{
 "bundle_of": "C19",
 "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": "C19",
   "statement": "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.",
   "about": {
    "subject": "the comparison of methods with different targets",
    "relation": "should use",
    "object": "measures consistent for each target",
    "comparator": null,
    "conditions": [
     "methods target different functionals"
    ]
   },
   "type": "methodological",
   "role": "principal",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "argument",
     "warrant": "W19"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H78",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "depends_on": [
    "C30"
   ],
   "scope": {
    "data_type": "point forecasts of methods that target different functionals"
   },
   "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": "C30",
   "statement": "Which point forecast has the lowest expected score depends on the scoring function: a [[D1: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.",
   "about": {
    "subject": "D1",
    "relation": "is lowest in expectation for",
    "object": "the forecast equal to its functional",
    "comparator": null,
    "conditions": []
   },
   "type": "methodological",
   "role": "supporting",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "cited",
     "reference": "B2",
     "locator": "Abstract (arXiv:0912.0902 numbering)"
    },
    {
     "kind": "cited",
     "reference": "B8"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H37",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "ext": {
    "review": {
     "extracts": [
      {
       "reference": "B2",
       "locator": "Abstract (arXiv:0912.0902 numbering)",
       "lab_event": "XT2",
       "exact": "it is critical that the\n                                         scoring function be consistent for it",
       "prefix": "ve in the form of a functional, ",
       "suffix": ", in the sense that the expected",
       "start": 2433,
       "end": 2535,
       "artefact": "A1"
      }
     ],
     "kind": "summary"
    }
   },
   "scope": {
    "data_type": "point forecasts"
   },
   "limitations": [
    "L3",
    "L5",
    "L6"
   ],
   "verifiability": "open",
   "verifiability_flags": []
  }
 ],
 "definitions": [
  {
   "id": "D1",
   "term": "consistent scoring function",
   "kind": "concept",
   "definition": "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": "B2"
  }
 ],
 "warrants": [
  {
   "id": "W19",
   "reasoning": "deductive",
   "premises": [
    "C30"
   ],
   "text": "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."
  }
 ],
 "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"
  },
  {
   "id": "L6",
   "category": "data_quality",
   "statement": "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.",
   "affects": [
    "C30",
    "C33",
    "C40",
    "C41",
    "C45",
    "C47",
    "C48",
    "C49",
    "C52",
    "C53"
   ],
   "impact": "reduces_precision",
   "mitigation": "none"
  }
 ],
 "artefacts": [
  {
   "id": "A1",
   "kind": "data",
   "version": "sha256:6b6cc2f0fd3daa1da42506f42f05fe88425880b2806f864ceaab85fc606ab5c9",
   "description": "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.",
   "uri": "https://arxiv.org/abs/0912.0902",
   "availability": {
    "level": "author_only",
    "reason": "legal",
    "content_hash": "sha256:6b6cc2f0fd3daa1da42506f42f05fe88425880b2806f864ceaab85fc606ab5c9"
   },
   "reference": "B2"
  }
 ],
 "references": [
  {
   "id": "B2",
   "target": "10.1198/jasa.2011.r10138",
   "id_type": "doi",
   "ext": {
    "review": {
     "read": "full_text",
     "version": "preprint",
     "checked_on": "2026-11-13",
     "artefact": "A1",
     "lab_event": "SC1"
    }
   }
  },
  {
   "id": "B8",
   "target": "10.1016/j.ijforecast.2019.02.017",
   "id_type": "doi",
   "ext": {
    "review": {
     "read": "full_text",
     "checked_on": "2026-11-13",
     "lab_event": "SC10"
    }
   }
  }
 ]
}
