{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H4YUJQ4BFZPQQ6SIIXESWML2O4","short_pith_number":"pith:H4YUJQ4B","schema_version":"1.0","canonical_sha256":"3f3144c3812e5f087a4845c92b317a77390e9ef9b9553dd609648838673bb63a","source":{"kind":"arxiv","id":"2605.16075","version":1},"attestation_state":"computed","paper":{"title":"REX-SUB: A Scalable Subsampling Strategy for Modeling Large Spatial Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ME","authors_text":"Ben Seiyon Lee, Nicholas Rios","submitted_at":"2026-05-15T15:35:42Z","abstract_excerpt":"Recent advances in data collection technologies have led to the emergence of massive spatial datasets, with measurements obtained at millions of spatial locations. Geostatistical models typically employ Gaussian processes (GPs) to capture spatial dependence, but standard GP fitting becomes prohibitive at such scales. A promising solution is optimal subsampling, where a subset of locations is selected that optimizes a criterion. In this study, we propose a randomized exchange algorithm for subsampling (REX-SUB) which efficiently selects small subsamples that minimize prediction errors in the fi"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.16075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-15T15:35:42Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"07cd2524e306545ddf415da49adf1543b9cf1907ca6a175b35972569d9725fd0","abstract_canon_sha256":"3590dd169b14a7a51143d610a9c2c0e19265ef3f11ee34952013b6d859931b6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:51.568054Z","signature_b64":"k/XNxB3wICYhikM7EcOlEQmXHrhtit4VtnG9/IksKMfaFLXAuhMh4+yTfY7nnQrPy91WnqjLX+u6Ae8ITqBoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f3144c3812e5f087a4845c92b317a77390e9ef9b9553dd609648838673bb63a","last_reissued_at":"2026-05-20T00:01:51.567296Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:51.567296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REX-SUB: A Scalable Subsampling Strategy for Modeling Large Spatial Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ME","authors_text":"Ben Seiyon Lee, Nicholas Rios","submitted_at":"2026-05-15T15:35:42Z","abstract_excerpt":"Recent advances in data collection technologies have led to the emergence of massive spatial datasets, with measurements obtained at millions of spatial locations. Geostatistical models typically employ Gaussian processes (GPs) to capture spatial dependence, but standard GP fitting becomes prohibitive at such scales. A promising solution is optimal subsampling, where a subset of locations is selected that optimizes a criterion. In this study, we propose a randomized exchange algorithm for subsampling (REX-SUB) which efficiently selects small subsamples that minimize prediction errors in the fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16075","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16075/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:41.540470Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.509587Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"eb13d5c995a0030264349ab2a1b21db6dbfb67bd3d82925d71dc0f3ecc11b28f"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2605.16075","created_at":"2026-05-20T00:01:51.567418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16075v1","created_at":"2026-05-20T00:01:51.567418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16075","created_at":"2026-05-20T00:01:51.567418+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4YUJQ4BFZPQ","created_at":"2026-05-20T00:01:51.567418+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4YUJQ4BFZPQQ6SI","created_at":"2026-05-20T00:01:51.567418+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4YUJQ4B","created_at":"2026-05-20T00:01:51.567418+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/H4YUJQ4BFZPQQ6SIIXESWML2O4","json":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4.json","graph_json":"https://pith.science/api/pith-number/H4YUJQ4BFZPQQ6SIIXESWML2O4/graph.json","events_json":"https://pith.science/api/pith-number/H4YUJQ4BFZPQQ6SIIXESWML2O4/events.json","paper":"https://pith.science/paper/H4YUJQ4B"},"agent_actions":{"view_html":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4","download_json":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4.json","view_paper":"https://pith.science/paper/H4YUJQ4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16075&json=true","fetch_graph":"https://pith.science/api/pith-number/H4YUJQ4BFZPQQ6SIIXESWML2O4/graph.json","fetch_events":"https://pith.science/api/pith-number/H4YUJQ4BFZPQQ6SIIXESWML2O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4/action/storage_attestation","attest_author":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4/action/author_attestation","sign_citation":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4/action/citation_signature","submit_replication":"https://pith.science/pith/H4YUJQ4BFZPQQ6SIIXESWML2O4/action/replication_record"}},"created_at":"2026-05-20T00:01:51.567418+00:00","updated_at":"2026-05-20T00:01:51.567418+00:00"}