{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A3TTUCGZQASIIFTKB33WRAZT5I","short_pith_number":"pith:A3TTUCGZ","schema_version":"1.0","canonical_sha256":"06e73a08d9802484166a0ef7688333ea17811054117f43c1d0a3fed9a96848e7","source":{"kind":"arxiv","id":"2109.05180","version":1},"attestation_state":"computed","paper":{"title":"A Novel Intrinsic Measure of Data Separability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Murray Loew, Shuyue Guan","submitted_at":"2021-09-11T04:20:08Z","abstract_excerpt":"In machine learning, the performance of a classifier depends on both the classifier model and the separability/complexity of datasets. To quantitatively measure the separability of datasets, we create an intrinsic measure -- the Distance-based Separability Index (DSI), which is independent of the classifier model. We consider the situation in which different classes of data are mixed in the same distribution to be the most difficult for classifiers to separate. We then formally show that the DSI can indicate whether the distributions of datasets are identical for any dimensionality. And we ver"},"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":"2109.05180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-11T04:20:08Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"b5ec97b9a1f55381cce41ff3ba942b0a81e41a2ec7bba4bf6e5f9b43d5fa9243","abstract_canon_sha256":"e9315565d9a6fc8585228f9bfe7d712ebdf26f6dd7f2096d2647a80919fd0075"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:35.930722Z","signature_b64":"xgAgf0BuQVe7xBHsFvTkO+8+w20MCxMzFKDTXt+c5VB9L3JM+trrKFRpYVaHjY5YxFMXqHaAd6Baf2bRTQFuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06e73a08d9802484166a0ef7688333ea17811054117f43c1d0a3fed9a96848e7","last_reissued_at":"2026-07-05T03:13:35.930296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:35.930296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel Intrinsic Measure of Data Separability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Murray Loew, Shuyue Guan","submitted_at":"2021-09-11T04:20:08Z","abstract_excerpt":"In machine learning, the performance of a classifier depends on both the classifier model and the separability/complexity of datasets. To quantitatively measure the separability of datasets, we create an intrinsic measure -- the Distance-based Separability Index (DSI), which is independent of the classifier model. We consider the situation in which different classes of data are mixed in the same distribution to be the most difficult for classifiers to separate. We then formally show that the DSI can indicate whether the distributions of datasets are identical for any dimensionality. And we ver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05180","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/2109.05180/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":"2109.05180","created_at":"2026-07-05T03:13:35.930358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05180v1","created_at":"2026-07-05T03:13:35.930358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05180","created_at":"2026-07-05T03:13:35.930358+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3TTUCGZQASI","created_at":"2026-07-05T03:13:35.930358+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3TTUCGZQASIIFTK","created_at":"2026-07-05T03:13:35.930358+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3TTUCGZ","created_at":"2026-07-05T03:13:35.930358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I","json":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I.json","graph_json":"https://pith.science/api/pith-number/A3TTUCGZQASIIFTKB33WRAZT5I/graph.json","events_json":"https://pith.science/api/pith-number/A3TTUCGZQASIIFTKB33WRAZT5I/events.json","paper":"https://pith.science/paper/A3TTUCGZ"},"agent_actions":{"view_html":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I","download_json":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I.json","view_paper":"https://pith.science/paper/A3TTUCGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05180&json=true","fetch_graph":"https://pith.science/api/pith-number/A3TTUCGZQASIIFTKB33WRAZT5I/graph.json","fetch_events":"https://pith.science/api/pith-number/A3TTUCGZQASIIFTKB33WRAZT5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I/action/storage_attestation","attest_author":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I/action/author_attestation","sign_citation":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I/action/citation_signature","submit_replication":"https://pith.science/pith/A3TTUCGZQASIIFTKB33WRAZT5I/action/replication_record"}},"created_at":"2026-07-05T03:13:35.930358+00:00","updated_at":"2026-07-05T03:13:35.930358+00:00"}