{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:37QRJHDKOXOFVZOYJNQ6PQY2DW","short_pith_number":"pith:37QRJHDK","schema_version":"1.0","canonical_sha256":"dfe1149c6a75dc5ae5d84b61e7c31a1d8b1e2db53d08f423bb619141f4e152a9","source":{"kind":"arxiv","id":"1610.08738","version":4},"attestation_state":"computed","paper":{"title":"Compressive K-means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nicolas Keriven (PANAMA), Nicolas Tremblay (GIPSA-CICS), R\\'emi Gribonval (PANAMA), Yann Traonmilin (PANAMA)","submitted_at":"2016-10-27T12:13:05Z","abstract_excerpt":"The Lloyd-Max algorithm is a classical approach to perform K-means clustering. Unfortunately, its cost becomes prohibitive as the training dataset grows large. We propose a compressive version of K-means (CKM), that estimates cluster centers from a sketch, i.e. from a drastically compressed representation of the training dataset. We demonstrate empirically that CKM performs similarly to Lloyd-Max, for a sketch size proportional to the number of cen-troids times the ambient dimension, and independent of the size of the original dataset. Given the sketch, the computational complexity of CKM is 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":"1610.08738","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-27T12:13:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"211b4f26113c3728d4ec908e63ece16c093c6fc7ae84f7e34c224080be09b59d","abstract_canon_sha256":"ba809aa057cf3e5d2f2395e45e1f9d3e812c93af4851569b41280cab7f9ad2f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:59.330143Z","signature_b64":"XHlC5QIcS3IsN2feZyWyux5OH1Ib0999VsgSQbCFMQC/uCTp9vBUq/XYyVnPCMUcodYb7EqIiJQH3bb8TGTWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfe1149c6a75dc5ae5d84b61e7c31a1d8b1e2db53d08f423bb619141f4e152a9","last_reissued_at":"2026-05-18T00:50:59.329581Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:59.329581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressive K-means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nicolas Keriven (PANAMA), Nicolas Tremblay (GIPSA-CICS), R\\'emi Gribonval (PANAMA), Yann Traonmilin (PANAMA)","submitted_at":"2016-10-27T12:13:05Z","abstract_excerpt":"The Lloyd-Max algorithm is a classical approach to perform K-means clustering. Unfortunately, its cost becomes prohibitive as the training dataset grows large. We propose a compressive version of K-means (CKM), that estimates cluster centers from a sketch, i.e. from a drastically compressed representation of the training dataset. We demonstrate empirically that CKM performs similarly to Lloyd-Max, for a sketch size proportional to the number of cen-troids times the ambient dimension, and independent of the size of the original dataset. Given the sketch, the computational complexity of CKM is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.08738","kind":"arxiv","version":4},"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":"1610.08738","created_at":"2026-05-18T00:50:59.329673+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.08738v4","created_at":"2026-05-18T00:50:59.329673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.08738","created_at":"2026-05-18T00:50:59.329673+00:00"},{"alias_kind":"pith_short_12","alias_value":"37QRJHDKOXOF","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"37QRJHDKOXOFVZOY","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"37QRJHDK","created_at":"2026-05-18T12:29:55.572404+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/37QRJHDKOXOFVZOYJNQ6PQY2DW","json":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW.json","graph_json":"https://pith.science/api/pith-number/37QRJHDKOXOFVZOYJNQ6PQY2DW/graph.json","events_json":"https://pith.science/api/pith-number/37QRJHDKOXOFVZOYJNQ6PQY2DW/events.json","paper":"https://pith.science/paper/37QRJHDK"},"agent_actions":{"view_html":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW","download_json":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW.json","view_paper":"https://pith.science/paper/37QRJHDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.08738&json=true","fetch_graph":"https://pith.science/api/pith-number/37QRJHDKOXOFVZOYJNQ6PQY2DW/graph.json","fetch_events":"https://pith.science/api/pith-number/37QRJHDKOXOFVZOYJNQ6PQY2DW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW/action/storage_attestation","attest_author":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW/action/author_attestation","sign_citation":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW/action/citation_signature","submit_replication":"https://pith.science/pith/37QRJHDKOXOFVZOYJNQ6PQY2DW/action/replication_record"}},"created_at":"2026-05-18T00:50:59.329673+00:00","updated_at":"2026-05-18T00:50:59.329673+00:00"}