{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K6GIFYU4YYK4DNHGONDG3TW4FJ","short_pith_number":"pith:K6GIFYU4","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"},"canonical_sha256":"578c82e29cc615c1b4e673466dcedc2a79f83cefd4bcebf43e6cbfa8fa534409","source":{"kind":"arxiv","id":"2501.09591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09591","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09591v1","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09591","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"K6GIFYU4YYK4","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"K6GIFYU4YYK4DNHG","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"K6GIFYU4","created_at":"2026-07-05T10:58:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K6GIFYU4YYK4DNHGONDG3TW4FJ","target":"record","payload":{"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"},"canonical_sha256":"578c82e29cc615c1b4e673466dcedc2a79f83cefd4bcebf43e6cbfa8fa534409","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"},"source_kind":"arxiv","source_id":"2501.09591","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/lWd60cuue779EVR2dcaiuoQsXO1Py9WRBuuYq806w48fTg16bdElf7CALOl8mQPuEKjBkEVkj2KTpbbEcACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:36:51.445607Z"},"content_sha256":"a1f0ceb2ebc597c97cb5507fb36182fbd3c4e4be8fa2eac3c4d421ff4818b886","schema_version":"1.0","event_id":"sha256:a1f0ceb2ebc597c97cb5507fb36182fbd3c4e4be8fa2eac3c4d421ff4818b886"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K6GIFYU4YYK4DNHGONDG3TW4FJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UD9qWNeU7hGWNkFiLLms6lAb9OGyYrHvrK3A6ONa2NdVY53Qzf7Hu/mqRrMN1W/CTDjao3OWvklhXSvamR8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:36:51.446003Z"},"content_sha256":"aed2ee67cec4a3a1da98bb6711fa93cbea8ecb1ab025074727648fe382823349","schema_version":"1.0","event_id":"sha256:aed2ee67cec4a3a1da98bb6711fa93cbea8ecb1ab025074727648fe382823349"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/bundle.json","state_url":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T06:36:51Z","links":{"resolver":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ","bundle":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/bundle.json","state":"https://pith.science/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6GIFYU4YYK4DNHGONDG3TW4FJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K6GIFYU4YYK4DNHGONDG3TW4FJ","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":"e3aa1b3c19876a217971d756162de4850c06172bbb800d5638cef4f3ccd50ddf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:17:27Z","title_canon_sha256":"a97df09ba96d7fbe6c5f353ed5ef7253c0b7a4fa1999c46b18756ebb744013f7"},"schema_version":"1.0","source":{"id":"2501.09591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09591","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09591v1","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09591","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"K6GIFYU4YYK4","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"K6GIFYU4YYK4DNHG","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"K6GIFYU4","created_at":"2026-07-05T10:58:22Z"}],"graph_snapshots":[{"event_id":"sha256:aed2ee67cec4a3a1da98bb6711fa93cbea8ecb1ab025074727648fe382823349","target":"graph","created_at":"2026-07-05T10:58:22Z","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/2501.09591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anton D. Lautrup, Arthur Zimek, Muhammad Rajabinasab","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:17:27Z","title":"Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation -- Extended Version"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09591","kind":"arxiv","version":1},"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:a1f0ceb2ebc597c97cb5507fb36182fbd3c4e4be8fa2eac3c4d421ff4818b886","target":"record","created_at":"2026-07-05T10:58:22Z","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":"e3aa1b3c19876a217971d756162de4850c06172bbb800d5638cef4f3ccd50ddf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:17:27Z","title_canon_sha256":"a97df09ba96d7fbe6c5f353ed5ef7253c0b7a4fa1999c46b18756ebb744013f7"},"schema_version":"1.0","source":{"id":"2501.09591","kind":"arxiv","version":1}},"canonical_sha256":"578c82e29cc615c1b4e673466dcedc2a79f83cefd4bcebf43e6cbfa8fa534409","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"578c82e29cc615c1b4e673466dcedc2a79f83cefd4bcebf43e6cbfa8fa534409","first_computed_at":"2026-07-05T10:58:22.448836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:22.448836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pPkQTUpER5vEVv8lctFFHHK6vwFcNmVeNdJeVlgEL63j8u0aADNEqHO04Vkgd5XiBTqViXXXu5roma3XQyNmAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:22.449375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1f0ceb2ebc597c97cb5507fb36182fbd3c4e4be8fa2eac3c4d421ff4818b886","sha256:aed2ee67cec4a3a1da98bb6711fa93cbea8ecb1ab025074727648fe382823349"],"state_sha256":"995b8165d028b31d93cc72bd0bcc015bcf84df74038e7dbeab76577554fbd734"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ptaC1/lDGo6HmSAirWRP7okPpNW2vsZ4OrH9kZkyOoT/1J0k4WisQi8bF56kCn7Jzpdx+flcPIjhxzwhl58Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:36:51.447979Z","bundle_sha256":"75626d1263977219f6965d2576b26a110b982c3a13e99239510dfd4f27f358cd"}}