{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:IMSGUSZGCKRFNALSKMSNRED7QO","short_pith_number":"pith:IMSGUSZG","schema_version":"1.0","canonical_sha256":"43246a4b2612a25681725324d8907f839af8d0ec2c7a608750e27b03a767c955","source":{"kind":"arxiv","id":"1511.08990","version":2},"attestation_state":"computed","paper":{"title":"k-Means for Streaming and Distributed Big Sparse Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Artem Barger, Dan Feldman","submitted_at":"2015-11-29T10:06:11Z","abstract_excerpt":"We provide the first streaming algorithm for computing a provable approximation to the $k$-means of sparse Big data. Here, sparse Big Data is a set of $n$ vectors in $\\mathbb{R}^d$, where each vector has $O(1)$ non-zeroes entries, and $d\\geq n$. E.g., adjacency matrix of a graph, web-links, social network, document-terms, or image-features matrices.\n  Our streaming algorithm stores at most $\\log n\\cdot k^{O(1)}$ input points in memory. If the stream is distributed among $M$ machines, the running time reduces by a factor of $M$, while communicating a total of $M\\cdot k^{O(1)}$ (sparse) input po"},"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":"1511.08990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-11-29T10:06:11Z","cross_cats_sorted":[],"title_canon_sha256":"5c8a88b87c77e7d41122241096b721d40129eded80513d96db0161f0b2649cce","abstract_canon_sha256":"ad2521e7bbf804397cea315a34225cee3af87c1a033d8f82ced92002bbb31ffc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:11.124535Z","signature_b64":"D/u7q+tZ78j/BIq0ejjbjMmTRpwWPVOHFG2U9KbU3TQR53i4zhtrkGp5Fj6fYASZ7kRLc1P6HZWZTsRG9zOuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43246a4b2612a25681725324d8907f839af8d0ec2c7a608750e27b03a767c955","last_reissued_at":"2026-05-18T01:21:11.123925Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:11.123925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"k-Means for Streaming and Distributed Big Sparse Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Artem Barger, Dan Feldman","submitted_at":"2015-11-29T10:06:11Z","abstract_excerpt":"We provide the first streaming algorithm for computing a provable approximation to the $k$-means of sparse Big data. Here, sparse Big Data is a set of $n$ vectors in $\\mathbb{R}^d$, where each vector has $O(1)$ non-zeroes entries, and $d\\geq n$. E.g., adjacency matrix of a graph, web-links, social network, document-terms, or image-features matrices.\n  Our streaming algorithm stores at most $\\log n\\cdot k^{O(1)}$ input points in memory. If the stream is distributed among $M$ machines, the running time reduces by a factor of $M$, while communicating a total of $M\\cdot k^{O(1)}$ (sparse) input po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08990","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":"1511.08990","created_at":"2026-05-18T01:21:11.124011+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.08990v2","created_at":"2026-05-18T01:21:11.124011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08990","created_at":"2026-05-18T01:21:11.124011+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMSGUSZGCKRF","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMSGUSZGCKRFNALS","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMSGUSZG","created_at":"2026-05-18T12:29:25.134429+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/IMSGUSZGCKRFNALSKMSNRED7QO","json":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO.json","graph_json":"https://pith.science/api/pith-number/IMSGUSZGCKRFNALSKMSNRED7QO/graph.json","events_json":"https://pith.science/api/pith-number/IMSGUSZGCKRFNALSKMSNRED7QO/events.json","paper":"https://pith.science/paper/IMSGUSZG"},"agent_actions":{"view_html":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO","download_json":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO.json","view_paper":"https://pith.science/paper/IMSGUSZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.08990&json=true","fetch_graph":"https://pith.science/api/pith-number/IMSGUSZGCKRFNALSKMSNRED7QO/graph.json","fetch_events":"https://pith.science/api/pith-number/IMSGUSZGCKRFNALSKMSNRED7QO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/action/storage_attestation","attest_author":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/action/author_attestation","sign_citation":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/action/citation_signature","submit_replication":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/action/replication_record"}},"created_at":"2026-05-18T01:21:11.124011+00:00","updated_at":"2026-05-18T01:21:11.124011+00:00"}