{
 "bundle_of": "C18",
 "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": "C18",
   "statement": "With rare positive cases, the [[D23:precision-recall curve]] should be reported rather than the ROC curve alone.",
   "about": {
    "subject": "D23",
    "relation": "is more informative than the ROC curve for",
    "object": "classifiers",
    "comparator": null,
    "conditions": [
     "imbalanced classes"
    ]
   },
   "type": "methodological",
   "role": "principal",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "argument",
     "warrant": "W18"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H77",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "depends_on": [
    "C43"
   ],
   "scope": {
    "data_type": "binary classifiers",
    "conditions": [
     "imbalanced classes"
    ]
   },
   "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": "C43",
   "statement": "On imbalanced data, the [[D23:precision-recall curve]] is more informative than the ROC curve for evaluating binary classifiers.",
   "about": {
    "subject": "D23",
    "relation": "is more informative than",
    "object": "the ROC curve",
    "comparator": null,
    "conditions": [
     "imbalanced data"
    ]
   },
   "type": "methodological",
   "role": "supporting",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "cited",
     "reference": "B7",
     "locator": "Title"
    },
    {
     "kind": "cited",
     "reference": "B7",
     "locator": "Abstract"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H50",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "ext": {
    "review": {
     "extracts": [
      {
       "reference": "B7",
       "locator": "Title",
       "lab_event": "XT15",
       "exact": "The Precision-Recall Plot Is More Informative\n                                                          than the ROC Plot When Evaluating Binary\n                                                          Classifiers on Imbalanced Datasets",
       "prefix": "                                ",
       "suffix": "\n                               ",
       "start": 135,
       "end": 372,
       "artefact": "A8"
      },
      {
       "reference": "B7",
       "locator": "Abstract",
       "lab_event": "XT16",
       "exact": "can be deceptive",
       "prefix": " context of imbalanced datasets ",
       "suffix": " with respect to conclu-\nROC Plo",
       "start": 2381,
       "end": 2397,
       "artefact": "A8"
      }
     ],
     "kind": "summary"
    }
   },
   "scope": {
    "data_type": "binary classifiers on imbalanced data"
   },
   "limitations": [
    "L5"
   ],
   "verifiability": "open",
   "verifiability_flags": []
  }
 ],
 "definitions": [
  {
   "id": "D23",
   "term": "precision-recall curve",
   "kind": "concept",
   "definition": "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": "B7"
  }
 ],
 "warrants": [
  {
   "id": "W18",
   "reasoning": "deductive",
   "premises": [
    "C43"
   ],
   "text": "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."
  }
 ],
 "limitations": [
  {
   "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": "A8",
   "kind": "data",
   "version": "sha256:8ae56333b46ffae705ec463b6a3dd1d81bc4fe5934e5e13a635e4bbf401d1a97",
   "description": "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.",
   "uri": "https://entrylib.org/p/2026.000008/v2/files/lab/sources/SR8/saito-rehmsmeier2015.pdf",
   "availability": {
    "level": "public"
   },
   "reference": "B7",
   "licence": "CC-BY-4.0"
  }
 ],
 "references": [
  {
   "id": "B7",
   "target": "10.1371/journal.pone.0118432",
   "id_type": "doi",
   "ext": {
    "review": {
     "read": "full_text",
     "version": "published",
     "checked_on": "2026-11-13",
     "artefact": "A8",
     "lab_event": "SC8"
    }
   }
  }
 ]
}
