{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/regions-of-reliability-in-the-evaluation-of","title":"Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts","arxiv_id":"2304.09836","date":"2023-04-19","proceeding":null,"authors":["Étienne Marcotte","Valentina Zantedeschi","Alexandre Drouin","Nicolas Chapados"],"abstract":"Multivariate probabilistic time series forecasts are commonly evaluated via proper scoring rules, i.e., functions that are minimal in expectation for the ground-truth distribution. However, this property is not sufficient to guarantee good discrimination in the non-asymptotic regime. In this paper, we provide the first systematic finite-sample study of proper scoring rules for time-series forecasting evaluation. Through a power analysis, we identify the \"region of reliability\" of a scoring rule, i.e., the set of practical conditions where it can be relied on to identify forecasting errors. We carry out our analysis on a comprehensive synthetic benchmark, specifically designed to test several key discrepancies between ground-truth and forecast distributions, and we gauge the generalizability of our findings to real-world tasks with an application to an electricity production problem. Our results reveal critical shortcomings in the evaluation of multivariate probabilistic forecasts as commonly performed in the literature.","url_abs":"https://arxiv.org/abs/2304.09836v2","url_pdf":"https://arxiv.org/pdf/2304.09836v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"regions-of-reliability-in-the-evaluation-of","repo_url":"https://github.com/ServiceNow/regions-of-reliability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"},{"task_slug":"scoring-rule","task_name":"scoring rule"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.09836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09836"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ServiceNow/regions-of-reliability","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":19},"by_repo_kind":{"official":{"samples":19,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"571e637ac68c5e1d","entry":"compute_metrics_from_benchmark","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/benchmark_data.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/benchmark_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"571e637ac68c5e1d"}},{"code_sha256_prefix":"c764476c7f3110be","entry":"compute_metrics_single_experiment","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/benchmark_data.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/benchmark_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c764476c7f3110be"}},{"code_sha256_prefix":"653bfa7827b0a9c9","entry":"crps_quantile","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/crps.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/crps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"653bfa7827b0a9c9"}},{"code_sha256_prefix":"683b8dfe9350f6f8","entry":"crps_slow","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/crps.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/crps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"683b8dfe9350f6f8"}},{"code_sha256_prefix":"58cab579ed6bb634","entry":"dawid_sebastiani_score","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/dawid_sebastiani.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/dawid_sebastiani.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"58cab579ed6bb634"}},{"code_sha256_prefix":"ec34b47822b2cf32","entry":"energy_score","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/energy.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/energy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec34b47822b2cf32"}},{"code_sha256_prefix":"086d8758cc92c2f9","entry":"energy_score_fast","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/energy.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/energy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"086d8758cc92c2f9"}},{"code_sha256_prefix":"622a08d2aedbaeaa","entry":"exponential_cross_entropy","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/experiments/kl_divergence.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/experiments/kl_divergence.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"622a08d2aedbaeaa"}},{"code_sha256_prefix":"42eb1613132e5bd3","entry":"gaussian_cross_entropy","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/experiments/kl_divergence.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/experiments/kl_divergence.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42eb1613132e5bd3"}},{"code_sha256_prefix":"5b1713c369009179","entry":"gaussian_kl_divergence","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/experiments/kl_divergence.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/experiments/kl_divergence.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b1713c369009179"}},{"code_sha256_prefix":"e9707f076eb0fd4d","entry":"gaussian_mixture_wasserstein_distance","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/experiments/wasserstein.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/experiments/wasserstein.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e9707f076eb0fd4d"}},{"code_sha256_prefix":"86b1b5e8b1f99a49","entry":"gaussian_wasserstein_distance","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/experiments/wasserstein.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/experiments/wasserstein.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86b1b5e8b1f99a49"}},{"code_sha256_prefix":"a89c62ddaf8564cf","entry":"kernel_laplace","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/kernel.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/kernel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a89c62ddaf8564cf"}},{"code_sha256_prefix":"0d2316045e5123c8","entry":"kernel_laplace_spherical","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/kernel.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/kernel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d2316045e5123c8"}},{"code_sha256_prefix":"cf9541f4fe97a349","entry":"kernel_matern","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/kernel.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/kernel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf9541f4fe97a349"}},{"code_sha256_prefix":"ec4c5581d554fa67","entry":"select_params","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/experiments/h0_vs_h1.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/experiments/h0_vs_h1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec4c5581d554fa67"}},{"code_sha256_prefix":"7db8a498674767fb","entry":"variogram_score_iter","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/variogram.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/variogram.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7db8a498674767fb"}},{"code_sha256_prefix":"7a7e624a0059daf1","entry":"variogram_score_mixed","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/variogram.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/variogram.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a7e624a0059daf1"}},{"code_sha256_prefix":"b76e853f4dce8b7b","entry":"variogram_score_tensor","repo":"ServiceNow/regions-of-reliability","repo_kind":"official","path":"ror/metrics/variogram.py","file_url":"https://github.com/ServiceNow/regions-of-reliability/blob/HEAD/ror/metrics/variogram.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b76e853f4dce8b7b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}