaged over series, but averages over many data sets are susceptible to outliers; the median and the quartiles show how accuracy is spread over the series, which the mean alone hides.

W21 · argument · deductive · premises C51

The Friedman test, followed by the Nemenyi test, compares methods by their ranks on each data set and assumes only limited commensurability of the measure across data sets; it tells whether differences between methods whose aggregate accuracy is close are larger than chance.

W22 · argument · deductive · premises C52

Multiple comparisons with the best on ranks test which methods differ from the best one, and were used for this on the methods of the M3 competition.

W23 · argument · deductive · premises C53

The Diebold-Mariano test allows forecast errors that are serially correlated and not normally distributed, as the errors of multi-step forecasts of one series usually are; tests that assume independent, normal errors do not hold for them.

W24 · argument · deductive · premises C30

A measure fits a study when it is consistent for what the compared methods predict; that a competition used a measure says nothing about whether it is consistent for the forecasts of this study.

W25 · argument · deductive · premises C44, C45

Scale-dependent measures cannot be compared across series on different scales, and summed or averaged without scaling they are dominated by the series with the largest values; the result then says little about accuracy on the other series.

W26 · argument · deductive · premises C44, C46, C47

Scaled errors are independent of the scale of the data and can be averaged over series; dividing by a quantity of the series that does not depend on the compared forecasts keeps the target that the unscaled measure is consistent for.

W27 · argument · deductive · premises C48, C34, C44

Pinball losses of series on different scales cannot be compared unscaled; dividing each series' pinball loss by a quantity of that series that does not depend on the forecasts keeps the quantile it is consistent for, as the scaled pinball loss of the M5 uncertainty competition does.

W28 · argument · deductive · premises C49, C35, C44

Interval scores of series on different scales cannot be compared unscaled; dividing each series' interval score by a positive quantity of that series that does not depend on the forecasts keeps it proper, as the mean scaled interval score of the M4 competition does.

Limitations

L1 · data quality · could reverse · affects C42, C17 · mitigation: none

These claims rest only on works checked by their abstracts and bibliographic records (Brier 1950, Hand 2009: lab notes NT7 and NT8); a full text could qualify what the abstract states.

L2 · data quality · reduces precision · affects C38 · mitigation: none

Part of the support of these claims comes from a work checked only by its abstract (Brier 1950, lab note NT7); the rest comes from works read in full.

L3 · measurement · reduces precision · affects C29, C30, C31, C32, C33, C34, C35, C36, C37, C38, C39, C44, C46 · mitigation: none

Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions.

L4 · other · could reverse · affects C16 · mitigation: none

No cited work states this recommendation or its reason; it rests on an argument from the definition of accuracy (its warrant), with the properness of the Brier and log scores as premises.

L5 · researcher position · could bias magnitude · affects C1, C2, C3, C4, C5, C6, C7, C8, C9, C10, C11, C12, C13, C14, C15, C16, C17, C18, C19, C20, C21, C22, C23, C24, C25, C26, C27, C28, C29, C30, C31, C32, C33, C34, C35, C36, C37, C38, C39, C40, C41, C42, C43, C44, C45, C46, C47, C48, C49, C50, C51, C52, C53 · mitigation: none

The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it.

L6 · data quality · reduces precision · affects C30, C33, C40, C41, C45, C47, C48, C49, C52, C53 · mitigation: none

These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves.

References

  1. Athanasopoulos, G., Kourentzes, N., 2023. On the evaluation of hierarchical forecasts. International Journal of Forecasting 39, 1502–1511. https://doi.org/10.1016/j.ijforecast.2022.08.003 Used by: C45, Context
  2. BRIER, G. W., 1950. VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITY. Monthly Weather Review 78, 1–3. https://doi.org/10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2 Used by: C38, D17
  3. Diebold, F. X., Mariano, R. S., 1995. Comparing Predictive Accuracy. Journal of Business &amp; Economic Statistics 13, 253–263. https://doi.org/10.1080/07350015.1995.10524599 Used by: Context, C53, D28
  4. Gneiting, T., 2011. Making and Evaluating Point Forecasts. Journal of the American Statistical Association 106, 746–762. https://doi.org/10.1198/jasa.2011.r10138 Used by: Context, C29, C30, C31, C32, C34, D1, D3, D4, D11, D12, A1
  5. Gneiting, T., Raftery, A. E., 2007. Strictly Proper Scoring Rules, Prediction, and Estimation. Journal of the American Statistical Association 102, 359–378. https://doi.org/10.1198/016214506000001437 Used by: Context, C35, C36, C37, C38, D2, D13, D14, D15, D16, A2
  6. Gneiting, T., Balabdaoui, F., Raftery, A. E., 2007. Probabilistic Forecasts, Calibration and Sharpness. Journal of the Royal Statistical Society Series B: Statistical Methodology 69, 243–268. https://doi.org/10.1111/j.1467-9868.2007.00587.x Used by: Context, C39, D18, D19, D20, A3
  7. Goodwin, P., Lawton, R., 1999. On the asymmetry of the symmetric MAPE. International Journal of Forecasting 15, 405–408. https://doi.org/10.1016/S0169-2070(99)00007-2 Used by: Context, C33, D10
  8. Hand, D. J., 2009. Measuring classifier performance: a coherent alternative to the area under the ROC curve. Machine Learning 77, 103–123. https://doi.org/10.1007/s10994-009-5119-5 Used by: Context, C42, D22
  9. Hyndman, R. J., Koehler, A. B., 2006. Another look at measures of forecast accuracy. International Journal of Forecasting 22, 679–688. https://doi.org/10.1016/j.ijforecast.2006.03.001 Used by: Context, C33, C44, C46, D5, D7, D8, D9, A7
  10. Kolassa, S., 2016. Evaluating predictive count data distributions in retail sales forecasting. International Journal of Forecasting 32, 788–803. https://doi.org/10.1016/j.ijforecast.2015.12.004 Used by: Context, C40, C41, D24
  11. Kolassa, S., 2020. Why the “best” point forecast depends on the error or accuracy measure. International Journal of Forecasting 36, 208–211. https://doi.org/10.1016/j.ijforecast.2019.02.017 Used by: Context, C30
  12. Koning, A. J., Franses, P. H., Hibon, M., Stekler, H. O., 2005. The M3 competition: Statistical tests of the results. International Journal of Forecasting 21, 397–409. https://doi.org/10.1016/j.ijforecast.2004.10.003 Used by: Context, C52, D27
  13. Makridakis, S., Spiliotis, E., Assimakopoulos, V., 2020. The M4 Competition: 100,000 time series and 61 forecasting methods. International Journal of Forecasting 36, 54–74. https://doi.org/10.1016/j.ijforecast.2019.04.014 Used by: Context, C49
  14. Makridakis, S., Spiliotis, E., Assimakopoulos, V., 2022a. M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting 38, 1346–1364. https://doi.org/10.1016/j.ijforecast.2021.11.013 Used by: C47, D6
  15. Makridakis, S., Spiliotis, E., Assimakopoulos, V., Chen, Z., Gaba, A., Tsetlin, I., Winkler, R. L., 2022b. The M5 uncertainty competition: Results, findings and conclusions. International Journal of Forecasting 38, 1365–1385. https://doi.org/10.1016/j.ijforecast.2021.10.009 Used by: C48
  16. Saito, T., Rehmsmeier, M., 2015. The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLOS ONE 10, e0118432. https://doi.org/10.1371/journal.pone.0118432 Used by: Context, C43, D23, A8
  17. https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf Used by: Context, C41, C47, C48, A9
  18. https://jmlr.org/papers/v7/demsar06a.html Used by: Context, C50, C51, D25, D26, A4

Artefacts

  • A1 · data · Gneiting (2011) Making and evaluating point forecasts (arXiv:0912.0902, the preprint of Gneiting 2011, JASA 106(494), 746-762, doi:10.1198/jasa.2011.r10138) (application/pdf), saved by hand on 2026-11-13; recorded in the lab record as SR1 on 2026-11-13. venue: arXiv. Written by others. 0912.0902
  • A2 · data · Gneiting and Raftery (2007) Strictly proper scoring rules, prediction, and estimation (Gneiting and Raftery 2007, JASA 102(477), 359-378, doi:10.1198/016214506000001437), author's copy (application/pdf), saved by hand on 2026-11-13; recorded in the lab record as SR2 on 2026-11-13. venue: Journal of the American Statistical Association. Written by others. Gneiting2007jasa.pdf
  • A3 · data · Gneiting et al. (2007) Probabilistic forecasts, calibration and sharpness (Gneiting, Balabdaoui and Raftery 2007, JRSS B 69(2), 243-268, doi:10.1111/j.1467-9868.2007.00587.x), author's copy (application/pdf), saved by hand on 2026-11-13; recorded in the lab record as SR3 on 2026-11-13. venue: Journal of the Royal Statistical Society B. Written by others. Gneiting2007jrssb.pdf
  • A4 · data · https://jmlr.org/papers/v7/demsar06a.html Statistical comparisons of classifiers over multiple data sets (Demsar 2006, JMLR 7, 1-30) (application/pdf), saved by hand on 2026-11-13; recorded in the lab record as SR4 on 2026-11-13. venue: Journal of Machine Learning Research. Written by others. demsar06a.pdf
  • A7 · data · Hyndman and Koehler (2006) Another look at measures of forecast accuracy (preprint of Hyndman and Koehler 2006, IJF 22(4), 679-688, doi:10.1016/j.ijforecast.2006.03.001) (application/pdf), saved by hand on 2026-11-13; recorded in the lab record as SR7 on 2026-11-13. venue: International Journal of Forecasting. Written by others. mase.pdf
  • A8 · data · Saito and Rehmsmeier (2015) The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets (Saito and Rehmsmeier 2015, PLoS ONE 10(3), e0118432, doi:10.1371/journal.pone.0118432) (application/pdf), saved by hand on 2026-11-13; recorded in the lab record as SR8 on 2026-11-13. venue: PLoS ONE; published: 2015-03-04. Written by others. saito-rehmsmeier2015.pdf
  • A9 · data · https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf The M5 Competition: Competitors' Guide (the organisers' definition of the RMSSE, the scaled pinball loss and the reasons for them) (application/pdf), saved by hand on 2026-11-13; recorded in the lab record as SR9 on 2026-11-13. venue: M Open Forecasting Center, GitHub repository Mcompetitions/M5-methods. Written by others. M5-Competitors-Guide.pdf
  • A10 · lab_record Lab record of the study: questions, hypotheses, plans, runs, results and decisions, as an append-only, hash-chained event log (Claimset lab record specification v0.22, begun 2026-11-13; exported with claimset 0.42.7). lab.jsonl

Score

Support of the paper: 78, Partly supported

Scores are computed by rules from the claimset file (EntryLib rubric 0.7): they check the record, not the science, and may change as the rubric and reviews develop. The rubric. Every issue as text, for an agent preparing the next version.

The mean of its 28 principal claims; the lowest is C17 at 64. Open problems in the principal claims and what they rest on, each counted once, with the most it costs a claim:

  1. −20 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. In C1, C2, C3, C4, C5, C6, C7, C8, C9, C10, C11, C12, C13, C14, C15, C16, C17, C18, C19, C20, C21, C22, C23, C24, C25, C26, C27, C28, C40, C42, C45, C49, C52, C53. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −10 Open problems Limitation L4 (could reverse, not mitigated): No cited work states this recommendation or its reason; it rests on an argument from the definition of accuracy (its warrant), with the properness of the Brier and log scores as premises. In C16. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −10 Open problems Limitation L1 (could reverse, not mitigated): These claims rest only on works checked by their abstracts and bibliographic records (Brier 1950, Hand 2009: lab notes NT7 and NT8); a full text could qualify what the abstract states. In C17, C42. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  4. −5 Context A principal claim related to no earlier work. In C16. To remove it: Relate the claim to the earlier work it extends, addresses or departs from.
  5. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. In C1, C2, C3, C4, C5, C6, C7, C8, C9, C10, C11, C12, C13, C14, C15, C16, C17, C18, C19, C20, C21, C22, C23, C24, C25, C26, C27, C28. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  6. −1 Open problems Limitation L2 (reduces precision, not mitigated): Part of the support of these claims comes from a work checked only by its abstract (Brier 1950, lab note NT7); the rest comes from works read in full. In C15, C16, C38. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  7. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. In C1, C2, C3, C4, C5, C6, C7, C8, C9, C10, C11, C12, C13, C14, C15, C16, C19, C20, C24, C25, C26, C27, C28, C29, C30, C31, C32, C33, C34, C35, C36, C37, C38, C39, C44, C46. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  8. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. In C1, C2, C3, C4, C5, C6, C7, C8, C9, C10, C11, C12, C13, C14, C15, C16, C17, C18, C19, C20, C21, C22, C23, C24, C25, C26, C27, C28, C29, C30, C31, C32, C33, C34, C35, C36, C37, C38, C39, C40, C41, C42, C43, C44, C45, C46, C47, C48, C49, C50, C51, C52, C53. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  9. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. In C1, C2, C3, C6, C8, C14, C19, C22, C23, C24, C25, C26, C27, C28, C30, C33, C40, C41, C45, C47, C48, C49, C52, C53. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

Claims

C1: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C2: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C3: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C4: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C5: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C6: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C7: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C8: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C9: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C10: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C11: 80, Well supported

Novelty: extends earlier work, by the authors · in question: close match on EntryLib not acknowledged

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C12: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C13: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C14: 74, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C15: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L2 (reduces precision, not mitigated): Part of the support of these claims comes from a work checked only by its abstract (Brier 1950, lab note NT7); the rest comes from works read in full. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C16: 67, Partly supported

Novelty: new, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −10 Open problems Limitation L4 (could reverse, not mitigated): No cited work states this recommendation or its reason; it rests on an argument from the definition of accuracy (its warrant), with the properness of the Brier and log scores as premises. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −5 Context A principal claim related to no earlier work. To remove it: Relate the claim to the earlier work it extends, addresses or departs from.
  4. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  5. −3 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  6. −1 Open problems Limitation L2 (reduces precision, not mitigated): Part of the support of these claims comes from a work checked only by its abstract (Brier 1950, lab note NT7); the rest comes from works read in full. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  7. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C17: 64, Partly supported

Novelty: extends earlier work, by the authors

  1. −20 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −10 Open problems Limitation L1 (could reverse, not mitigated): These claims rest only on works checked by their abstracts and bibliographic records (Brier 1950, Hand 2009: lab notes NT7 and NT8); a full text could qualify what the abstract states. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −3 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C18: 81, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.

C19: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C20: 80, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C21: 81, Well supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.

C22: 75, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C23: 75, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C24: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C25: 74, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C26: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C27: 79, Partly supported

Novelty: extends earlier work, by the authors

  1. −10 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C28: 74, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Plan The review's search for the literature: none is recorded; the claims were confirmed against works the authors knew. To remove it: Record the protocol, then the searches and the screening of what they found (claimset lab protocol, search, screen), and export them.
  4. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  5. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C29: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C30: 92, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C31: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C32: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C33: 92, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C34: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C35: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C36: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C37: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C38: 92, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L2 (reduces precision, not mitigated): Part of the support of these claims comes from a work checked only by its abstract (Brier 1950, lab note NT7); the rest comes from works read in full. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C39: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C40: 78, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C41: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C42: 67, Partly supported

Novelty: extends earlier work, by the authors

  1. −20 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −10 Open problems Limitation L1 (could reverse, not mitigated): These claims rest only on works checked by their abstracts and bibliographic records (Brier 1950, Hand 2009: lab notes NT7 and NT8); a full text could qualify what the abstract states. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −3 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C43: 94, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C44: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C45: 78, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C46: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L3 (reduces precision, not mitigated): Section and theorem numbers for Gneiting 2011, Gneiting and Raftery 2007, Gneiting, Balabdaoui and Raftery 2007 and Hyndman and Koehler 2006 were read in their preprints or authors' copies (arXiv:0912.0902 and the authors' web pages), whose numbering may differ from the published versions. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C47: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C48: 93, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  2. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C49: 78, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C50: 94, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C51: 94, Well supported

Novelty: extends earlier work, by the authors

  1. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C52: 78, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

C53: 78, Partly supported

Novelty: extends earlier work, by the authors

  1. −15 Evidence Rests on cited work only; cited work read in full, without the passage it rests on; an argument from other claims. To remove it: Support the claim with evidence the claimset records, citing the result entries or table rows it reports, or have its proof checked; for cited work, read the work in full and quote the passage the claim rests on from a captured copy (claimset extension review).
  2. −6 Open problems Limitation L5 (could bias magnitude, not mitigated): The claims restate EntryLib's study-planning guide on prediction, drafted by an agent of the same system that checked them here, and were stated before the works were read; the works were read to confirm what the guide states, and no search was run for work that disagrees with it. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.
  3. −1 Open problems Limitation L6 (reduces precision, not mitigated): These claims rest in part on works read in full by the guarantor, not by the agent that wrote the claimset (lab note NT14); no passage of those works is quoted, so a reader checks these claims against the works themselves. To remove it: Mitigate it with evidence, or narrow the claim's scope so that it no longer applies.

Versions

  • Version 2 · 14 November 2026 at 12:59 UTC · updated
  • Version 1 (this page) · 14 November 2026 at 09:28 UTC · active

Every version is kept in the public registry (github.com/entrylib/registry).