{
 "bundle_of": "C11",
 "schema_version": "0.43",
 "paper": {
  "id": "entrylib:2026.000008",
  "version": 2,
  "title": "Evaluating forecasts and classifiers: which measures, scoring rules and tests to use",
  "licence": "CC-BY-4.0",
  "status": "corrected",
  "date": "2026-11-14",
  "status_notice": {
   "date": "2026-11-14",
   "reason_code": "correction",
   "statement": "Version 1 labelled the review's findings and recommendations extension, with an extends relation to the very works cited as their evidence, which said they extend those works; they state what those works establish, so version 2 labels them synthesis (claimset v0.43) and drops those relations, keeping extension only for C16, the one rule that goes beyond its sources, which extends Gneiting and Raftery (2007); and, at the guarantor's request, it rewords C3 (RMSSE as an example of the scaling), C4 (MAE and MASE as the main measure only when the mean and median forecasts coincide), C8 (absolute-error measures avoided on intermittent series), C13 (sharpness compared only among calibrated distributions and intervals) and C24 (choose a measure for what the methods predict, even if precedent used another).",
   "issued_by": "Ivan Svetunkov (ORCID 0000-0001-7826-0281)"
  }
 },
 "extensions": {
  "review": "0.1"
 },
 "claims": [
  {
   "id": "C11",
   "statement": "[[D14:Coverage]] alone should not be the measure of prediction intervals.",
   "about": {
    "subject": "D14",
    "relation": "should not be the only measure of",
    "object": "prediction intervals",
    "comparator": null,
    "conditions": []
   },
   "type": "methodological",
   "role": "principal",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "argument",
     "warrant": "W11"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H70",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "depends_on": [
    "C35"
   ],
   "scope": {
    "data_type": "prediction intervals"
   },
   "ext": {
    "review": {
     "kind": "recommendation"
    }
   },
   "limitations": [
    "L5"
   ],
   "assessments": [
    {
     "by": "author",
     "strength": "high",
     "rationale": "Exploratory in the lab's terms: a literature claim, stated from the guide before its papers were read, then confirmed against them (the status of its hypothesis in the lab record); no test was planned or run. It follows by the argument of its warrant from findings that its works state, quoted from full texts or read in full by the guarantor."
    }
   ],
   "verifiability": "open",
   "verifiability_flags": []
  },
  {
   "id": "C35",
   "statement": "The [[D13:interval score]] is a [[D2:proper scoring rule]] for central prediction intervals that addresses both their width and their coverage.",
   "about": {
    "subject": "D13",
    "relation": "is proper for",
    "object": "central prediction intervals",
    "comparator": null,
    "conditions": []
   },
   "type": "methodological",
   "role": "supporting",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "cited",
     "reference": "B3",
     "locator": "Section 1 (Introduction)"
    },
    {
     "kind": "cited",
     "reference": "B3",
     "locator": "Abstract"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H89",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "ext": {
    "review": {
     "extracts": [
      {
       "reference": "B3",
       "locator": "Section 1 (Introduction)",
       "lab_event": "XT8",
       "exact": "a scoring rule for prediction intervals that is proper",
       "prefix": " the general idea dates back at\n",
       "suffix": " and has in-     least to Brier ",
       "start": 15726,
       "end": 15780,
       "artefact": "A2"
      },
      {
       "reference": "B3",
       "locator": "Abstract",
       "lab_event": "XT9",
       "exact": "propose the intuitively appealing interval score as a utility function in interval estimation that addresses width as well as\n           coverage",
       "prefix": "tile\n           estimation, and ",
       "suffix": ".\n           KEY WORDS: Bayes fa",
       "start": 2499,
       "end": 2644,
       "artefact": "A2"
      }
     ],
     "kind": "summary"
    }
   },
   "scope": {
    "data_type": "central prediction intervals"
   },
   "limitations": [
    "L3",
    "L5"
   ],
   "verifiability": "open",
   "verifiability_flags": []
  }
 ],
 "definitions": [
  {
   "id": "D2",
   "term": "proper scoring rule",
   "kind": "concept",
   "definition": "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": "B3"
  },
  {
   "id": "D13",
   "term": "interval score",
   "kind": "variable",
   "definition": "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": "B3"
  },
  {
   "id": "D14",
   "term": "coverage",
   "kind": "variable",
   "definition": "The share of outcomes that fall inside the prediction intervals, compared with their nominal level.",
   "source": "B3"
  }
 ],
 "warrants": [
  {
   "id": "W11",
   "reasoning": "deductive",
   "premises": [
    "C35"
   ],
   "text": "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."
  }
 ],
 "limitations": [
  {
   "id": "L3",
   "category": "measurement",
   "statement": "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.",
   "affects": [
    "C29",
    "C30",
    "C31",
    "C32",
    "C33",
    "C34",
    "C35",
    "C36",
    "C37",
    "C38",
    "C39",
    "C44",
    "C46"
   ],
   "impact": "reduces_precision",
   "mitigation": "none"
  },
  {
   "id": "L5",
   "category": "researcher_position",
   "statement": "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.",
   "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"
   ],
   "impact": "could_bias_magnitude",
   "mitigation": "none"
  }
 ],
 "artefacts": [
  {
   "id": "A2",
   "kind": "data",
   "version": "sha256:d31a0c5f0ae8fec1a0a6544db5d056645b2d7296d71b44a2e8efb293c7d87ba2",
   "description": "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.",
   "uri": "https://sites.stat.washington.edu/raftery/Research/PDF/Gneiting2007jasa.pdf",
   "availability": {
    "level": "author_only",
    "reason": "legal",
    "content_hash": "sha256:d31a0c5f0ae8fec1a0a6544db5d056645b2d7296d71b44a2e8efb293c7d87ba2"
   },
   "reference": "B3"
  }
 ],
 "references": [
  {
   "id": "B3",
   "target": "10.1198/016214506000001437",
   "id_type": "doi",
   "ext": {
    "review": {
     "read": "full_text",
     "version": "author_copy",
     "checked_on": "2026-11-13",
     "artefact": "A2",
     "lab_event": "SC2"
    }
   }
  }
 ]
}
