{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WB7CKQLJBAPIJJH5BSKCK7BYNK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ff86d3ac9c46bea35d3278ab689fd9397a5796373fc000b1fcbccd03fa32c1f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-11T12:31:45Z","title_canon_sha256":"a86378a977a3adc8bc6ea8319a0b28ec8aedc4a96b82a49d0ccbe8a4b423d2aa"},"schema_version":"1.0","source":{"id":"2312.06334","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06334","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06334v3","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06334","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"WB7CKQLJBAPI","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_16","alias_value":"WB7CKQLJBAPIJJH5","created_at":"2026-07-05T08:07:12Z"},{"alias_kind":"pith_short_8","alias_value":"WB7CKQLJ","created_at":"2026-07-05T08:07:12Z"}],"graph_snapshots":[{"event_id":"sha256:7e9f172269fc5b3280d9b67dfdf63464525d58fd7245f62695fad6a2b362cb2d","target":"graph","created_at":"2026-07-05T08:07:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.06334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalization to new samples is a fundamental rationale for statistical modeling. For this purpose, model validation is particularly important, but recent work in survey inference has suggested that simple aggregation of individual prediction scores does not give a good measure of the score for population aggregate estimates. In this manuscript we explain why this occurs, propose two scoring metrics designed specifically for this problem, and demonstrate their use in three different ways. We show that these scoring metrics correctly order models when compared to the true score, although they ","authors_text":"Aki Vehtari, Andrew Gelman, Lauren Kennedy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-11T12:31:45Z","title":"Model validation for aggregate inferences in out-of-sample prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06334","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b5c79b000b6a3f0990271554fd1daba5f3143457bd2fe435be321aa410e4616","target":"record","created_at":"2026-07-05T08:07:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ff86d3ac9c46bea35d3278ab689fd9397a5796373fc000b1fcbccd03fa32c1f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-11T12:31:45Z","title_canon_sha256":"a86378a977a3adc8bc6ea8319a0b28ec8aedc4a96b82a49d0ccbe8a4b423d2aa"},"schema_version":"1.0","source":{"id":"2312.06334","kind":"arxiv","version":3}},"canonical_sha256":"b07e254169081e84a4fd0c94257c386a98a947506eae9eba7457d89b12868b80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b07e254169081e84a4fd0c94257c386a98a947506eae9eba7457d89b12868b80","first_computed_at":"2026-07-05T08:07:12.480432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:12.480432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IZoYfddpMvRvEwCHE3/StqJOpafO27ig3ShLEPNhGaKiJMw9Cce2WMfXn0JNcYnt+F4PK8eb2J9tXP6lTZeYAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:12.480888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06334","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b5c79b000b6a3f0990271554fd1daba5f3143457bd2fe435be321aa410e4616","sha256:7e9f172269fc5b3280d9b67dfdf63464525d58fd7245f62695fad6a2b362cb2d"],"state_sha256":"cbecc2f8f950530c024e4b137c9e6617dbb2ac116b7c81cef0477a882635d634"}