{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K6GIFYU4YYK4DNHGONDG3TW4FJ","short_pith_number":"pith:K6GIFYU4","schema_version":"1.0","canonical_sha256":"578c82e29cc615c1b4e673466dcedc2a79f83cefd4bcebf43e6cbfa8fa534409","source":{"kind":"arxiv","id":"2501.09591","version":1},"attestation_state":"computed","paper":{"title":"Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation -- Extended Version","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anton D. Lautrup, Arthur Zimek, Muhammad Rajabinasab","submitted_at":"2025-01-16T15:17:27Z","abstract_excerpt":"Measuring inter-dataset similarity is an important task in machine learning and data mining with various use cases and applications. Existing methods for measuring inter-dataset similarity are computationally expensive, limited, or sensitive to different entities and non-trivial choices for parameters. They also lack a holistic perspective on the entire dataset. In this paper, we propose two novel metrics for measuring inter-dataset similarity. We discuss the mathematical foundation and the theoretical basis of our proposed metrics. We demonstrate the effectiveness of the proposed metrics by i"},"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":"2501.09591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"a97df09ba96d7fbe6c5f353ed5ef7253c0b7a4fa1999c46b18756ebb744013f7","abstract_canon_sha256":"e3aa1b3c19876a217971d756162de4850c06172bbb800d5638cef4f3ccd50ddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:22.449375Z","signature_b64":"pPkQTUpER5vEVv8lctFFHHK6vwFcNmVeNdJeVlgEL63j8u0aADNEqHO04Vkgd5XiBTqViXXXu5roma3XQyNmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"578c82e29cc615c1b4e673466dcedc2a79f83cefd4bcebf43e6cbfa8fa534409","last_reissued_at":"2026-07-05T10:58:22.448836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:22.448836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation -- Extended Version","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anton D. Lautrup, Arthur Zimek, Muhammad Rajabinasab","submitted_at":"2025-01-16T15:17:27Z","abstract_excerpt":"Measuring inter-dataset similarity is an important task in machine learning and data mining with various use cases and applications. Existing methods for measuring inter-dataset similarity are computationally expensive, limited, or sensitive to different entities and non-trivial choices for parameters. They also lack a holistic perspective on the entire dataset. In this paper, we propose two novel metrics for measuring inter-dataset similarity. We discuss the mathematical foundation and the theoretical basis of our proposed metrics. We demonstrate the effectiveness of the proposed metrics by i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09591","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/2501.09591/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":"2501.09591","created_at":"2026-07-05T10:58:22.448894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09591v1","created_at":"2026-07-05T10:58:22.448894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09591","created_at":"2026-07-05T10:58:22.448894+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6GIFYU4YYK4","created_at":"2026-07-05T10:58:22.448894+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6GIFYU4YYK4DNHG","created_at":"2026-07-05T10:58:22.448894+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6GIFYU4","created_at":"2026-07-05T10:58:22.448894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.12057","citing_title":"Towards Truly Unsupervised Evaluation of Feature Selection","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ","json":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ.json","graph_json":"https://pith.science/api/pith-number/K6GIFYU4YYK4DNHGONDG3TW4FJ/graph.json","events_json":"https://pith.science/api/pith-number/K6GIFYU4YYK4DNHGONDG3TW4FJ/events.json","paper":"https://pith.science/paper/K6GIFYU4"},"agent_actions":{"view_html":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ","download_json":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ.json","view_paper":"https://pith.science/paper/K6GIFYU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09591&json=true","fetch_graph":"https://pith.science/api/pith-number/K6GIFYU4YYK4DNHGONDG3TW4FJ/graph.json","fetch_events":"https://pith.science/api/pith-number/K6GIFYU4YYK4DNHGONDG3TW4FJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/action/storage_attestation","attest_author":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/action/author_attestation","sign_citation":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/action/citation_signature","submit_replication":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/action/replication_record"}},"created_at":"2026-07-05T10:58:22.448894+00:00","updated_at":"2026-07-05T10:58:22.448894+00:00"}