{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K64RD2RUTZYFG5FTB2GGYHUCNO","short_pith_number":"pith:K64RD2RU","schema_version":"1.0","canonical_sha256":"57b911ea349e705374b30e8c6c1e826b88623b4700b7435a3c88c16054357554","source":{"kind":"arxiv","id":"2605.13689","version":1},"attestation_state":"computed","paper":{"title":"Moving beyond spatial and random cross-validation in environmental modelling: a call for prediction-domain adaptive evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Prediction-domain adaptive cross-validation provides reliable accuracy estimates across interpolation and extrapolation scenarios.","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Hanna Meyer, Jakub Nowosad, Jan Linnenbrink","submitted_at":"2026-05-13T15:42:40Z","abstract_excerpt":"With the growing application of spatial predictive modeling in ecology, the question of how to appropriately evaluate the resulting maps has gained increasing attention. While there is consensus that map accuracy is ideally estimated using an independent probability sample of the prediction area, there is still no agreement on the most appropriate way to conduct an evaluation for the common case when such a sample is not available.\n  Cross-validation, which involves multiple train-test splits, is commonly applied not only to estimate final model accuracy but also to guide model tuning and sele"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2026-05-13T15:42:40Z","cross_cats_sorted":[],"title_canon_sha256":"bdf8daa2283fd02103a94f875e9624a625d3da0c0647e8e68a8c7b6ce06c2afd","abstract_canon_sha256":"9ae2955b15f154cf020adec98f61fc0690388e534887e47ad2b2881db261c4ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.967561Z","signature_b64":"8fo2hpEMFZUAxk49nKYtd2FWomNpXZsuR5T/N39k2Ewfr/m4c6PVIJL9nciehuqnGz75DML1sKL7kb5G1gJXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57b911ea349e705374b30e8c6c1e826b88623b4700b7435a3c88c16054357554","last_reissued_at":"2026-05-18T02:44:16.967007Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.967007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moving beyond spatial and random cross-validation in environmental modelling: a call for prediction-domain adaptive evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Prediction-domain adaptive cross-validation provides reliable accuracy estimates across interpolation and extrapolation scenarios.","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Hanna Meyer, Jakub Nowosad, Jan Linnenbrink","submitted_at":"2026-05-13T15:42:40Z","abstract_excerpt":"With the growing application of spatial predictive modeling in ecology, the question of how to appropriately evaluate the resulting maps has gained increasing attention. While there is consensus that map accuracy is ideally estimated using an independent probability sample of the prediction area, there is still no agreement on the most appropriate way to conduct an evaluation for the common case when such a sample is not available.\n  Cross-validation, which involves multiple train-test splits, is commonly applied not only to estimate final model accuracy but also to guide model tuning and sele"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"To address this gap, we advocate for a new category of cross-validation methods to account for this: prediction-domain adaptive evaluation. Methods in this category flexibly adapt to the prediction situation, yielding most reliable estimates of map accuracy across different scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That practical methods belonging to the proposed prediction-domain adaptive category can be developed and will demonstrably outperform existing random and spatial cross-validation approaches in providing reliable accuracy estimates across the interpolation-extrapolation continuum.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Prediction-domain adaptive cross-validation is proposed as a flexible alternative to fixed random or spatial methods for reliably estimating accuracy in environmental maps.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Prediction-domain adaptive cross-validation provides reliable accuracy estimates across interpolation and extrapolation scenarios.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"eedd3ded26c16b9694e0600bf37b3527558b69c46e26ac6d429225f72526791a"},"source":{"id":"2605.13689","kind":"arxiv","version":1},"verdict":{"id":"9c061680-48bd-4a0c-b268-90f456063b32","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T17:49:23.597654Z","strongest_claim":"To address this gap, we advocate for a new category of cross-validation methods to account for this: prediction-domain adaptive evaluation. Methods in this category flexibly adapt to the prediction situation, yielding most reliable estimates of map accuracy across different scenarios.","one_line_summary":"Prediction-domain adaptive cross-validation is proposed as a flexible alternative to fixed random or spatial methods for reliably estimating accuracy in environmental maps.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That practical methods belonging to the proposed prediction-domain adaptive category can be developed and will demonstrably outperform existing random and spatial cross-validation approaches in providing reliable accuracy estimates across the interpolation-extrapolation continuum.","pith_extraction_headline":"Prediction-domain adaptive cross-validation provides reliable accuracy estimates across interpolation and extrapolation scenarios."},"references":{"count":45,"sample":[{"doi":"","year":2020,"title":"Nature Communications , author =","work_id":"fa3b9c24-9cf6-4a5a-b26e-09747308da75","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Nature Communications , author =","work_id":"7fbc10e1-2ebd-4ece-8bb7-3186b09bba6d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1111/2041-210x.13650","year":2041,"title":"Methods in Ecology and Evolution , volume =","work_id":"a08bf2ab-bc42-464f-9fb5-6ef41b32eded","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.ecolmodel.2021.109692","year":2021,"title":"Wadoux and Gerard B.M","work_id":"13be2481-08ad-49c5-8094-2812f1a588e0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/igarss.2012.6352393","year":2012,"title":"Brenning , title =","work_id":"e5bb9932-d5cd-439e-b3a6-10b7461df328","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":45,"snapshot_sha256":"1968b005caa7470327c2d08071eaa40025f6c4860af91189d5901e3f2147c6da","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.13689","created_at":"2026-05-18T02:44:16.967136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13689v1","created_at":"2026-05-18T02:44:16.967136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13689","created_at":"2026-05-18T02:44:16.967136+00:00"},{"alias_kind":"pith_short_12","alias_value":"K64RD2RUTZYF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"K64RD2RUTZYFG5FT","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"K64RD2RU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO","json":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO.json","graph_json":"https://pith.science/api/pith-number/K64RD2RUTZYFG5FTB2GGYHUCNO/graph.json","events_json":"https://pith.science/api/pith-number/K64RD2RUTZYFG5FTB2GGYHUCNO/events.json","paper":"https://pith.science/paper/K64RD2RU"},"agent_actions":{"view_html":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO","download_json":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO.json","view_paper":"https://pith.science/paper/K64RD2RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13689&json=true","fetch_graph":"https://pith.science/api/pith-number/K64RD2RUTZYFG5FTB2GGYHUCNO/graph.json","fetch_events":"https://pith.science/api/pith-number/K64RD2RUTZYFG5FTB2GGYHUCNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO/action/storage_attestation","attest_author":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO/action/author_attestation","sign_citation":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO/action/citation_signature","submit_replication":"https://pith.science/pith/K64RD2RUTZYFG5FTB2GGYHUCNO/action/replication_record"}},"created_at":"2026-05-18T02:44:16.967136+00:00","updated_at":"2026-05-18T02:44:16.967136+00:00"}