{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M2Y2CJZBSGSGZOPNBAN2NCE64V","short_pith_number":"pith:M2Y2CJZB","schema_version":"1.0","canonical_sha256":"66b1a1272191a46cb9ed081ba6889ee5732ecb4579bd47d5cf63b72e1d8f516e","source":{"kind":"arxiv","id":"2107.00798","version":2},"attestation_state":"computed","paper":{"title":"Near-optimal Algorithms for Explainable k-Medians and k-Means","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Konstantin Makarychev, Liren Shan","submitted_at":"2021-07-02T02:07:12Z","abstract_excerpt":"We consider the problem of explainable $k$-medians and $k$-means introduced by Dasgupta, Frost, Moshkovitz, and Rashtchian~(ICML 2020). In this problem, our goal is to find a threshold decision tree that partitions data into $k$ clusters and minimizes the $k$-medians or $k$-means objective. The obtained clustering is easy to interpret because every decision node of a threshold tree splits data based on a single feature into two groups. We propose a new algorithm for this problem which is $\\tilde O(\\log k)$ competitive with $k$-medians with $\\ell_1$ norm and $\\tilde O(k)$ competitive with $k$-m"},"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":"2107.00798","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2021-07-02T02:07:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae9f4c7c9cdd4bfb1ae9483533188020574aca9c7d25f7c24cf2288b438ca5de","abstract_canon_sha256":"7bb4d3c8259e9d130bd95b5a75ef4b74bcaa5f4fe5667438c8fe8658ed801480"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:56.511686Z","signature_b64":"6deokPeOkiAMdJyHOAZqceQy5Vm9aKgR3GVqJn3Pw6Ne3eV52BClD6zvdKzyAPYaBTw1z/jnfjkMKFtLWSR/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66b1a1272191a46cb9ed081ba6889ee5732ecb4579bd47d5cf63b72e1d8f516e","last_reissued_at":"2026-07-05T03:02:56.511286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:56.511286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-optimal Algorithms for Explainable k-Medians and k-Means","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Konstantin Makarychev, Liren Shan","submitted_at":"2021-07-02T02:07:12Z","abstract_excerpt":"We consider the problem of explainable $k$-medians and $k$-means introduced by Dasgupta, Frost, Moshkovitz, and Rashtchian~(ICML 2020). In this problem, our goal is to find a threshold decision tree that partitions data into $k$ clusters and minimizes the $k$-medians or $k$-means objective. The obtained clustering is easy to interpret because every decision node of a threshold tree splits data based on a single feature into two groups. We propose a new algorithm for this problem which is $\\tilde O(\\log k)$ competitive with $k$-medians with $\\ell_1$ norm and $\\tilde O(k)$ competitive with $k$-m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00798","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/2107.00798/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":"2107.00798","created_at":"2026-07-05T03:02:56.511349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00798v2","created_at":"2026-07-05T03:02:56.511349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00798","created_at":"2026-07-05T03:02:56.511349+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2Y2CJZBSGSG","created_at":"2026-07-05T03:02:56.511349+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2Y2CJZBSGSGZOPN","created_at":"2026-07-05T03:02:56.511349+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2Y2CJZB","created_at":"2026-07-05T03:02:56.511349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08197","citing_title":"Self-Explaining Segment Trees: A KPI-Conditioned Segmentation Framework for Business Analytics with Node-Level Explanation via Recursive Subspace Partitioning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V","json":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V.json","graph_json":"https://pith.science/api/pith-number/M2Y2CJZBSGSGZOPNBAN2NCE64V/graph.json","events_json":"https://pith.science/api/pith-number/M2Y2CJZBSGSGZOPNBAN2NCE64V/events.json","paper":"https://pith.science/paper/M2Y2CJZB"},"agent_actions":{"view_html":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V","download_json":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V.json","view_paper":"https://pith.science/paper/M2Y2CJZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00798&json=true","fetch_graph":"https://pith.science/api/pith-number/M2Y2CJZBSGSGZOPNBAN2NCE64V/graph.json","fetch_events":"https://pith.science/api/pith-number/M2Y2CJZBSGSGZOPNBAN2NCE64V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V/action/storage_attestation","attest_author":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V/action/author_attestation","sign_citation":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V/action/citation_signature","submit_replication":"https://pith.science/pith/M2Y2CJZBSGSGZOPNBAN2NCE64V/action/replication_record"}},"created_at":"2026-07-05T03:02:56.511349+00:00","updated_at":"2026-07-05T03:02:56.511349+00:00"}