{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EUIG2CWLFRROYFJPQPAR2EZSWJ","short_pith_number":"pith:EUIG2CWL","schema_version":"1.0","canonical_sha256":"25106d0acb2c62ec152f83c11d1332b25dc7f4bfe7d1c3a60f8a292048426639","source":{"kind":"arxiv","id":"1704.01858","version":1},"attestation_state":"computed","paper":{"title":"An Online Hierarchical Algorithm for Extreme Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Andrew McCallum, Ari Kobren, Nicholas Monath","submitted_at":"2017-04-06T14:29:10Z","abstract_excerpt":"Many modern clustering methods scale well to a large number of data items, N, but not to a large number of clusters, K. This paper introduces PERCH, a new non-greedy algorithm for online hierarchical clustering that scales to both massive N and K--a problem setting we term extreme clustering. Our algorithm efficiently routes new data points to the leaves of an incrementally-built tree. Motivated by the desire for both accuracy and speed, our approach performs tree rotations for the sake of enhancing subtree purity and encouraging balancedness. We prove that, under a natural separability assump"},"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":"1704.01858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-06T14:29:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbfe48c69ddca984ce89253320f1e54f05712296afb909be3d2e9a1502b0703e","abstract_canon_sha256":"f3586362335e8c73e4adf319260ff2a6d0545b0a646e513e0f6ed4ada5cdb469"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:54.153723Z","signature_b64":"cOAxoFF2RZUEtO3lZkj/nFZlBak5lFutlI7nV24vyeS6aflAoz7DO7+BTWXcSCUro2EXWD0nhNtHseQH5TNPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25106d0acb2c62ec152f83c11d1332b25dc7f4bfe7d1c3a60f8a292048426639","last_reissued_at":"2026-05-18T00:46:54.153284Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:54.153284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Online Hierarchical Algorithm for Extreme Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Andrew McCallum, Ari Kobren, Nicholas Monath","submitted_at":"2017-04-06T14:29:10Z","abstract_excerpt":"Many modern clustering methods scale well to a large number of data items, N, but not to a large number of clusters, K. This paper introduces PERCH, a new non-greedy algorithm for online hierarchical clustering that scales to both massive N and K--a problem setting we term extreme clustering. Our algorithm efficiently routes new data points to the leaves of an incrementally-built tree. Motivated by the desire for both accuracy and speed, our approach performs tree rotations for the sake of enhancing subtree purity and encouraging balancedness. We prove that, under a natural separability assump"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01858","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":""},"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":"1704.01858","created_at":"2026-05-18T00:46:54.153349+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.01858v1","created_at":"2026-05-18T00:46:54.153349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01858","created_at":"2026-05-18T00:46:54.153349+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUIG2CWLFRRO","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUIG2CWLFRROYFJP","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUIG2CWL","created_at":"2026-05-18T12:31:12.930513+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/EUIG2CWLFRROYFJPQPAR2EZSWJ","json":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ.json","graph_json":"https://pith.science/api/pith-number/EUIG2CWLFRROYFJPQPAR2EZSWJ/graph.json","events_json":"https://pith.science/api/pith-number/EUIG2CWLFRROYFJPQPAR2EZSWJ/events.json","paper":"https://pith.science/paper/EUIG2CWL"},"agent_actions":{"view_html":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ","download_json":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ.json","view_paper":"https://pith.science/paper/EUIG2CWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.01858&json=true","fetch_graph":"https://pith.science/api/pith-number/EUIG2CWLFRROYFJPQPAR2EZSWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EUIG2CWLFRROYFJPQPAR2EZSWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/action/storage_attestation","attest_author":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/action/author_attestation","sign_citation":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/action/citation_signature","submit_replication":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/action/replication_record"}},"created_at":"2026-05-18T00:46:54.153349+00:00","updated_at":"2026-05-18T00:46:54.153349+00:00"}