{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:TLVI2WXHGZZAKU47EWAN36F23V","short_pith_number":"pith:TLVI2WXH","schema_version":"1.0","canonical_sha256":"9aea8d5ae7367205539f2580ddf8badd55b7b15900ab057c0dce9f49226d618c","source":{"kind":"arxiv","id":"1504.01294","version":2},"attestation_state":"computed","paper":{"title":"A Probabilistic $\\ell_1$ Method for Clustering High Dimensional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Adi Ben-Israel, Tsvetan Asamov","submitted_at":"2015-04-06T14:49:13Z","abstract_excerpt":"In general, the clustering problem is NP-hard, and global optimality cannot be established for non-trivial instances. For high-dimensional data, distance-based methods for clustering or classification face an additional difficulty, the unreliability of distances in very high-dimensional spaces. We propose a distance-based iterative method for clustering data in very high-dimensional space, using the $\\ell_1$-metric that is less sensitive to high dimensionality than the Euclidean distance. For $K$ clusters in $\\mathbb{R}^n$, the problem decomposes to $K$ problems coupled by probabilities, and a"},"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":"1504.01294","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2015-04-06T14:49:13Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML","stat.TH"],"title_canon_sha256":"eb54f699bb4c4d0ff93d6ecd8434617084c2d81ef8f22ac282b42eeff242c8cb","abstract_canon_sha256":"98d109bbbedcc3766a6bcdf9b8de6bf27fafe13f242e35e527dc2a491de7c174"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:26.488209Z","signature_b64":"Z3a4cLoJtNGfOzVmKKHslgSQHORhuv7PmR4aAEM7TEGuxmvxLaZD0EGvzIjnNkUt1SIj0sLdo3p1HUYJ8CoIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aea8d5ae7367205539f2580ddf8badd55b7b15900ab057c0dce9f49226d618c","last_reissued_at":"2026-05-18T01:16:26.487486Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:26.487486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Probabilistic $\\ell_1$ Method for Clustering High Dimensional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Adi Ben-Israel, Tsvetan Asamov","submitted_at":"2015-04-06T14:49:13Z","abstract_excerpt":"In general, the clustering problem is NP-hard, and global optimality cannot be established for non-trivial instances. For high-dimensional data, distance-based methods for clustering or classification face an additional difficulty, the unreliability of distances in very high-dimensional spaces. We propose a distance-based iterative method for clustering data in very high-dimensional space, using the $\\ell_1$-metric that is less sensitive to high dimensionality than the Euclidean distance. For $K$ clusters in $\\mathbb{R}^n$, the problem decomposes to $K$ problems coupled by probabilities, and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.01294","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":""},"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":"1504.01294","created_at":"2026-05-18T01:16:26.487596+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.01294v2","created_at":"2026-05-18T01:16:26.487596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.01294","created_at":"2026-05-18T01:16:26.487596+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLVI2WXHGZZA","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLVI2WXHGZZAKU47","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLVI2WXH","created_at":"2026-05-18T12:29:42.218222+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/TLVI2WXHGZZAKU47EWAN36F23V","json":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V.json","graph_json":"https://pith.science/api/pith-number/TLVI2WXHGZZAKU47EWAN36F23V/graph.json","events_json":"https://pith.science/api/pith-number/TLVI2WXHGZZAKU47EWAN36F23V/events.json","paper":"https://pith.science/paper/TLVI2WXH"},"agent_actions":{"view_html":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V","download_json":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V.json","view_paper":"https://pith.science/paper/TLVI2WXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.01294&json=true","fetch_graph":"https://pith.science/api/pith-number/TLVI2WXHGZZAKU47EWAN36F23V/graph.json","fetch_events":"https://pith.science/api/pith-number/TLVI2WXHGZZAKU47EWAN36F23V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V/action/storage_attestation","attest_author":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V/action/author_attestation","sign_citation":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V/action/citation_signature","submit_replication":"https://pith.science/pith/TLVI2WXHGZZAKU47EWAN36F23V/action/replication_record"}},"created_at":"2026-05-18T01:16:26.487596+00:00","updated_at":"2026-05-18T01:16:26.487596+00:00"}