{
 "bundle_of": "C3",
 "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": "C3",
   "statement": "When [[D3:point forecasts of the mean]] are compared over series on different scales, each series' [[D5:RMSE]] should be scaled by the in-sample RMSE of its one-step naive forecast, for example, as in [[D6:RMSSE]].",
   "about": {
    "subject": "D5",
    "relation": "should be scaled per series, when compared over",
    "object": "D3",
    "comparator": null,
    "conditions": [
     "series on different scales"
    ]
   },
   "type": "methodological",
   "role": "principal",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "argument",
     "warrant": "W3"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H93",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "depends_on": [
    "C47",
    "C29",
    "C46"
   ],
   "scope": {
    "data_type": "point forecasts of the mean, over series on different scales"
   },
   "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": "C29",
   "statement": "Squared error is a [[D1:consistent scoring function]] for the mean.",
   "about": {
    "subject": "squared error",
    "relation": "is consistent for",
    "object": "the mean",
    "comparator": null,
    "conditions": []
   },
   "type": "methodological",
   "role": "supporting",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "cited",
     "reference": "B2",
     "locator": "Section 5 (Discussion); Theorem 3.1 (arXiv:0912.0902 numbering)"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H36",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "ext": {
    "review": {
     "extracts": [
      {
       "reference": "B2",
       "locator": "Section 5 (Discussion); Theorem 3.1 (arXiv:0912.0902 numbering)",
       "lab_event": "XT1",
       "exact": "the squared error scoring function is consistent for the mean",
       "prefix": "businesses and organi-\nzations, ",
       "suffix": ", and the absolute error\nscoring",
       "start": 74674,
       "end": 74735,
       "artefact": "A1"
      }
     ],
     "kind": "summary"
    }
   },
   "scope": {
    "data_type": "point forecasts"
   },
   "limitations": [
    "L3",
    "L5"
   ],
   "verifiability": "open",
   "verifiability_flags": []
  },
  {
   "id": "C46",
   "statement": "Scaled errors, as in [[D8:MASE]], are independent of the scale of the data and can be averaged over series on different scales.",
   "about": {
    "subject": "D8",
    "relation": "can be averaged over",
    "object": "series on different scales",
    "comparator": null,
    "conditions": []
   },
   "type": "methodological",
   "role": "supporting",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "cited",
     "reference": "B6",
     "locator": "Abstract; Section 3 (Scaled errors)"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H53",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "ext": {
    "review": {
     "extracts": [
      {
       "reference": "B6",
       "locator": "Abstract; Section 3 (Scaled errors)",
       "lab_event": "XT19",
       "exact": "we propose that the mean absolute scaled error become the standard measure for\ncomparing forecast accuracy across multiple time series",
       "prefix": "ccurring situ-\nations. Instead, ",
       "suffix": ".\n\n\n\nKeywords: forecast accuracy",
       "start": 840,
       "end": 974,
       "artefact": "A7"
      }
     ],
     "kind": "summary"
    }
   },
   "scope": {
    "data_type": "error measures over series on different scales"
   },
   "limitations": [
    "L3",
    "L5"
   ],
   "verifiability": "open",
   "verifiability_flags": []
  },
  {
   "id": "C47",
   "statement": "The M5 accuracy competition scored point forecasts with the [[D6:RMSSE]]: each series' squared errors divided by the in-sample mean squared error of its one-step naive forecast.",
   "about": {
    "subject": "D6",
    "relation": "scored point forecasts in",
    "object": "the M5 accuracy competition",
    "comparator": null,
    "conditions": []
   },
   "type": "methodological",
   "role": "supporting",
   "novelty": "synthesis",
   "support": [
    {
     "kind": "cited",
     "reference": "B1",
     "locator": "Point forecasts"
    },
    {
     "kind": "cited",
     "reference": "B9"
    }
   ],
   "provenance": "author_stated",
   "hypothesis": {
    "lab_event": "H54",
    "outcome": "supported"
   },
   "planning": "exploratory",
   "ext": {
    "review": {
     "extracts": [
      {
       "reference": "B1",
       "locator": "Point forecasts",
       "lab_event": "XT20",
       "exact": "The accuracy of the point forecasts will be evaluated using the Root Mean Squared Scaled Error (RMSSE)",
       "prefix": "ce-\nprogram\n\n5\n\fPoint forecasts\n",
       "suffix": ",\nwhich is a variant of the well",
       "start": 14467,
       "end": 14569,
       "artefact": "A9"
      },
      {
       "reference": "B1",
       "locator": "Point forecasts",
       "lab_event": "XT21",
       "exact": "The measure is scale independent, meaning that it can be effectively used to compare forecasts\n        across series with different scales",
       "prefix": "optimized for the mean.\n       ",
       "suffix": ".\n       In contrast to other m",
       "start": 16197,
       "end": 16335,
       "artefact": "A9"
      }
     ],
     "kind": "summary"
    }
   },
   "scope": {
    "data_type": "point forecasts in the M5 accuracy competition"
   },
   "limitations": [
    "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"
  },
  {
   "id": "D3",
   "term": "point forecast of the mean",
   "kind": "concept",
   "definition": "A single-valued forecast meant to equal the mean (expected value) of the outcome's distribution given the information available.",
   "source": "B2"
  },
  {
   "id": "D5",
   "term": "RMSE",
   "kind": "variable",
   "definition": "Root mean squared error: the square root of the mean of the squared differences between outcomes and point forecasts.",
   "source": "B6"
  },
  {
   "id": "D6",
   "term": "RMSSE",
   "kind": "variable",
   "definition": "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": "B9"
  },
  {
   "id": "D8",
   "term": "MASE",
   "kind": "variable",
   "definition": "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": "B6"
  }
 ],
 "warrants": [
  {
   "id": "W3",
   "reasoning": "deductive",
   "premises": [
    "C47",
    "C29",
    "C46"
   ],
   "text": "Dividing a series' squared errors by a fixed positive number, such as the in-sample mean squared error of its one-step naive forecast, does not change which forecast minimises their expected value, so the scaled RMSE (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."
  }
 ],
 "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"
  },
  {
   "id": "A7",
   "kind": "data",
   "version": "sha256:b86b2d78457b62195faa87e2071beb3cacea2d6cb413c296dab746b00bb90a80",
   "description": "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.",
   "uri": "https://robjhyndman.com/papers/mase.pdf",
   "availability": {
    "level": "author_only",
    "reason": "legal",
    "content_hash": "sha256:b86b2d78457b62195faa87e2071beb3cacea2d6cb413c296dab746b00bb90a80"
   },
   "reference": "B6"
  },
  {
   "id": "A9",
   "kind": "data",
   "version": "sha256:f2650a2dbfb14d2c7d4482bda66c129ce5eec9341a76b76a833219559bf17109",
   "description": "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.",
   "uri": "https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf",
   "availability": {
    "level": "author_only",
    "reason": "legal",
    "content_hash": "sha256:f2650a2dbfb14d2c7d4482bda66c129ce5eec9341a76b76a833219559bf17109"
   },
   "reference": "B1"
  }
 ],
 "references": [
  {
   "id": "B1",
   "target": "https://github.com/Mcompetitions/M5-methods/blob/master/M5-Competitors-Guide.pdf",
   "id_type": "url",
   "ext": {
    "review": {
     "read": "full_text",
     "version": "other",
     "checked_on": "2026-11-13",
     "artefact": "A9",
     "lab_event": "SC9"
    }
   }
  },
  {
   "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": "B6",
   "target": "10.1016/j.ijforecast.2006.03.001",
   "id_type": "doi",
   "ext": {
    "review": {
     "read": "full_text",
     "version": "author_copy",
     "checked_on": "2026-11-13",
     "artefact": "A7",
     "lab_event": "SC7"
    }
   }
  },
  {
   "id": "B9",
   "target": "10.1016/j.ijforecast.2021.11.013",
   "id_type": "doi",
   "ext": {
    "review": {
     "read": "full_text",
     "checked_on": "2026-11-13",
     "lab_event": "SC11"
    }
   }
  }
 ]
}
