{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MFMK5OSG6IMRTV3RZ37PGT6NAH","short_pith_number":"pith:MFMK5OSG","schema_version":"1.0","canonical_sha256":"6158aeba46f21919d771cefef34fcd01c938d9527c41137fb5bb682844f1b362","source":{"kind":"arxiv","id":"2502.02668","version":2},"attestation_state":"computed","paper":{"title":"Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debarghya Ghoshdastidar, Martin Eppert, Satyaki Mukherjee","submitted_at":"2025-02-04T19:18:17Z","abstract_excerpt":"Projection Pursuit is a classic exploratory technique for finding interesting projections of a dataset. We propose a method for recovering projections containing either Imbalanced Clusters or a Bernoulli-Rademacher distribution using a gradient-based technique to optimize the projection index. As sample complexity is a major limiting factor in Projection Pursuit, we analyze our algorithm's sample complexity within a Planted Vector setting where we can observe that Imbalanced Clusters can be recovered more easily than balanced ones. Additionally, we give a generalized result that works for a va"},"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":"2502.02668","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T19:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"bbb8ac9586ba973c05edcc79cbe36ce876cca4cd5e607c27f49b14e86ffb32e0","abstract_canon_sha256":"a9aadc4a544f3d3050c3cb9f8996511b6b4d0287caffd56e1725396aa61da760"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:06.559420Z","signature_b64":"zQ+D0ico7pDusx7uH3EuJNzMM57uYzQjDUDckQNXLSQ9AgPwOU5ZuQ03QCXNV+afDB5iwfN9tflqmkzRSlN9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6158aeba46f21919d771cefef34fcd01c938d9527c41137fb5bb682844f1b362","last_reissued_at":"2026-07-05T11:29:06.558792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:06.558792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debarghya Ghoshdastidar, Martin Eppert, Satyaki Mukherjee","submitted_at":"2025-02-04T19:18:17Z","abstract_excerpt":"Projection Pursuit is a classic exploratory technique for finding interesting projections of a dataset. We propose a method for recovering projections containing either Imbalanced Clusters or a Bernoulli-Rademacher distribution using a gradient-based technique to optimize the projection index. As sample complexity is a major limiting factor in Projection Pursuit, we analyze our algorithm's sample complexity within a Planted Vector setting where we can observe that Imbalanced Clusters can be recovered more easily than balanced ones. Additionally, we give a generalized result that works for a va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02668","kind":"arxiv","version":2},"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/2502.02668/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":"2502.02668","created_at":"2026-07-05T11:29:06.558877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02668v2","created_at":"2026-07-05T11:29:06.558877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02668","created_at":"2026-07-05T11:29:06.558877+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFMK5OSG6IMR","created_at":"2026-07-05T11:29:06.558877+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFMK5OSG6IMRTV3R","created_at":"2026-07-05T11:29:06.558877+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFMK5OSG","created_at":"2026-07-05T11:29:06.558877+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/MFMK5OSG6IMRTV3RZ37PGT6NAH","json":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH.json","graph_json":"https://pith.science/api/pith-number/MFMK5OSG6IMRTV3RZ37PGT6NAH/graph.json","events_json":"https://pith.science/api/pith-number/MFMK5OSG6IMRTV3RZ37PGT6NAH/events.json","paper":"https://pith.science/paper/MFMK5OSG"},"agent_actions":{"view_html":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH","download_json":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH.json","view_paper":"https://pith.science/paper/MFMK5OSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02668&json=true","fetch_graph":"https://pith.science/api/pith-number/MFMK5OSG6IMRTV3RZ37PGT6NAH/graph.json","fetch_events":"https://pith.science/api/pith-number/MFMK5OSG6IMRTV3RZ37PGT6NAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH/action/storage_attestation","attest_author":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH/action/author_attestation","sign_citation":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH/action/citation_signature","submit_replication":"https://pith.science/pith/MFMK5OSG6IMRTV3RZ37PGT6NAH/action/replication_record"}},"created_at":"2026-07-05T11:29:06.558877+00:00","updated_at":"2026-07-05T11:29:06.558877+00:00"}