{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XJZU2DOEFZNF66WZQJETEDXXS4","short_pith_number":"pith:XJZU2DOE","schema_version":"1.0","canonical_sha256":"ba734d0dc42e5a5f7ad98249320ef7972309a7ad27fb49de60afa5c1f08022e8","source":{"kind":"arxiv","id":"2312.04078","version":3},"attestation_state":"computed","paper":{"title":"Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Andrea Bommert, Franziska Kappenberg, J\\\"org Rahnenf\\\"uhrer, Marieke Stolte","submitted_at":"2023-12-07T06:44:14Z","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"},"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":"2312.04078","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-07T06:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"a3f3ad09030ed1c1c4f8277a0750c0143adb628aff9e6b6e89358e7e2d067406","abstract_canon_sha256":"af8aa1e14263cf32762fdd949cb3d4684e98a2ef126962900a35e2e89460969a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:29.412801Z","signature_b64":"rt7B7KbH7FB6Uk4VmowWo0W81OkjrMForlSG2DvpwrnLlkeiZ7V8SA1D9+69BCamhAklV5YG0GaEHxK/5H7kAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba734d0dc42e5a5f7ad98249320ef7972309a7ad27fb49de60afa5c1f08022e8","last_reissued_at":"2026-07-05T11:22:29.412267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:29.412267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Andrea Bommert, Franziska Kappenberg, J\\\"org Rahnenf\\\"uhrer, Marieke Stolte","submitted_at":"2023-12-07T06:44:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04078","kind":"arxiv","version":3},"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/2312.04078/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2312.04078","created_at":"2026-07-05T11:22:29.412338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04078v3","created_at":"2026-07-05T11:22:29.412338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04078","created_at":"2026-07-05T11:22:29.412338+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJZU2DOEFZNF","created_at":"2026-07-05T11:22:29.412338+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJZU2DOEFZNF66WZ","created_at":"2026-07-05T11:22:29.412338+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJZU2DOE","created_at":"2026-07-05T11:22:29.412338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09591","citing_title":"Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation -- Extended Version","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4","json":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4.json","graph_json":"https://pith.science/api/pith-number/XJZU2DOEFZNF66WZQJETEDXXS4/graph.json","events_json":"https://pith.science/api/pith-number/XJZU2DOEFZNF66WZQJETEDXXS4/events.json","paper":"https://pith.science/paper/XJZU2DOE"},"agent_actions":{"view_html":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4","download_json":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4.json","view_paper":"https://pith.science/paper/XJZU2DOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04078&json=true","fetch_graph":"https://pith.science/api/pith-number/XJZU2DOEFZNF66WZQJETEDXXS4/graph.json","fetch_events":"https://pith.science/api/pith-number/XJZU2DOEFZNF66WZQJETEDXXS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4/action/storage_attestation","attest_author":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4/action/author_attestation","sign_citation":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4/action/citation_signature","submit_replication":"https://pith.science/pith/XJZU2DOEFZNF66WZQJETEDXXS4/action/replication_record"}},"created_at":"2026-07-05T11:22:29.412338+00:00","updated_at":"2026-07-05T11:22:29.412338+00:00"}