{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XJZU2DOEFZNF66WZQJETEDXXS4","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":"af8aa1e14263cf32762fdd949cb3d4684e98a2ef126962900a35e2e89460969a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-07T06:44:14Z","title_canon_sha256":"a3f3ad09030ed1c1c4f8277a0750c0143adb628aff9e6b6e89358e7e2d067406"},"schema_version":"1.0","source":{"id":"2312.04078","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04078","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04078v3","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04078","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"XJZU2DOEFZNF","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"XJZU2DOEFZNF66WZ","created_at":"2026-07-05T11:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"XJZU2DOE","created_at":"2026-07-05T11:22:29Z"}],"graph_snapshots":[{"event_id":"sha256:0d9ce8599ee4fe765e558e1bb12328c2703d5c58a8a3353b0ec0403b1ab6d8f9","target":"graph","created_at":"2026-07-05T11:22:29Z","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/2312.04078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantifying the similarity between datasets has widespread applications in statistics and machine learning. The performance of a predictive model on novel datasets, referred to as generalizability, depends on how similar the training and evaluation datasets are. Exploiting or transferring insights between similar datasets is a key aspect of meta-learning and transfer-learning. In simulation studies, the similarity between distributions of simulated datasets and real datasets, for which the performance of methods is assessed, is crucial. In two- or $k$-sample testing, it is checked, whether the","authors_text":"Andrea Bommert, Franziska Kappenberg, J\\\"org Rahnenf\\\"uhrer, Marieke Stolte","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-07T06:44:14Z","title":"Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04078","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:b56d0a82f6a4e17a29a7adf1fc87f4eb874fc7db57db82907c68920a88d3a7a5","target":"record","created_at":"2026-07-05T11:22:29Z","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":"af8aa1e14263cf32762fdd949cb3d4684e98a2ef126962900a35e2e89460969a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-07T06:44:14Z","title_canon_sha256":"a3f3ad09030ed1c1c4f8277a0750c0143adb628aff9e6b6e89358e7e2d067406"},"schema_version":"1.0","source":{"id":"2312.04078","kind":"arxiv","version":3}},"canonical_sha256":"ba734d0dc42e5a5f7ad98249320ef7972309a7ad27fb49de60afa5c1f08022e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba734d0dc42e5a5f7ad98249320ef7972309a7ad27fb49de60afa5c1f08022e8","first_computed_at":"2026-07-05T11:22:29.412267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:29.412267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rt7B7KbH7FB6Uk4VmowWo0W81OkjrMForlSG2DvpwrnLlkeiZ7V8SA1D9+69BCamhAklV5YG0GaEHxK/5H7kAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:29.412801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04078","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b56d0a82f6a4e17a29a7adf1fc87f4eb874fc7db57db82907c68920a88d3a7a5","sha256:0d9ce8599ee4fe765e558e1bb12328c2703d5c58a8a3353b0ec0403b1ab6d8f9"],"state_sha256":"27d292886349a766e02de18ed74afb9cc6986b700c22b2484d3b3be3b9be9e98"}